Paper Digest: NeurIPS 2021 Highlights
To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights / summaries to quickly get the main idea of each paper. Based in New York, Paper Digest is dedicated to producing high-quality text analysis results that people can acturally use on a daily basis. In the past 4 years, we have been serving users across the world with a number of exclusive services on ranking, search, tracking and review. This month we feature Literature Review Generator, which automatically generates literature review around any topic.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: NeurIPS 2021 Highlights
Paper | Author(s) | Code | |
---|---|---|---|
1 | Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. |
Christoph Dann; Teodor Vanislavov Marinov; Mehryar Mohri; Julian Zimmert; | |
2 | Learning One Representation to Optimize All Rewards Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. |
Ahmed Touati; Yann Ollivier; | |
3 | Matrix Factorisation and The Interpretation of Geodesic Distance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given a graph or similarity matrix, we consider the problem of recovering a notion of true distance between the nodes, and so their true positions. |
Nick Whiteley; Annie Gray; Patrick Rubin-Delanchy; | |
4 | UniDoc: Unified Pretraining Framework for Document Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present UniDoc, a new unified pretraining framework for document understanding. |
Jiuxiang Gu; Jason Kuen; Vlad Morariu; Handong Zhao; Rajiv Jain; Nikolaos Barmpalios; Ani Nenkova; Tong Sun; | |
5 | Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To find the answer, we propose a new diagnostic tool — Filter Attribution method based on Integral Gradient (FAIG). |
Liangbin Xie; Xintao Wang; Chao Dong; Zhongang Qi; Ying Shan; | |
6 | Counterfactual Explanations Can Be Manipulated Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce the first framework that describes the vulnerabilities of counterfactual explanations and shows how they can be manipulated. |
Dylan Slack; Anna Hilgard; Himabindu Lakkaraju; Sameer Singh; | |
7 | From Canonical Correlation Analysis to Self-supervised Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. |
Hengrui Zhang; Qitian Wu; Junchi Yan; David Wipf; Philip S. Yu; | |
8 | BAST: Bayesian Additive Regression Spanning Trees for Complex Constrained Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article proposes a Bayesian additive regression spanning trees (BAST) model for nonparametric regression on manifolds, with an emphasis on complex constrained domains or irregularly shaped spaces embedded in Euclidean spaces. |
Zhao Tang Luo; Huiyan Sang; Bani Mallick; | |
9 | Hyperbolic Busemann Learning with Ideal Prototypes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Hyperbolic Busemann Learning. The main idea behind our approach is to position prototypes on the ideal boundary of the Poincar\'{e} ball, which does not require prior label knowledge. |
Mina Ghadimi Atigh; Martin Keller-Ressel; Pascal Mettes; | |
10 | Backward-Compatible Prediction Updates: A Probabilistic Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize the Prediction Update Problem and present an efficient probabilistic approach as answer to the above questions. |
Frederik Tr�uble; Julius von K�gelgen; Matth�us Kleindessner; Francesco Locatello; Bernhard Sch�lkopf; Peter Gehler; | |
11 | Truncated Marginal Neural Ratio Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a neural simulation-based inference algorithm which simultaneously offers simulation efficiency and fast empirical posterior testability, which is unique among modern algorithms. |
Benjamin Miller; Alex Cole; Patrick Forr�; Gilles Louppe; Christoph Weniger; | |
12 | ReAct: Out-of-distribution Detection With Rectified Activations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose ReAct—a simple and effective technique for reducing model overconfidence on OOD data. |
Yiyou Sun; Chuan Guo; Sharon Li; | |
13 | Non-local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new set of non-local relations in order to characterize long-range latent pose interactions, unlike general contrastive relations where positive couplings are limited to a local neighborhood structure. |
Jogendra Nath Kundu; Siddharth Seth; Anirudh Jamkhandi; Pradyumna YM; Varun Jampani; Anirban Chakraborty; Venkatesh Babu R; | |
14 | Fast Training of Neural Lumigraph Representations Using Meta Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by neural variants of image-based rendering, we develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time. |
Alexander Bergman; Petr Kellnhofer; Gordon Wetzstein; | |
15 | Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use dynamical mean field theory techniques to describe analytically the average dynamics of these methods in a prototypical non-convex model: the (spiked) matrix-tensor model. |
Stefano Sarao Mannelli; Pierfrancesco Urbani; | |
16 | Multimodal Few-Shot Learning with Frozen Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present a simple, yet effective, approach for transferring this few-shot learning ability to a multimodal setting (vision and language). |
Maria Tsimpoukelli; Jacob Menick; Serkan Cabi; S. M. Ali Eslami; Oriol Vinyals; Felix Hill; | |
17 | Approximating The Permanent with Deep Rejection Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a randomized approximation scheme for the permanent of a matrix with nonnegative entries. |
Juha Harviainen; Antti R�ysk�; Mikko Koivisto; | |
18 | Revisiting Model Stitching to Compare Neural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit and extend model stitching (Lenc & Vedaldi 2015) as a methodology to study the internal representations of neural networks. |
Yamini Bansal; Preetum Nakkiran; Boaz Barak; | |
19 | AugMax: Adversarial Composition of Random Augmentations for Robust Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we propose a data augmentation framework, termed AugMax, to unify the two aspects of diversity and hardness. |
Haotao N. Wang; Chaowei Xiao; Jean Kossaifi; Zhiding Yu; Anima Anandkumar; Zhangyang Wang; | code |
20 | Habitat 2.0: Training Home Assistants to Rearrange Their Habitat Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. |
Andrew Szot; Alexander Clegg; Eric Undersander; Erik Wijmans; Yili Zhao; John Turner; Noah Maestre; Mustafa Mukadam; Devendra Singh Chaplot; Oleksandr Maksymets; Aaron Gokaslan; Vladim�r Vondru�; Sameer Dharur; Franziska Meier; Wojciech Galuba; Angel Chang; Zsolt Kira; Vladlen Koltun; Jitendra Malik; Manolis Savva; Dhruv Batra; | |
21 | Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we seek to find a $\delta$-invariant algorithm for policy gradient (PG) methods, which performs well regardless of the value of $\delta$. |
Seohong Park; Jaekyeom Kim; Gunhee Kim; | code |
22 | Meta-Learning Reliable Priors in The Function Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Addressing these shortcomings, we introduce a novel meta-learning framework, called F-PACOH, that treats meta-learned priors as stochastic processes and performs meta-level regularization directly in the function space. |
Jonas Rothfuss; Dominique Heyn; jinfan Chen; Andreas Krause; | |
23 | VoiceMixer: Adversarial Voice Style Mixup Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present VoiceMixer which can effectively decompose and transfer voice style through a novel information bottleneck and adversarial feedback. |
Sang-Hoon Lee; Ji-Hoon Kim; Hyunseung Chung; Seong-Whan Lee; | |
24 | Predicting What You Already Know Helps: Provable Self-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper posits a mechanism based on approximate conditional independence to formalize how solving certain pretext tasks can learn representations that provably decrease the sample complexity of downstream supervised tasks. |
Jason D. Lee; Qi Lei; Nikunj Saunshi; JIACHENG ZHUO; | |
25 | Oracle Complexity in Nonsmooth Nonconvex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study nonsmooth nonconvex optimization from an oracle complexity viewpoint, where the algorithm is assumed to be given access only to local information about the function at various points. |
Guy Kornowski; Ohad Shamir; | |
26 | CentripetalText: An Efficient Text Instance Representation for Scene Text Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient text instance representation named CentripetalText (CT), which decomposes text instances into the combination of text kernels and centripetal shifts. |
Tao Sheng; Jie Chen; Zhouhui Lian; | |
27 | Learning to Select Exogenous Events for Marked Temporal Point Process Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To thisend, our goal in this paper is to identify the set of exogenous events from a set ofunlabelled events. |
Ping Zhang; Rishabh Iyer; Ashish Tendulkar; Gaurav Aggarwal; Abir De; | |
28 | DRIVE: One-bit Distributed Mean Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem where $n$ clients transmit $d$-dimensional real-valued vectors using $d(1+o(1))$ bits each, in a manner that allows the receiver to approximately reconstruct their mean. |
Shay Vargaftik; Ran Ben-Basat; Amit Portnoy; Gal Mendelson; Yaniv Ben-Itzhak; Michael Mitzenmacher; | |
29 | Learning Space Partitions for Path Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a novel formal regret analysis for when and why such an adaptive region partitioning scheme works. |
Kevin Yang; Tianjun Zhang; Chris Cummins; Brandon Cui; Benoit Steiner; Linnan Wang; Joseph E. Gonzalez; Dan Klein; Yuandong Tian; | code |
30 | Progressive Feature Interaction Search for Deep Sparse Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we approach this problem with neural architecture search by automatically searching the critical component in DSNs, the feature-interaction layer. |
Chen Gao; Yinfeng Li; Quanming Yao; Depeng Jin; Yong Li; | |
31 | Local Explanation of Dialogue Response Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study model-agnostic explanations of a representative text generation task — dialogue response generation. |
Yi-Lin Tuan; Connor Pryor; Wenhu Chen; Lise Getoor; William Yang Wang; | |
32 | Scalable Inference in SDEs By Direct Matching of The Fokker-Planck-Kolmogorov Equation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this issue by revisiting the classical SDE literature and derive direct approximations to the (typically intractable) Fokker–Planck–Kolmogorov equation by matching moments. |
Arno Solin; Ella Tamir; Prakhar Verma; | |
33 | The Complexity of Bayesian Network Learning: Revisiting The Superstructure Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the parameterized complexity of Bayesian Network Structure Learning (BNSL), a classical problem that has received significant attention in empirical but also purely theoretical studies. |
Robert Ganian; Viktoriia Korchemna; | |
34 | Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an efficient low-rank approximation algorithm for non-negative tensors. |
Kazu Ghalamkari; Mahito Sugiyama; | |
35 | Learning Stochastic Majority Votes By Minimizing A PAC-Bayes Generalization Bound Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties. |
Valentina Zantedeschi; Paul Viallard; Emilie Morvant; R�mi Emonet; Amaury Habrard; Pascal Germain; Benjamin Guedj; | |
36 | Numerical Influence of ReLU'(0) on Backpropagation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the importance of the value of ReLU'(0) for several precision levels (16, 32, 64 bits), on various networks (fully connected, VGG, ResNet) and datasets (MNIST, CIFAR10, SVHN, ImageNet). |
David Bertoin; J�r�me Bolte; S�bastien Gerchinovitz; Edouard Pauwels; | |
37 | A Contrastive Learning Approach for Training Variational Autoencoder Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we propose an energy-based prior defined by the product of a base prior distribution and a reweighting factor, designed to bring the base closer to the aggregate posterior. |
Jyoti Aneja; Alex Schwing; Jan Kautz; Arash Vahdat; | |
38 | What Training Reveals About Neural Network Complexity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training dynamics. |
Andreas Loukas; Marinos Poiitis; Stefanie Jegelka; | |
39 | Class-agnostic Reconstruction of Dynamic Objects from Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos. |
Zhongzheng Ren; Xiaoming Zhao; Alex Schwing; | |
40 | Unique Sparse Decomposition of Low Rank Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the problem of seeking a unique decomposition of a low-rank matrix $Y\in \mathbb{R}^{p\times n}$ that admits a sparse representation. |
Dian Jin; Xin Bing; Yuqian Zhang; | |
41 | Neighborhood Reconstructing Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To simultaneously address the two issues of overfitting and local connectivity, we propose a new graph-based autoencoder, the Neighborhood Reconstructing Autoencoder (NRAE). |
Yonghyeon LEE; Hyeokjun Kwon; Frank Park; | code |
42 | TopicNet: Semantic Graph-Guided Topic Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as inductive bias to influence the learning. |
Zhibin Duan; Yi.shi Xu; Bo Chen; dongsheng wang; Chaojie Wang; Mingyuan Zhou; | |
43 | (Almost) Free Incentivized Exploration from Decentralized Learning Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we break this barrier and study incentivized exploration with multiple and long-term strategic agents, who have more complicated behaviors that often appear in real-world applications. |
Chengshuai Shi; Haifeng Xu; Wei Xiong; Cong Shen; | |
44 | Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a simple sequence model inspired by control systems that generalizes these approaches while addressing their shortcomings. |
Albert Gu; Isys Johnson; Karan Goel; Khaled Saab; Tri Dao; Atri Rudra; Christopher R�; | |
45 | Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. |
Zifeng Wang; Tong Jian; Aria Masoomi; Stratis Ioannidis; Jennifer Dy; | |
46 | T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new prior for high-dimensional parameters with graphical relations, referred to as the Tree-based Low-rank Horseshoe (T-LoHo) model, that generalizes the popular univariate Bayesian horseshoe shrinkage prior to the multivariate setting to detect structured sparsity and smoothness simultaneously. |
Changwoo Lee; Zhao Tang Luo; Huiyan Sang; | |
47 | The Utility of Explainable AI in Ad Hoc Human-Machine Teaming Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present two novel human-subject experiments quantifying the benefits of deploying xAI techniques within a human-machine teaming scenario. |
Rohan Paleja; Muyleng Ghuy; Nadun Ranawaka Arachchige; Reed Jensen; Matthew Gombolay; | |
48 | Subgoal Search For Complex Reasoning Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. |
Konrad Czechowski; Tomasz Odrzyg�zdz; Marek Zbysinski; Michal Zawalski; Krzysztof Olejnik; Yuhuai Wu; Lukasz Kucinski; Piotr Milos; | |
49 | MCMC Variational Inference Via Uncorrected Hamiltonian Annealing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework to use an AIS-like procedure with Uncorrected Hamiltonian MCMC, called Uncorrected Hamiltonian Annealing. |
Tomas Geffner; Justin Domke; | |
50 | Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the cross-modal alignment challenge from a fine-grained perspective. |
Keji He; Yan Huang; Qi Wu; Jianhua Yang; Dong An; Shuanglin Sima; Liang Wang; | code |
51 | A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To answer this question, we perform a large-scale analysis of popular model compression techniques which uncovers several intriguing patterns. |
James Diffenderfer; Brian Bartoldson; Shreya Chaganti; Jize Zhang; Bhavya Kailkhura; | code |
52 | On The Importance of Gradients for Detecting Distributional Shifts in The Wild Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present GradNorm, a simple and effective approach for detecting OOD inputs by utilizing information extracted from the gradient space. |
Rui Huang; Andrew Geng; Sharon Li; | |
53 | Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that approximately preserves the answers to a large collection of statistical queries. |
Terrance Liu; Giuseppe Vietri; Steven Z. Wu; | |
54 | Understanding End-to-End Model-Based Reinforcement Learning Methods As Implicit Parameterization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore such implicit representations of value functions via theory and focused experimentation. |
Clement Gehring; Kenji Kawaguchi; Jiaoyang Huang; Leslie Kaelbling; | |
55 | Mirror Langevin Monte Carlo: The Case Under Isoperimetry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the connection between sampling and optimization, we study a mirror descent analogue of Langevin dynamics and analyze three different discretization schemes, giving nonasymptotic convergence rate under functional inequalities such as Log-Sobolev in the corresponding metric. |
Qijia Jiang; | |
56 | Do Different Tracking Tasks Require Different Appearance Models? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. |
Zhongdao Wang; Hengshuang Zhao; Ya-Li Li; Shengjin Wang; Philip Torr; Luca Bertinetto; | |
57 | Towards Robust Vision By Multi-task Learning on Monkey Visual Cortex Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we successfully leveraged these inductive biases with a multi-task learning approach: we jointly trained a deep network to perform image classification and to predict neural activity in macaque primary visual cortex (V1) in response to the same natural stimuli. |
Shahd Safarani; Arne Nix; Konstantin Willeke; Santiago Cadena; Kelli Restivo; George Denfield; Andreas Tolias; Fabian Sinz; | |
58 | Arbitrary Conditional Distributions with Energy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method, Arbitrary Conditioning with Energy (ACE), that can simultaneously estimate the distribution $p(\mathbf{x}_u \mid \mathbf{x}_o)$ for all possible subsets of unobserved features $\mathbf{x}_u$ and observed features $\mathbf{x}_o$. |
Ryan Strauss; Junier B. Oliva; | |
59 | Learning Domain Invariant Representations in Goal-conditioned Block MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study this problem for goal-conditioned RL agents. |
Beining Han; Chongyi Zheng; Harris Chan; Keiran Paster; Michael Zhang; Jimmy Ba; | |
60 | Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop efficient algorithms for optimizing different objective functions quantifying the informativeness of a budget-constrained batch of experiments. |
Scott Sussex; Caroline Uhler; Andreas Krause; | |
61 | Fuzzy Clustering with Similarity Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a semi-supervised active clustering framework, where the learner is allowed to interact with an oracle (domain expert), asking for the similarity between a certain set of chosen items. |
Wasim Huleihel; Arya Mazumdar; Soumyabrata Pal; | |
62 | Improving Black-box Optimization in VAE Latent Space Using Decoder Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to leverage the epistemic uncertainty of the decoder to guide the optimization process. |
Pascal Notin; Jos� Miguel Hern�ndez-Lobato; Yarin Gal; | |
63 | Sample Selection for Fair and Robust Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a sample selection-based algorithm for fair and robust training. |
Yuji Roh; Kangwook Lee; Steven Whang; Changho Suh; | |
64 | NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes NeurWIN, a neural Whittle index network that seeks to learn the Whittle indices for any restless bandits by leveraging mathematical properties of the Whittle indices. |
Khaled Nakhleh; Santosh Ganji; Ping-Chun Hsieh; I-Hong Hou; Srinivas Shakkottai; | |
65 | Sageflow: Robust Federated Learning Against Both Stragglers and Adversaries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Sageflow, staleness-aware grouping with entropy-based filtering and loss-weighted averaging, to handle both stragglers and adversaries simultaneously. |
Jung Wuk Park; Dong-Jun Han; Minseok Choi; Jaekyun Moon; | |
66 | Alias-Free Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. |
Tero Karras; Miika Aittala; Samuli Laine; Erik H�rk�nen; Janne Hellsten; Jaakko Lehtinen; Timo Aila; | |
67 | Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising Without Clean Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, here we present a novel approach, called Noise2Score, which reveals a missing link in order to unite these seemingly different approaches.Specifically, we show that image denoising problems without clean images can be addressed by finding the mode of the posterior distribution and that the Tweedie’s formula offers an explicit solution through the score function (i.e. the gradient of loglikelihood). |
Kwanyoung Kim; Jong Chul Ye; | |
68 | Continuous Mean-Covariance Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Continuous Mean-Covariance Bandit (CMCB) model to explicitly take into account option correlation. |
Yihan Du; Siwei Wang; Zhixuan Fang; Longbo Huang; | |
69 | Dynamic Visual Reasoning By Learning Differentiable Physics Models from Video and Language Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects and their interactions from videos and language. |
Mingyu Ding; Zhenfang Chen; Tao Du; Ping Luo; Josh Tenenbaum; Chuang Gan; | |
70 | Solving Soft Clustering Ensemble Via $k$-Sparse Discrete Wasserstein Barycenter Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the more general soft clustering ensemble problem where each individual solution is a soft clustering. |
Ruizhe Qin; Mengying Li; Hu Ding; | |
71 | Bayesian Adaptation for Covariate Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters, and show how approximate inference in this model can be instantiated with a simple regularized entropy minimization procedure at test-time. |
Aurick Zhou; Sergey Levine; | |
72 | Perturb-and-max-product: Sampling and Learning in Discrete Energy-based Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present perturb-and-max-product (PMP), a parallel and scalable mechanism for sampling and learning in discrete EBMs. |
Miguel Lazaro-Gredilla; Antoine Dedieu; Dileep George; | |
73 | Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we summarize previous concepts of diversity and work towards offering a unified measure of diversity in multi-agent open-ended learning to include all elements in Markov games, based on both Behavioral Diversity (BD) and Response Diversity (RD). |
Xiangyu Liu; Hangtian Jia; Ying Wen; Yaodong Yang; Yujing Hu; Yingfeng Chen; Changjie Fan; ZHIPENG HU; | |
74 | Towards Better Understanding of Training Certifiably Robust Models Against Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of training certifiably robust models against adversarial examples. |
Sungyoon Lee; WOOJIN LEE; Jinseong Park; Jaewook Lee; | code |
75 | Mitigating Covariate Shift in Imitation Learning Via Offline Data With Partial Coverage Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Model-based IL from Offline data (MILO): an algorithmic framework that utilizes the static dataset to solve the offline IL problem efficiently both in theory and in practice. |
Jonathan Chang; Masatoshi Uehara; Dhruv Sreenivas; Rahul Kidambi; Wen Sun; | code |
76 | Global Filter Networks for Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity. |
Yongming Rao; Wenliang Zhao; Zheng Zhu; Jiwen Lu; Jie Zhou; | code |
77 | Catastrophic Data Leakage in Vertical Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. |
Xiao Jin; Pin-Yu Chen; Chia-Yi Hsu; Chia-Mu Yu; Tianyi Chen; | code |
78 | Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this end, we propose the first FRL framework the convergence of which is guaranteed and tolerant to less than half of the participating agents being random system failures or adversarial attackers. |
Xiaofeng Fan; Yining Ma; Zhongxiang Dai; Wei Jing; Cheston Tan; Bryan Kian Hsiang Low; | |
79 | Compacter: Efficient Low-Rank Hypercomplex Adapter Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Compacter, a method for fine-tuning large-scale language models with a better trade-off between task performance and the number of trainable parameters than prior work. |
Rabeeh Karimi Mahabadi; James Henderson; Sebastian Ruder; | code |
80 | Distilling Image Classifiers in Object Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we study the case of object detection and, instead of following the standard detector-to-detector distillation approach, introduce a classifier-to-detector knowledge transfer framework. |
Shuxuan Guo; Jose M. Alvarez; Mathieu Salzmann; | |
81 | Subgroup Generalization and Fairness of Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel PAC-Bayesian analysis for GNNs under a non-IID semi-supervised learning setup. |
Jiaqi Ma; Junwei Deng; Qiaozhu Mei; | |
82 | Scaling Neural Tangent Kernels Via Sketching and Random Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To accelerate learning with NTK, we design a near input-sparsity time approximation algorithm for NTK, by sketching the polynomial expansions of arc-cosine kernels: our sketch for the convolutional counterpart of NTK (CNTK) can transform any image using a linear runtime in the number of pixels. |
Amir Zandieh; Insu Han; Haim Avron; Neta Shoham; Chaewon Kim; Jinwoo Shin; | |
83 | BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose BatchQuant, a robust quantizer formulation that allows fast and stable training of a compact, single-shot, mixed-precision, weight-sharing supernet. |
Haoping Bai; Meng Cao; Ping Huang; Jiulong Shan; | |
84 | Long Short-Term Transformer for Online Action Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. |
Mingze Xu; Yuanjun Xiong; Hao Chen; Xinyu Li; Wei Xia; Zhuowen Tu; Stefano Soatto; | |
85 | Near Optimal Policy Optimization Via REPS Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we aim to fill this gap by providing guarantees and convergence rates for the sub-optimality of a policy learned using first-order optimization methods applied to the REPS objective. |
Aldo Pacchiano; Jonathan Lee; Peter Bartlett; Ofir Nachum; | |
86 | Self-Consistent Models and Values Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate a way of augmenting model-based RL, by additionally encouraging a learned model and value function to be jointly \emph{self-consistent}. |
Greg Farquhar; Kate Baumli; Zita Marinho; Angelos Filos; Matteo Hessel; Hado P. van Hasselt; David Silver; | |
87 | Learning on Random Balls Is Sufficient for Estimating (Some) Graph Parameters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a theoretical framework for graph classification problems in the partial observation setting (i.e., subgraph samplings). |
Takanori Maehara; Hoang NT; | |
88 | Risk-Averse Bayes-Adaptive Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address risk-averse Bayes-adaptive reinforcement learning. |
Marc Rigter; Bruno Lacerda; Nick Hawes; | |
89 | Iterative Connecting Probability Estimation for Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a two-stage neighborhood selection procedure to achieve the trade-off between smoothness of the estimate and the ability to discover local structure. |
Yichen Qin; Linhan Yu; Yang Li; | |
90 | Learning to Adapt Via Latent Domains for Adaptive Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Alternatively, in this work we break through the standard “source-target” one pair adaptation framework and construct multiple adaptation pairs (e.g. “source-latent” and “latent-target”). |
Yunan Liu; Shanshan Zhang; Yang Li; Jian Yang; | |
91 | Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we utilize the {\em predictive normalized maximum likelihood} (pNML) learner, in which no assumptions are made on the tested input. |
Koby Bibas; Meir Feder; Tal Hassner; | |
92 | Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation. |
Lei Ke; Xia Li; Martin Danelljan; Yu-Wing Tai; Chi-Keung Tang; Fisher Yu; | code |
93 | Algorithmic Instabilities of Accelerated Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the algorithmic stability of Nesterov’s accelerated gradient method. |
Amit Attia; Tomer Koren; | |
94 | Learning Optimal Predictive Checklists Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a method to learn checklists for clinical decision support. |
Haoran Zhang; Quaid Morris; Berk Ustun; Marzyeh Ghassemi; | |
95 | Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The focus of this paper is on sample complexity guarantees of average-reward reinforcement learning algorithms, which are known to be more challenging to study than their discounted-reward counterparts. |
Sheng Zhang; Zhe Zhang; Siva Theja Maguluri; | |
96 | Generalization Bounds for Graph Embedding Using Negative Sampling: Linear Vs Hyperbolic Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a generalization error bound applicable for graph embedding both in linear and hyperbolic spaces under various negative sampling settings that appear in graph embedding. |
Atsushi Suzuki; Atsushi Nitanda; jing wang; Linchuan Xu; Kenji Yamanishi; Marc Cavazza; | |
97 | Gradient Starvation: A Learning Proclivity in Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. |
Mohammad Pezeshki; Oumar Kaba; Yoshua Bengio; Aaron C. Courville; Doina Precup; Guillaume Lajoie; | |
98 | Offline Reinforcement Learning As One Big Sequence Modeling Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we explore how RL can be reframed as "one big sequence modeling" problem, using state-of-the-art Transformer architectures to model distributions over sequences of states, actions, and rewards. |
Michael Janner; Qiyang Li; Sergey Levine; | |
99 | Optimality and Stability in Federated Learning: A Game-theoretic Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we motivate and define a notion of optimality given by the average error rates among federating agents (players). |
Kate Donahue; Jon Kleinberg; | |
100 | Understanding Deflation Process in Over-parametrized Tensor Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study the training dynamics for gradient flow on over-parametrized tensor decomposition problems. |
Rong Ge; Yunwei Ren; Xiang Wang; Mo Zhou; | |
101 | Privately Learning Subspaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present differentially private algorithms that take input data sampled from a low-dimensional linear subspace (possibly with a small amount of error) and output that subspace (or an approximation to it). |
Vikrant Singhal; Thomas Steinke; | |
102 | On The Value of Interaction and Function Approximation in Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce a new problem called confidence set linear classification, that can be used to construct sample-efficient IL algorithms. |
Nived Rajaraman; Yanjun Han; Lin Yang; Jingbo Liu; Jiantao Jiao; Kannan Ramchandran; | |
103 | Shapeshifter: A Parameter-efficient Transformer Using Factorized Reshaped Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we focus on factorized representations of matrices that underpin dense, embedding, and self-attention layers. |
Aliakbar Panahi; Seyran Saeedi; Tom Arodz; | |
104 | The Adaptive Doubly Robust Estimator and A Paradox Concerning Logging Policy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To obtain an asymptotically normal semiparametric estimator from dependent samples without non-Donsker nuisance estimators, we propose adaptive-fitting as a variant of sample-splitting. |
Masahiro Kato; Kenichiro McAlinn; Shota Yasui; | |
105 | Regularized Softmax Deep Multi-Agent Q-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we empirically demonstrate that QMIX, a popular $Q$-learning algorithm for cooperative multi-agent reinforcement learning (MARL), suffers from a more severe overestimation in practice than previously acknowledged, and is not mitigated by existing approaches. |
Ling Pan; Tabish Rashid; Bei Peng; Longbo Huang; Shimon Whiteson; | |
106 | Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We train a deep neural network to perform physics-informed downsampling of the terrain map: we optimize the coarse grid representation of the terrain maps, so that the flood prediction will match the fine grid solution. |
Niv Giladi; Zvika Ben-Haim; Sella Nevo; Yossi Matias; Daniel Soudry; | |
107 | Systematic Generalization with Edge Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we propose Edge Transformer, a new model that combines inspiration from Transformers and rule-based symbolic AI. |
Leon Bergen; Timothy O'Donnell; Dzmitry Bahdanau; | |
108 | TransformerFusion: Monocular RGB Scene Reconstruction Using Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. |
Aljaz Bozic; Pablo Palafox; Justus Thies; Angela Dai; Matthias Niessner; | |
109 | Maximum Likelihood Training of Score-Based Diffusion Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that for a specific weighting scheme, the objective upper bounds the negative log-likelihood, thus enabling approximate maximum likelihood training of score-based diffusion models. |
Yang Song; Conor Durkan; Iain Murray; Stefano Ermon; | |
110 | Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the asymmetric low-rank factorization problem:\[\min_{\mathbf{U} \in \mathbb{R}^{m \times d}, \mathbf{V} \in \mathbb{R}^{n \times d}} \frac{1}{2}\|\mathbf{U}\mathbf{V}^\top -\mathbf{\Sigma}\|_F^2\]where $\mathbf{\Sigma}$ is a given matrix of size $m \times n$ and rank $d$. |
Tian Ye; Simon S. Du; | |
111 | Adaptive Data Augmentation on Temporal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information. |
Yiwei Wang; Yujun Cai; Yuxuan Liang; Henghui Ding; Changhu Wang; Siddharth Bhatia; Bryan Hooi; | |
112 | Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce regularized Frank-Wolfe, a general and effective algorithm for inference and learning of dense conditional random fields (CRFs). |
�.Khu� L�-Huu; Karteek Alahari; | |
113 | Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we propose Terra, an imperative-symbolic co-execution system that can handle any imperative DL programs while achieving the optimized performance of symbolic graph execution. |
Taebum Kim; Eunji Jeong; Geon-Woo Kim; Yunmo Koo; Sehoon Kim; Gyeongin Yu; Byung-Gon Chun; | |
114 | Uniform Sampling Over Episode Difficulty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on this method, we perform an extensive analysis and find that sampling uniformly over episode difficulty outperforms other sampling schemes, including curriculum and easy-/hard-mining. |
S�bastien Arnold; Guneet Dhillon; Avinash Ravichandran; Stefano Soatto; | |
115 | Scalable Intervention Target Estimation in Linear Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a scalable and efficient algorithm that consistently identifies all intervention targets. |
Burak Varici; Karthikeyan Shanmugam; Prasanna Sattigeri; Ali Tajer; | code |
116 | Play to Grade: Testing Coding Games As Classifying Markov Decision Process Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we formalize the challenge of providing feedback to interactive programs as a task of classifying Markov Decision Processes (MDPs). |
Allen Nie; Emma Brunskill; Chris Piech; | |
117 | Distributional Reinforcement Learning for Multi-Dimensional Reward Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fully inherit the benefits of distributional RL and hybrid reward architectures, we introduce Multi-Dimensional Distributional DQN (MD3QN), which extends distributional RL to model the joint return distribution from multiple reward sources. |
Pushi Zhang; Xiaoyu Chen; Li Zhao; Wei Xiong; Tao Qin; Tie-Yan Liu; | |
118 | Differentiable Unsupervised Feature Selection Based on A Gated Laplacian Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a method for unsupervised feature selection, and we demonstrate its advantage in clustering, a common unsupervised task. |
Ofir Lindenbaum; Uri Shaham; Erez Peterfreund; Jonathan Svirsky; Nicolas Casey; Yuval Kluger; | |
119 | Smooth Bilevel Programming for Sparse Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how a surprisingly simple re-parametrization of IRLS, coupled with a bilevel resolution (instead of an alternating scheme) is able to achieve top performances on a wide range of sparsity (such as Lasso, group Lasso and trace norm regularizations), regularization strength (including hard constraints), and design matrices (ranging from correlated designs to differential operators). |
Clarice Poon; Gabriel Peyr�; | |
120 | Grounding Representation Similarity Through Statistical Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: These disagreements raise the question: which, if any, of these dissimilarity measures should we believe? We provide a framework to ground this question through a concrete test: measures should have \emph{sensitivity} to changes that affect functional behavior, and \emph{specificity} against changes that do not. |
Frances Ding; Jean-Stanislas Denain; Jacob Steinhardt; | |
121 | A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. |
Mingde Zhao; Zhen Liu; Sitao Luan; Shuyuan Zhang; Doina Precup; Yoshua Bengio; | |
122 | Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new provably efficient algorithm, called UCRL-RFE under the Linear Mixture MDP assumption, where the transition probability kernel of the MDP can be parameterized by a linear function over certain feature mappings defined on the triplet of state, action, and next state. |
Weitong ZHANG; Dongruo Zhou; Quanquan Gu; | |
123 | Beltrami Flow and Neural Diffusion on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel class of graph neural networks based on the discretized Beltrami flow, a non-Euclidean diffusion PDE. |
Benjamin Chamberlain; James Rowbottom; Davide Eynard; Francesco Di Giovanni; Xiaowen Dong; Michael Bronstein; | |
124 | Think Big, Teach Small: Do Language Models Distil Occam’s Razor? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We frame this question as a teaching problem with strong priors, and study whether language models can identify simple algorithmic concepts from small witness sets. |
Gonzalo Jaimovitch-Lopez; David Castellano Falc�n; Cesar Ferri; Jos� Hern�ndez-Orallo; | |
125 | Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). |
Hermanni H�lv�; Sylvain Le Corff; Luc Leh�ricy; Jonathan So; Yongjie Zhu; Elisabeth Gassiat; Aapo Hyvarinen; | |
126 | Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We generalize the idea of conditional parameterization — using trainable functions of input parameters to generate the weights of a neural network, and extend them in a flexible way to encode critical information. |
Jiayang Xu; Aniruddhe Pradhan; Karthikeyan Duraisamy; | |
127 | USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For learning foundations, we present learning-error analysis under the PAC-Bayesian framework using a new margin-based analysis. |
Guangmo Tong; | |
128 | Adaptive Conformal Inference Under Distribution Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop methods for forming prediction sets in an online setting where the data generating distribution is allowed to vary over time in an unknown fashion. |
Isaac Gibbs; Emmanuel Candes; | |
129 | Periodic Activation Functions Induce Stationarity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We seek to build models that `know what they do not know’ by introducing inductive biases in the function space. |
Lassi Meronen; Martin Trapp; Arno Solin; | |
130 | Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we build on top of recent advances in domain-adaptation theory, and from this perspective, propose ways to minimize the reality gap. |
David Acuna; Jonah Philion; Sanja Fidler; | |
131 | KS-GNN: Keywords Search Over Incomplete Graphs Via Graphs Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the problem of keyword search over incomplete graphs, we propose a novel model named KS-GNN based on the graph neural network and the auto-encoder. |
YU HAO; Xin Cao; Yufan Sheng; Yixiang Fang; Wei Wang; | |
132 | Reconstruction for Powerful Graph Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show the extent to which graph reconstruction—reconstructing a graph from its subgraphs—can mitigate the theoretical and practical problems currently faced by GRL architectures. |
Leonardo Cotta; Christopher Morris; Bruno Ribeiro; | |
133 | Revealing and Protecting Labels in Distributed Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a method to discover the set of labels of training samples from only the gradient of the last layer and the id to label mapping. |
Trung Dang; Om Thakkar; Swaroop Ramaswamy; Rajiv Mathews; Peter Chin; Fran�oise Beaufays; | |
134 | Solving Graph-based Public Goods Games with Tree Search and Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we adopt the perspective of a central planner with a global view of a network of self-interested agents and the goal of maximizing some desired property in the context of a best-shot public goods game. |
Victor-Alexandru Darvariu; Stephen Hailes; Mirco Musolesi; | |
135 | Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a principled technical method to optimize AUPRC for deep learning. |
Qi Qi; Youzhi Luo; Zhao Xu; Shuiwang Ji; Tianbao Yang; | code |
136 | Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we establish a theoretically grounded and practically useful framework for the transfer learning of GNNs. |
Qi Zhu; Carl Yang; Yidan Xu; Haonan Wang; Chao Zhang; Jiawei Han; | |
137 | You Are Caught Stealing My Winning Lottery Ticket! Making A Lottery Ticket Claim Its Ownership Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our setting adds a new dimension to the recently soaring interest in protecting against the intellectual property (IP) infringement of deep models and verifying their ownerships, since they take owners’ massive/unique resources to develop or train. |
Xuxi Chen; Tianlong Chen; Zhenyu Zhang; Zhangyang Wang; | code |
138 | Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a first-order oracle complexity lower bound for finding stationary points of min-max optimization problems where the objective function is smooth, nonconvex in the minimization variable, and strongly concave in the maximization variable. |
Haochuan Li; Yi Tian; Jingzhao Zhang; Ali Jadbabaie; | |
139 | Early-stopped Neural Networks Are Consistent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is … |
Ziwei Ji; Justin Li; Matus Telgarsky; | |
140 | NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding Via ADMM Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such an issue in a principled manner, we introduce a new learning framework, called NxMTransformer, to induce NxM semi-structured sparsity on pretrained language models for natural language understanding to obtain better performance. |
Connor Holmes; Minjia Zhang; Yuxiong He; Bo Wu; | |
141 | Reliable Decisions with Threshold Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a stronger notion of calibration called threshold calibration, which is exactly the condition required to ensure that decision loss is predicted accurately for threshold decisions. |
Roshni Sahoo; Shengjia Zhao; Alyssa Chen; Stefano Ermon; | |
142 | End-to-End Weak Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these caveats we propose an end-to-end approach for directly learning the downstream model by maximizing its agreement with probabilistic labels generated by reparameterizing previous probabilistic posteriors with a neural network. |
Salva R�hling Cachay; Benedikt Boecking; Artur Dubrawski; | code |
143 | Shift Invariance Can Reduce Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background. |
Vasu Singla; Songwei Ge; Basri Ronen; David Jacobs; | |
144 | Wisdom of The Crowd Voting: Truthful Aggregation of Voter Information and Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider two-alternative elections where voters’ preferences depend on a state variable that is not directly observable. |
Grant Schoenebeck; Biaoshuai Tao; | |
145 | Replay-Guided Adversarial Environment Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we cast Prioritized Level Replay (PLR), an empirically successful but theoretically unmotivated method that selectively samples randomly-generated training levels, as UED. We argue that by curating completely random levels, PLR, too, can generate novel and complex levels for effective training. |
Minqi Jiang; Michael Dennis; Jack Parker-Holder; Jakob Foerster; Edward Grefenstette; Tim Rockt�schel; | |
146 | There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). |
Nathan Grinsztajn; Johan Ferret; Olivier Pietquin; philippe preux; Matthieu Geist; | |
147 | Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work, we investigate how both approaches can be integrated into one framework that combines their strengths. |
Ingmar Schubert; Danny Driess; Ozgur Oguz; Marc Toussaint; | |
148 | Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote diversity in sample generation without degrading the overall quality, we propose a simple yet effective method to diagnose and emphasize underrepresented samples during training of a GAN. |
Jinhee Lee; Haeri Kim; Youngkyu Hong; Hye Won Chung; | |
149 | Online Multi-Armed Bandits with Adaptive Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our thesis in this paper is that more sophisticated inference schemes that take into account the adaptive nature of the sequentially collected data can unlock further performance gains, even though both UCB and TS type algorithms are optimal in the worst case. |
Maria Dimakopoulou; Zhimei Ren; Zhengyuan Zhou; | |
150 | Efficient Truncated Linear Regression with Unknown Noise Variance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the first computationally and statistically efficient estimators for truncated linear regression when the noise variance is unknown, estimating both the linear model and the variance of the noise. |
Constantinos Daskalakis; Patroklos Stefanou; Rui Yao; Emmanouil Zampetakis; | |
151 | Breaking The Dilemma of Medical Image-to-image Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to break the dilemma of the existing modes, we propose a new unsupervised mode called RegGAN for medical image-to-image translation. |
Lingke Kong; Chenyu Lian; Detian Huang; zhenjiang li; Yanle Hu; Qichao Zhou; | code |
152 | Temporally Abstract Partial Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we define a notion of affordances for options, and develop temporally abstract partial option models, that take into account the fact that an option might be affordable only in certain situations. |
Khimya Khetarpal; Zafarali Ahmed; Gheorghe Comanici; Doina Precup; | |
153 | TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, we propose a new simplified decoder, which drops the full attention implementation with the softmax weighting, keeping only the query-key similarity computation. |
Shengcai Liao; Ling Shao; | code |
154 | Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We build on traditional SPI algorithms and propose a novel method based on Safe Policy Iteration with Baseline Bootstrapping (SPIBB, Laroche et al., 2019) that provides high probability guarantees on the performance of the agent in the true environment. |
harsh satija; Philip S. Thomas; Joelle Pineau; Romain Laroche; | |
155 | Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Automated evaluations declare a winning model when corresponding human evaluations do not, calling into question the validity of fully automatic evaluations independent of human judgments. |
Alexander Hoyle; Pranav Goel; Andrew Hian-Cheong; Denis Peskov; Jordan Boyd-Graber; Philip Resnik; | |
156 | INDIGO: GNN-Based Inductive Knowledge Graph Completion Using Pair-Wise Encoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach, where the KG is fully encoded into a GNN in a transparent way, and where the predicted triples can be read out directly from the last layer of the GNN without the need for additional components or scoring functions. |
Shuwen Liu; Bernardo Grau; Ian Horrocks; Egor Kostylev; | |
157 | Do Input Gradients Highlight Discriminative Features? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Post-hoc gradient-based interpretability methods [Simonyan et al., 2013, Smilkov et al., 2017] that provide instance-specific explanations of model predictions are often based on assumption (A): magnitude of input gradients-gradients of logits with respect to input-noisily highlight discriminative task-relevant features. In this work, we test the validity of assumption (A) using a three-pronged approach: |
Harshay Shah; Prateek Jain; Praneeth Netrapalli; | |
158 | Improving Conditional Coverage Via Orthogonal Quantile Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a method to generate prediction intervals that have a user-specified coverage level across all regions of feature-space, a property called conditional coverage. |
Shai Feldman; Stephen Bates; Yaniv Romano; | |
159 | Minimizing Polarization and Disagreement in Social Networks Via Link Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple greedy algorithm with a constant-factor approximation that solves the problem in cubic running time, and we provide theoretical analysis of the approximation guarantee for the algorithm. |
Liwang Zhu; Qi Bao; Zhongzhi Zhang; | |
160 | Adversarial Attacks on Black Box Video Classifiers: Leveraging The Power of Geometric Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that such effective gradients can be searched for by parameterizing the temporal structure of the search space with geometric transformations. |
Shasha Li; Abhishek Aich; Shitong Zhu; Salman Asif; Chengyu Song; Amit Roy-Chowdhury; Srikanth Krishnamurthy; | |
161 | Optimal Rates for Random Order Online Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Focusing on the scenario where the cumulative loss function is (strongly) convex, yet individual loss functions are smooth but might be non-convex, we give algorithms that achieve the optimal bounds and significantly outperform the results of Garber et al. (2020), completely removing the dimension dependence and improve their scaling with respect to the strong convexity parameter. |
Uri Sherman; Tomer Koren; Yishay Mansour; | |
162 | Discrete-Valued Neural Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we further tighten the bottleneck via discreteness of the representations transmitted between components. |
Dianbo Liu; Alex M. Lamb; Kenji Kawaguchi; Anirudh Goyal ALIAS PARTH GOYAL; Chen Sun; Michael C. Mozer; Yoshua Bengio; | |
163 | Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage the computation methods for kernel machines to alleviate the high computational cost and introduce Skyformer, which replaces the softmax structure with a Gaussian kernel to stabilize the model training and adapts the Nyström method to a non-positive semidefinite matrix to accelerate the computation. |
Yifan Chen; Qi Zeng; Heng Ji; Yun Yang; | |
164 | TransMIL: Transformer Based Correlated Multiple Instance Learning for Whole Slide Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence. |
Zhuchen Shao; Hao Bian; Yang Chen; Yifeng Wang; Jian Zhang; Xiangyang Ji; yongbing zhang; | code |
165 | Multi-view Contrastive Graph Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generic framework to cluster multi-view attributed graph data. |
ErLin Pan; Zhao Kang; | |
166 | Inverse-Weighted Survival Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve this dilemma, we introduce Inverse-Weighted Survival Games to train both failure and censoring models with respect to criteria such as BS or BLL. |
Xintian Han; Mark Goldstein; Aahlad Puli; Thomas Wies; Adler Perotte; Rajesh Ranganath; | |
167 | Generalization Bounds for Meta-Learning Via PAC-Bayes and Uniform Stability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive a probably approximately correct (PAC) bound for gradient-based meta-learning using two different generalization frameworks in order to deal with the qualitatively different challenges of generalization at the base and meta levels. |
Alec Farid; Anirudha Majumdar; | |
168 | Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel acquisition function, NEHVI, that overcomes this important practical limitation by applying a Bayesian treatment to the popular expected hypervolume improvement (EHVI) criterion and integrating over this uncertainty in the Pareto frontier. |
Samuel Daulton; Maximilian Balandat; Eytan Bakshy; | |
169 | Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots. |
Jagdeep Bhatia; Holly Jackson; Yunsheng Tian; Jie Xu; Wojciech Matusik; | code |
170 | On Calibration and Out-of-Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we draw a link between OOD performance and model calibration, arguing that calibration across multiple domains can be viewed as a special case of an invariant representation leading to better OOD generalization. |
Yoav Wald; Amir Feder; Daniel Greenfeld; Uri Shalit; | |
171 | On The Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a simple gradient truncation mechanism is proposed to address this issue. |
Junyu Zhang; Chengzhuo Ni; zheng Yu; Csaba Szepesvari; Mengdi Wang; | |
172 | Circa: Stochastic ReLUs for Private Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we re-think ReLU computations and propose optimizations for PI tailored to properties of neural networks. |
Zahra Ghodsi; Nandan Kumar Jha; Brandon Reagen; Siddharth Garg; | |
173 | Reinforcement Learning in Reward-Mixing MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP). |
Jeongyeol Kwon; Yonathan Efroni; Constantine Caramanis; Shie Mannor; | |
174 | A Gang of Adversarial Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two learning algorithms, GABA-I and GABA-II, which exploit the network structure to bias towards functions of low $\Psi$ values. |
Mark Herbster; Stephen Pasteris; Fabio Vitale; Massimiliano Pontil; | |
175 | Explaining Hyperparameter Optimization Via Partial Dependence Plots Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging the posterior uncertainty of the BO surrogate model, we introduce a variant of the PDP with estimated confidence bands.We propose to partition the hyperparameter space to obtain more confident and reliable PDPs in relevant sub-regions. |
Julia Moosbauer; Julia Herbinger; Giuseppe Casalicchio; Marius Lindauer; Bernd Bischl; | |
176 | Robustifying Algorithms of Learning Latent Trees with Vector Variables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider learning the structures of Gaussian latent tree models with vector observations when a subset of them are arbitrarily corrupted. |
Fengzhuo Zhang; Vincent Tan; | |
177 | Representation Learning on Spatial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, this paper proposes a generic framework for spatial network representation learning. |
Zheng Zhang; Liang Zhao; | code |
178 | Continuous-time Edge Modelling Using Non-parametric Point Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we discuss various approaches to model design, and develop three variants of non-parametric point processes for continuous-time edge modelling (CTEM). |
Xuhui Fan; Bin Li; Feng Zhou; Scott SIsson; | |
179 | Deep Inference of Latent Dynamics with Spatio-temporal Super-resolution Using Selective Backpropagation Through Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. |
Feng Zhu; Andrew Sedler; Harrison Grier; Nauman Ahad; Mark Davenport; Matthew Kaufman; Andrea Giovannucci; Chethan Pandarinath; | |
180 | Memory-efficient Patch-based Inference for Tiny Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this issue, we propose a generic patch-by-patch inference scheduling, which operates only on a small spatial region of the feature map and significantly cuts down the peak memory. |
Ji Lin; Wei-Ming Chen; Han Cai; Chuang Gan; Song Han; | |
181 | Self-Interpretable Model with Transformation Equivariant Interpretation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose to learn robust interpretation through transformation equivariant regularization in a self-interpretable model. |
Yipei Wang; Xiaoqian Wang; | |
182 | Solving Min-Max Optimization with Hidden Structure Via Gradient Descent Ascent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide conditions under which vanilla GDA provably converges not merely to local Nash, but the actual von-Neumann solution. |
Emmanouil-Vasileios Vlatakis-Gkaragkounis; Lampros Flokas; Georgios Piliouras; | |
183 | Preserved Central Model for Faster Bidirectional Compression in Distributed Settings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose and analyze a new algorithm that performs bidirectional compression and achieves the same convergence rate as algorithms using only uplink (from the local workers to the central server) compression. |
Constantin Philippenko; Aymeric Dieuleveut; | |
184 | Understanding Instance-based Interpretability of Variational Auto-Encoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate influence functions [20], a popular instance-based interpretation method, for a class of deep generative models called variational auto-encoders (VAE). |
Zhifeng Kong; Kamalika Chaudhuri; | |
185 | Voxel-based 3D Detection and Reconstruction of Multiple Objects from A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to learn a regular grid of 3D voxel features from the input image which is aligned with 3D scene space via a 3D feature lifting operator. |
Feng Liu; Xiaoming Liu; | |
186 | Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new algorithm for domain generalization (DG), \textit{test-time template adjuster (T3A)}, aiming to robustify a model to unknown distribution shift. |
Yusuke Iwasawa; Yutaka Matsuo; | |
187 | Luna: Linear Unified Nested Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Luna, a linear unified nested attention mechanism that approximates softmax attention with two nested linear attention functions, yielding only linear (as opposed to quadratic) time and space complexity. |
Xuezhe Ma; Xiang Kong; Sinong Wang; Chunting Zhou; Jonathan May; Hao Ma; Luke Zettlemoyer; | |
188 | Iterative Causal Discovery in The Possible Presence of Latent Confounders and Selection Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a sound and complete algorithm, called iterative causal discovery (ICD), for recovering causal graphs in the presence of latent confounders and selection bias. |
Raanan Yehezkel Rohekar; Shami Nisimov; Yaniv Gurwicz; Gal Novik; | |
189 | Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a formulation of hindsight relabelling for meta-RL, which relabels experience during meta-training to enable learning to learn entirely using sparse reward. |
Charles Packer; Pieter Abbeel; Joseph E. Gonzalez; | |
190 | A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Bayesian-symbolic framework (BSP) for physical reasoning and learning that is close to human-level sample-efficiency and accuracy. |
Kai Xu; Akash Srivastava; Dan Gutfreund; Felix Sosa; Tomer Ullman; Josh Tenenbaum; Charles Sutton; | |
191 | Associating Objects with Transformers for Video Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the problem, we propose an Associating Objects with Transformers (AOT) approach to match and decode multiple objects uniformly. |
Zongxin Yang; Yunchao Wei; Yi Yang; | |
192 | Automatic Symmetry Discovery with Lie Algebra Convolutional Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to work with Lie algebras (infinitesimal generators) instead of Lie groups. |
Nima Dehmamy; Robin Walters; Yanchen Liu; Dashun Wang; Rose Yu; | |
193 | Zero Time Waste: Recycling Predictions in Early Exit Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this issue, we introduce Zero Time Waste (ZTW), a novel approach in which each IC reuses predictions returned by its predecessors by (1) adding direct connections between ICs and (2) combining previous outputs in an ensemble-like manner. |
Maciej Wolczyk; Bartosz W�jcik; Klaudia Balazy; Igor Podolak; Jacek Tabor; Marek Smieja; Tomasz Trzcinski; | |
194 | On Model Calibration for Long-Tailed Object Detection and Instance Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate a largely overlooked approach — post-processing calibration of confidence scores. |
Tai-Yu Pan; Cheng Zhang; Yandong Li; Hexiang Hu; Dong Xuan; Soravit Changpinyo; Boqing Gong; Wei-Lun Chao; | code |
195 | ReSSL: Relational Self-Supervised Learning with Weak Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduced a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. |
Mingkai Zheng; Shan You; Fei Wang; Chen Qian; Changshui Zhang; Xiaogang Wang; Chang Xu; | |
196 | Learning to See By Looking at Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we go a step further and ask if we can do away with real image datasets entirely, instead learning from procedural noise processes. |
Manel Baradad; Jonas Wulff; Tongzhou Wang; Phillip Isola; Antonio Torralba; | |
197 | Explicit Loss Asymptotics in The Gradient Descent Training of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work we take a different approach and show that the learning trajectory of a wide network in a lazy training regime can be characterized by an explicit asymptotic at large training times. |
Maksim Velikanov; Dmitry Yarotsky; | |
198 | Test-Time Personalization with A Transformer for Human Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to personalize a 2D human pose estimator given a set of test images of a person without using any manual annotations. |
Yizhuo Li; Miao Hao; Zonglin Di; Nitesh Bharadwaj Gundavarapu; Xiaolong Wang; | code |
199 | Towards Scalable Unpaired Virtual Try-On Via Patch-Routed Spatially-Adaptive GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To achieve a scalable virtual try-on system that can transfer arbitrary garments between a source and a target person in an unsupervised manner, we thus propose a texture-preserving end-to-end network, the PAtch-routed SpaTially-Adaptive GAN (PASTA-GAN), that facilitates real-world unpaired virtual try-on. |
Zhenyu Xie; Zaiyu Huang; Fuwei Zhao; Haoye Dong; Michael Kampffmeyer; Xiaodan Liang; | |
200 | Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we conduct an in-depth analysis of GPT-2, which is the most downloaded text generation model on HuggingFace, with over half a million downloads per month. |
Hannah Rose Kirk; yennie jun; Filippo Volpin; Haider Iqbal; Elias Benussi; Frederic Dreyer; Aleksandar Shtedritski; Yuki Asano; | |
201 | Weisfeiler and Lehman Go Cellular: CW Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend recent theoretical results on SCs to regular Cell Complexes, topological objects that flexibly subsume SCs and graphs. |
Cristian Bodnar; Fabrizio Frasca; Nina Otter; Yu Guang Wang; Pietro Li�; Guido F. Montufar; Michael Bronstein; | |
202 | Learning Conjoint Attentions for Graph Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). |
Tiantian He; Yew Ong; L Bai; | |
203 | Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study aims to develop bandit algorithms that automatically exploit tendencies of certain environments to improve performance, without any prior knowledge regarding the environments. |
Shinji Ito; | |
204 | Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we find that non-selective attention sharing is sub-optimal for achieving good generalization across all languages and domains. |
Hongyu Gong; Yun Tang; Juan Pino; Xian Li; | |
205 | Cardinality-Regularized Hawkes-Granger Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new sparse Granger-causal learning framework for temporal event data. |
Tsuyoshi Ide; Georgios Kollias; Dzung Phan; Naoki Abe; | |
206 | Aligned Structured Sparsity Learning for Efficient Image Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above issues, we propose aligned structured sparsity learning (ASSL), which introduces a weight normalization layer and applies $L_2$ regularization to the scale parameters for sparsity. |
Yulun Zhang; Huan Wang; Can Qin; Yun Fu; | |
207 | Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To the best of our knowledge, our work, for the first time, characterizes the performance of training a pruned neural network by analyzing the geometric structure of the objective function and the sample complexity to achieve zero generalization error. |
Shuai Zhang; Meng Wang; Sijia Liu; Pin-Yu Chen; Jinjun Xiong; | |
208 | Constrained Robust Submodular Partitioning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two classes of algorithms, i.e., Min-Block Greedy based algorithms (with an $\Omega(1/m)$ bound), and Round-Robin Greedy based algorithms (with a constant bound) and show that under various constraints, they still have good approximation guarantees. |
Shengjie Wang; Tianyi Zhou; Chandrashekhar Lavania; Jeff A. Bilmes; | |
209 | Online Knapsack with Frequency Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we continue this line of work by studying the online knapsack problem, but with very weak predictions: in the form of knowing an upper and lower bound for the number of items of each value. |
Sungjin Im; Ravi Kumar; Mahshid Montazer Qaem; Manish Purohit; | |
210 | On Component Interactions in Two-Stage Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As manual search for a good pool allocation is difficult, we propose to learn one instead using a Mixture-of-Experts based approach. |
Jiri Hron; Karl Krauth; Michael Jordan; Niki Kilbertus; | |
211 | Lip to Speech Synthesis with Visual Context Attentional GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel lip-to-speech generative adversarial network, Visual Context Attentional GAN (VCA-GAN), which can jointly model local and global lip movements during speech synthesis. |
Minsu Kim; Joanna Hong; Yong Man Ro; | |
212 | Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we bridge the gap by studying DRO algorithms for general smooth non-convex losses. |
Jikai Jin; Bohang Zhang; Haiyang Wang; Liwei Wang; | |
213 | Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose goal-aware cross-entropy (GACE) loss, that can be utilized in a self-supervised way using auto-labeled goal states alongside reinforcement learning. |
Kibeom Kim; Min Whoo Lee; Yoonsung Kim; JeHwan Ryu; Minsu Lee; Byoung-Tak Zhang; | |
214 | Smooth Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a class of smooth mixture transformations working on both compact intervals and hypertori.Mixture transformations employ root-finding methods to invert them in practice, which has so far prevented bi-directional flow training. |
Jonas K�hler; Andreas Kr�mer; Frank Noe; | |
215 | MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to create generalizable and controllable neural signed distance fields (SDFs) that represent clothed humans from monocular depth observations. |
Shaofei Wang; Marko Mihajlovic; Qianli Ma; Andreas Geiger; Siyu Tang; | |
216 | Distributed Principal Component Analysis with Limited Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new quantized variant of Riemannian gradient descent to solve this problem, and prove that the algorithm converges with high probability under a set of necessary spherical-convexity properties. |
Foivos Alimisis; Peter Davies; Bart Vandereycken; Dan Alistarh; | |
217 | Newton-LESS: Sparsification Without Trade-offs for The Sketched Newton Update Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove that Newton-LESS enjoys nearly the same problem-independent local convergence rate as Gaussian embeddings for a large class of functions. In particular, this leads to a new state-of-the-art convergence result for an iterative least squares solver. |
Michal Derezinski; Jonathan Lacotte; Mert Pilanci; Michael W. Mahoney; | |
218 | Confident Anchor-Induced Multi-Source Free Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we develop a novel Confident-Anchor-induced multi-source-free Domain Adaptation (CAiDA) model, which is a pioneer exploration of knowledge adaptation from multiple source domains to the unlabeled target domain without any source data, but with only pre-trained source models. |
Jiahua Dong; Zhen Fang; Anjin Liu; Gan Sun; Tongliang Liu; | code |
219 | Word2Fun: Modelling Words As Functions for Diachronic Word Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we will carry on this line of work by learning explicit functions over time for each word. |
benyou wang; Emanuele Di Buccio; Massimo Melucci; | code |
220 | Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we prove that a variant of IRLS converges \emph{with a global linear rate} to a sparse solution, i.e., with a linear error decrease occurring immediately from any initialization if the measurements fulfill the usual null space property assumption. |
Christian K�mmerle; Claudio Mayrink Verdun; Dominik St�ger; | |
221 | Low-Rank Constraints for Fast Inference in Structured Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. |
Justin Chiu; Yuntian Deng; Alexander Rush; | |
222 | Accumulative Poisoning Attacks on Real-time Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the real-time settings and propose a new attacking strategy, which affiliates an accumulative phase with poisoning attacks to secretly (i.e., without affecting accuracy) magnify the destructive effect of a (poisoned) trigger batch. |
Tianyu Pang; Xiao Yang; Yinpeng Dong; Hang Su; Jun Zhu; | |
223 | UCB-based Algorithms for Multinomial Logistic Regression Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this problem, we present MNL-UCB, an upper confidence bound (UCB)-based algorithm, that achieves regret $\tilde{\mathcal{O}}(dK\sqrt{T})$ with small dependency on problem-dependent constants that can otherwise be arbitrarily large and lead to loose regret bounds. |
Sanae Amani; Christos Thrampoulidis; | |
224 | Estimating The Long-Term Effects of Novel Treatments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a surrogate-based approach using a long-term dataset where only past treatments were administered and a short-term dataset where novel treatments have been administered. |
Keith Battocchi; Eleanor Dillon; Maggie Hei; Greg Lewis; Miruna Oprescu; Vasilis Syrgkanis; | |
225 | Dual Progressive Prototype Network for Generalized Zero-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we handle the critical issue of domain shift problem, i.e., confusion between seen and unseen categories, by progressively improving cross-domain transferability and category discriminability of visual representations. |
Chaoqun Wang; Shaobo Min; Xuejin Chen; Xiaoyan Sun; Houqiang Li; | |
226 | Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We make a step toward addressing this open problem, by providing the first sample complexity results for policy gradient (PG) methods in two fundamental risk-sensitive/robust control settings: the linear exponential quadratic Gaussian, and the linear-quadratic (LQ) disturbance attenuation problems. |
Kaiqing Zhang; Xiangyuan Zhang; Bin Hu; Tamer Basar; | |
227 | G-PATE: Scalable Differentially Private Data Generator Via Private Aggregation of Teacher Discriminators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel privacy-preserving data Generative model based on the PATE framework (G-PATE), aiming to train a scalable differentially private data generator that preserves high generated data utility. |
Yunhui Long; Boxin Wang; Zhuolin Yang; Bhavya Kailkhura; Aston Zhang; Carl Gunter; Bo Li; | code |
228 | On The Existence of The Adversarial Bayes Classifier Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study a fundamental question regarding Bayes optimality for adversarial robustness. |
Pranjal Awasthi; Natalie Frank; Mehryar Mohri; | |
229 | Convex-Concave Min-Max Stackelberg Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce two first-order methods that solve a large class of convex-concave min-max Stackelberg games, and show that our methods converge in polynomial time. |
Denizalp Goktas; Amy Greenwald; | |
230 | Misspecified Gaussian Process Bandit Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we present two algorithms based on Gaussian process (GP) methods: an optimistic EC-GP-UCB algorithm that requires knowing the misspecification error, and Phased GP Uncertainty Sampling, an elimination-type algorithm that can adapt to unknown model misspecification. |
Ilija Bogunovic; Andreas Krause; | |
231 | Visual Adversarial Imitation Learning Using Variational Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This setting presents a number of challenges including representation learning for visual observations, sample complexity due to high dimensional spaces, and learning instability due to the lack of a fixed reward or learning signal. Towards addressing these challenges, we develop a variational model-based adversarial imitation learning (V-MAIL) algorithm. |
Rafael Rafailov; Tianhe Yu; Aravind Rajeswaran; Chelsea Finn; | code |
232 | Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents Object-aware REgularizatiOn (OREO), a simple technique that regularizes an imitation policy in an object-aware manner. |
Jongjin Park; Younggyo Seo; Chang Liu; Li Zhao; Tao Qin; Jinwoo Shin; Tie-Yan Liu; | |
233 | Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the feasibility of using state-of-the-art out-of-distribution detectors for reliable and trustworthy diagnostic predictions. |
Chunjong Park; Anas Awadalla; Tadayoshi Kohno; Shwetak Patel; | |
234 | Multiclass Boosting and The Cost of Weak Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study multiclass boosting with a possibly large number of classes or categories. |
Nataly Brukhim; Elad Hazan; Shay Moran; Indraneel Mukherjee; Robert E. Schapire; | |
235 | Partition-Based Formulations for Mixed-Integer Optimization of Trained ReLU Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a class of mixed-integer formulations for trained ReLU neural networks. |
Calvin Tsay; Nikos Vlassis; Alexander Thebelt; Ruth Misener; | |
236 | Hyperparameter Optimization Is Deceiving Us, and How to Stop It Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We call this process epistemic hyperparameter optimization (EHPO), and put forth a logical framework to capture its semantics and how it can lead to inconsistent conclusions about performance. |
A. Feder Cooper; Yucheng Lu; Jessica Forde; Christopher M. De Sa; | |
237 | On The Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this formulation, we propose a variant of the MAML method, named Stochastic Gradient Meta-Reinforcement Learning (SG-MRL), and study its convergence properties. |
Alireza Fallah; Kristian Georgiev; Aryan Mokhtari; Asuman Ozdaglar; | |
238 | 3D Pose Transfer with Correspondence Learning and Mesh Refinement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a correspondence-refinement network to help the 3D pose transfer for both human and animal meshes. |
Chaoyue Song; Jiacheng Wei; Ruibo Li; Fayao Liu; Guosheng Lin; | |
239 | Framing RNN As A Kernel Method: A Neural ODE Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a RNN can be viewed as a linear function of a specific feature set of the input sequence, known as the signature. |
Adeline Fermanian; Pierre Marion; Jean-Philippe Vert; G�rard Biau; | |
240 | Contextual Similarity Aggregation with Self-attention for Visual Re-ranking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this observation, in this paper, we propose a visual re-ranking method by contextual similarity aggregation with self-attention. |
Jianbo Ouyang; Hui Wu; Min Wang; Wengang Zhou; Houqiang Li; | |
241 | Can Information Flows Suggest Targets for Interventions in Neural Circuits? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by neuroscientific and clinical applications, we empirically examine whether observational measures of information flow can suggest interventions. |
Praveen Venkatesh; Sanghamitra Dutta; Neil Mehta; Pulkit Grover; | |
242 | AutoBalance: Optimized Loss Functions for Imbalanced Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose AutoBalance, a bi-level optimization framework that automatically designs a training loss function to optimize a blend of accuracy and fairness-seeking objectives. |
Mingchen Li; Xuechen Zhang; Christos Thrampoulidis; Jiasi Chen; Samet Oymak; | |
243 | SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge the gap, this paper develops a new method, SyncTwin, that learns a patient-specific time-constant representation from the pre-treatment observations. |
Zhaozhi Qian; Yao Zhang; Ioana Bica; Angela Wood; Mihaela van der Schaar; | |
244 | Statistical Query Lower Bounds for List-Decodable Linear Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of list-decodable linear regression, where an adversary can corrupt a majority of the examples. |
Ilias Diakonikolas; Daniel Kane; Ankit Pensia; Thanasis Pittas; Alistair Stewart; | |
245 | Unsupervised Motion Representation Learning with Capsule Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. |
Ziwei Xu; Xudong Shen; Yongkang Wong; Mohan S. Kankanhalli; | |
246 | VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we propose a coordination detection framework incorporating neural temporal point process with prior knowledge such as temporal logic or pre-defined filtering functions. |
Yizhou Zhang; Karishma Sharma; Yan Liu; | |
247 | An Improved Analysis and Rates for Variance Reduction Under Without-replacement Sampling Orders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we will improve the convergence analysis and rates of variance reduction under without-replacement sampling orders for composite finite-sum minimization.Our results are in two-folds. |
Xinmeng Huang; Kun Yuan; Xianghui Mao; Wotao Yin; | |
248 | Exploring Forensic Dental Identification with Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we pioneer to study deep learning for dental forensic identification based on panoramic radiographs. |
Yuan Liang; Weikun Han; Liang Qiu; Chen Wu; Yiting Shao; Kun Wang; Lei He; | code |
249 | Learning to Generate Realistic Noisy Images Via Pixel-level Noise-aware Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, this work investigates how to generate realistic noisy images. |
Yuanhao Cai; Xiaowan Hu; Haoqian Wang; Yulun Zhang; Hanspeter Pfister; Donglai Wei; | |
250 | Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a problem in power networks that creates an exciting and yet challenging real-world scenario for application of multi-agent reinforcement learning (MARL). |
Jianhong Wang; Wangkun Xu; Yunjie Gu; Wenbin Song; Tim Green; | |
251 | Looking Beyond Single Images for Contrastive Semantic Segmentation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach to contrastive representation learning for semantic segmentation. |
FEIHU ZHANG; Philip Torr; Rene Ranftl; Stephan Richter; | |
252 | A Constant Approximation Algorithm for Sequential Random-Order No-Substitution K-Median Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give the first algorithm for this setting that obtains a constant approximation factor on the optimal cost under a random arrival order, an exponential improvement over previous work. |
Tom Hess; Michal Moshkovitz; Sivan Sabato; | |
253 | Dangers of Bayesian Model Averaging Under Covariate Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explain this surprising result, showing how a Bayesian model average can in fact be problematic under covariate shift, particularly in cases where linear dependencies in the input features cause a lack of posterior contraction. |
Pavel Izmailov; Patrick Nicholson; Sanae Lotfi; Andrew G. Wilson; | |
254 | Learning Equilibria in Matching Markets from Bandit Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge this gap, we develop a framework and algorithms for learning stable market outcomes under uncertainty. |
Meena Jagadeesan; Alexander Wei; Yixin Wang; Michael Jordan; Jacob Steinhardt; | |
255 | Towards Lower Bounds on The Depth of ReLU Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We contribute to a better understanding of the class of functions that is represented by a neural network with ReLU activations and a given architecture. |
Christoph Hertrich; Amitabh Basu; Marco Di Summa; Martin Skutella; | |
256 | The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our analysis in this paper decouples capacity and width via the generalization of neural networks to Deep Gaussian Processes (Deep GP), a class of nonparametric hierarchical models that subsume neural nets. |
Geoff Pleiss; John P. Cunningham; | |
257 | Exact Marginal Prior Distributions of Finite Bayesian Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we derive exact solutions for the function space priors for individual input examples of a class of finite fully-connected feedforward Bayesian neural networks. |
Jacob Zavatone-Veth; Cengiz Pehlevan; | |
258 | Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce spatiotemporal joint filter decomposition to decouple spatial and temporal learning, while preserving spatiotemporal dependency in a video. |
Zichen Miao; Ze Wang; Xiuyuan Cheng; Qiang Qiu; | |
259 | Pooling By Sliced-Wasserstein Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a geometrically-interpretable and generic pooling mechanism for aggregating a set of features into a fixed-dimensional representation. |
Navid Naderializadeh; Joseph Comer; Reed Andrews; Heiko Hoffmann; Soheil Kolouri; | code |
260 | On The Theory of Reinforcement Learning with Once-per-Episode Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a theory of reinforcement learning (RL) in which the learner receives binary feedback only once at the end of an episode. |
Niladri Chatterji; Aldo Pacchiano; Peter Bartlett; Michael Jordan; | |
261 | ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To codify such a difference in nonlinearities and reveal a linear estimation property, we define ResNEsts, i.e., Residual Nonlinear Estimators, by simply dropping nonlinearities at the last residual representation from standard ResNets. We show that wide ResNEsts with bottleneck blocks can always guarantee a very desirable training property that standard ResNets aim to achieve, i.e., adding more blocks does not decrease performance given the same set of basis elements. |
Kuan-Lin Chen; Ching-Hua Lee; Harinath Garudadri; Bhaskar Rao; | |
262 | Locally Private Online Change Point Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our primary aim is to detect changes in the regression function $m_t(x)=\mathbb{E}(Y_t |X_t=x)$ as soon as the change occurs. |
Tom Berrett; Yi Yu; | |
263 | Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approach that incorporates both of these principles and demonstrate its effectiveness in several experiments. |
Kartik Ahuja; Ethan Caballero; Dinghuai Zhang; Jean-Christophe Gagnon-Audet; Yoshua Bengio; Ioannis Mitliagkas; Irina Rish; | |
264 | Repulsive Deep Ensembles Are Bayesian Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce a kernelized repulsive term in the update rule of the deep ensembles. |
Francesco D'Angelo; Vincent Fortuin; | |
265 | BayesIMP: Uncertainty Quantification for Causal Data Fusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the causal data fusion problem, where data arising from multiple causal graphs are combined to estimate the average treatment effect of a target variable. |
Siu Lun Chau; Jean-Francois Ton; Javier Gonz�lez; Yee Teh; Dino Sejdinovic; | |
266 | RMM: Reinforced Memory Management for Class-Incremental Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a dynamic memory management strategy that is optimized for the incremental phases and different object classes. |
Yaoyao Liu; Bernt Schiele; Qianru Sun; | code |
267 | Learning Compact Representations of Neural Networks Using DiscriminAtive Masking (DAM) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel single-stage structured pruning method termed DiscriminAtive Masking (DAM). |
Jie Bu; Arka Daw; M. Maruf; Anuj Karpatne; | code |
268 | Neural Auto-Curricula in Two-Player Zero-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel framework—Neural Auto-Curricula (NAC)—that leverages meta-gradient descent to automate the discovery of the learning update rule without explicit human design. |
Xidong Feng; Oliver Slumbers; Ziyu Wan; Bo Liu; Stephen McAleer; Ying Wen; Jun Wang; Yaodong Yang; | |
269 | ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a remedy we incorporate a coarse-to-fine hierarchy of context by combining the autoregressive formulation with a multinomial diffusion process: Whereas a multistage diffusion process successively compresses and removes information to coarsen an image, we train a Markov chain to invert this process. |
Patrick Esser; Robin Rombach; Andreas Blattmann; Bjorn Ommer; | |
270 | From Global to Local MDI Variable Importances for Random Forests and When They Are Shapley Values Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this context, we first show that the global Mean Decrease of Impurity (MDI) variable importance scores correspond to Shapley values under some conditions. Then, we derive a local MDI importance measure of variable relevance, which has a very natural connection with the global MDI measure and can be related to a new notion of local feature relevance. |
Antonio Sutera; Gilles Louppe; Van Anh Huynh-Thu; Louis Wehenkel; Pierre Geurts; | |
271 | Adversarial Robustness of Streaming Algorithms Through Importance Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce adversarially robust streaming algorithms for central machine learning and algorithmic tasks, such as regression and clustering, as well as their more general counterparts, subspace embedding, low-rank approximation, and coreset construction. |
Vladimir braverman; Avinatan Hasidim; Yossi Matias; Mariano Schain; Sandeep Silwal; Samson Zhou; | |
272 | Tractable Regularization of Probabilistic Circuits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we re-think regularization for PCs and propose two intuitive techniques, data softening and entropy regularization, that both take advantage of PCs’ tractability and still have an efficient implementation as a computation graph. |
Anji Liu; Guy Van den Broeck; | code |
273 | On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we develop a feature space for image transforms, and then use a new measure in this space between augmentations and corruptions called the Minimal Sample Distance to demonstrate there is a strong correlation between similarity and performance. |
Eric Mintun; Alexander Kirillov; Saining Xie; | code |
274 | Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple dynamic distillation-based approach to facilitate unlabeled images from the novel/base dataset. |
Ashraful Islam; Chun-Fu (Richard) Chen; Rameswar Panda; Leonid Karlinsky; Rogerio Feris; Richard Radke; | |
275 | Hypergraph Propagation and Community Selection for Objects Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these problems, we propose a novel hypergraph-based framework that efficiently propagates spatial information in query time and retrieves an object in the database accurately. |
Guoyuan An; Yuchi Huo; Sung-eui Yoon; | |
276 | Deep Learning Is Adaptive to Intrinsic Dimensionality of Model Smoothness in Anisotropic Besov Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand this property, we investigate the approximation and estimation ability of deep learning on {\it anisotropic Besov spaces}. |
Taiji Suzuki; Atsushi Nitanda; | |
277 | QuPeD: Quantized Personalization Via Distillation with Applications to Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a quantized and personalized FL algorithm QuPeD that facilitates collective (personalized model compression) training via knowledge distillation (KD) among clients who have access to heterogeneous data and resources. |
Kaan Ozkara; Navjot Singh; Deepesh Data; Suhas Diggavi; | |
278 | Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation Without Source Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA. |
Jiaxing Huang; Dayan Guan; Aoran Xiao; Shijian Lu; | |
279 | The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study several under-explored dimensions of FI explanations, providing conceptual and empirical improvements for this form of explanation. |
Peter Hase; Harry Xie; Mohit Bansal; | |
280 | Control Variates for Slate Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of off-policy evaluation from batched contextual bandit data with multidimensional actions, often termed slates. |
Nikos Vlassis; Ashok Chandrashekar; Fernando Amat; Nathan Kallus; | |
281 | Stabilizing Deep Q-Learning with ConvNets and Vision Transformers Under Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate causes of instability when using data augmentation in common off-policy RL algorithms. |
Nicklas Hansen; Hao Su; Xiaolong Wang; | |
282 | On Effective Scheduling of Model-based Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the analysis, we propose a framework named AutoMBPO to automatically schedule the real data ratio as well as other hyperparameters in training model-based policy optimization (MBPO) algorithm, a representative running case of model-based methods. |
Hang Lai; Jian Shen; Weinan Zhang; Yimin Huang; Xing Zhang; Ruiming Tang; Yong Yu; Zhenguo Li; | |
283 | Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While applications of these methods have been mostly limited to single-cell genomics, in this work, we develop a theoretical framework for domain adaptation in systems neuroscience. |
Dominic Gonschorek; Larissa H�fling; Klaudia Szatko; Katrin Franke; Timm Schubert; Benjamin Dunn; Philipp Berens; David Klindt; Thomas Euler; | code |
284 | Learning Knowledge Graph-based World Models of Textual Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work focuses on the task of building world models of text-based game environments. |
Prithviraj Ammanabrolu; Mark Riedl; | |
285 | Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide deeper insights into a class of acceleration schemes built on Anderson mixing that improve the convergence of deep RL algorithms. |
Ke Sun; Yafei Wang; Yi Liu; yingnan zhao; Bo Pan; Shangling Jui; Bei Jiang; Linglong Kong; | |
286 | Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop faster techniques for instances where components in the sum are cardinality-based, meaning they depend only on the size of the input set. |
Nate Veldt; Austin R. Benson; Jon Kleinberg; | |
287 | Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. |
Lulu Zheng; Jiarui Chen; Jianhao Wang; Jiamin He; Yujing Hu; Yingfeng Chen; Changjie Fan; Yang Gao; Chongjie Zhang; | |
288 | Two Sides of Meta-Learning Evaluation: In Vs. Out of Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our work aims to inform the meta-learning community about the importance and distinction of ID vs. OOD evaluation, as well as the subtleties of OOD evaluation with current benchmarks. |
Amrith Setlur; Oscar Li; Virginia Smith; | |
289 | Debiased Visual Question Answering from Feature and Sample Perspectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method named D-VQA to alleviate the above challenges from the feature and sample perspectives. |
Zhiquan Wen; Guanghui Xu; Mingkui Tan; Qingyao Wu; Qi Wu; | |
290 | Towards A Unified Game-Theoretic View of Adversarial Perturbations and Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. |
Jie Ren; Die Zhang; Yisen Wang; Lu Chen; Zhanpeng Zhou; Yiting Chen; Xu Cheng; Xin Wang; Meng Zhou; Jie Shi; Quanshi Zhang; | code |
291 | On The Out-of-distribution Generalization of Probabilistic Image Modelling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This motivates our proposal of a Local Autoregressive model that exclusively models local image features towards improving OOD performance. |
Mingtian Zhang; Andi Zhang; Steven McDonagh; | |
292 | Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the application of quasi-Newton methods for solving empirical risk minimization (ERM) problems defined over a large dataset. |
Qiujiang Jin; Aryan Mokhtari; | |
293 | PDE-GCN: Novel Architectures for Graph Neural Networks Motivated By Partial Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a family of architecturesto control this behavior by design. |
Moshe Eliasof; Eldad Haber; Eran Treister; | |
294 | Information Directed Reward Learning for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider an RL setting where the agent can obtain information about the reward only by querying an expert that can, for example, evaluate individual states or provide binary preferences over trajectories. |
David Lindner; Matteo Turchetta; Sebastian Tschiatschek; Kamil Ciosek; Andreas Krause; | |
295 | SSMF: Shifting Seasonal Matrix Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Shifting Seasonal Matrix Factorization approach, namely SSMF, that can adaptively learn multiple seasonal patterns (called regimes), as well as switching between them. |
Koki Kawabata; Siddharth Bhatia; Rui Liu; Mohit Wadhwa; Bryan Hooi; | |
296 | Associative Memories Via Predictive Coding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel neural model for realizing associative memories, which is based on a hierarchical generative network that receives external stimuli via sensory neurons. |
Tommaso Salvatori; Yuhang Song; Yujian Hong; Lei Sha; Simon Frieder; Zhenghua Xu; Rafal Bogacz; Thomas Lukasiewicz; | |
297 | Robust and Differentially Private Mean Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce PRIME, which is the first efficient algorithm that achieves both privacy and robustness for a wide range of distributions. |
Xiyang Liu; Weihao Kong; Sham Kakade; Sewoong Oh; | |
298 | Adaptable Agent Populations Via A Generative Model of Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to learn a space of diverse and high-reward policies in a given environment. |
Kenneth Derek; Phillip Isola; | code |
299 | A No-go Theorem for Robust Acceleration in The Hyperbolic Plane Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we prove that in a noisy setting, there is no analogue of accelerated gradient descent for geodesically convex functions on the hyperbolic plane. |
Linus Hamilton; Ankur Moitra; | |
300 | Privately Learning Mixtures of Axis-Aligned Gaussians Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of learning multivariate Gaussians under the constraint of approximate differential privacy. |
Ishaq Aden-Ali; Hassan Ashtiani; Christopher Liaw; | |
301 | Deep Self-Dissimilarities As Powerful Visual Fingerprints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Features extracted from deep layers of classification networks are widely used as image descriptors. Here, we exploit an unexplored property of these features: their internal dissimilarity. |
Idan Kligvasser; Tamar Shaham; Yuval Bahat; Tomer Michaeli; | |
302 | Invariant Causal Imitation Learning for Generalizable Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging data from multiple environments, we propose Invariant Causal Imitation Learning (ICIL), a novel technique in which we learn a feature representation that is invariant across domains, on the basis of which we learn an imitation policy that matches expert behavior. |
Ioana Bica; Daniel Jarrett; Mihaela van der Schaar; | |
303 | CoAtNet: Marrying Convolution and Attention for All Data Sizes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that while Transformers tend to have larger model capacity, their generalization can be worse than convolutional networks due to the lack of the right inductive bias. |
Zihang Dai; Hanxiao Liu; Quoc Le; Mingxing Tan; | |
304 | Mixed Supervised Object Detection By Transferring Mask Prior and Semantic Similarity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we further transfer mask prior and semantic similarity to bridge the gap between novel categories and base categories. |
Yan Liu; Zhijie Zhang; Li Niu; Junjie Chen; Liqing Zhang; | code |
305 | Celebrating Diversity in Shared Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to introduce diversity in both optimization and representation of shared multi-agent reinforcement learning. |
Li Chenghao; Tonghan Wang; Chengjie Wu; Qianchuan Zhao; Jun Yang; Chongjie Zhang; | |
306 | Rebounding Bandits for Modeling Satiation Effects Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce rebounding bandits, a multi-armed bandit setup, where satiation dynamics are modeled as time-invariant linear dynamical systems. |
Liu Leqi; Fatma Kilinc Karzan; Zachary Lipton; Alan Montgomery; | |
307 | Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we provide sample complexity bounds for cut-selection in branch-and-cut (B&C). |
Maria-Florina F. Balcan; Siddharth Prasad; Tuomas Sandholm; Ellen Vitercik; | |
308 | IQ-Learn: Inverse Soft-Q Learning for Imitation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a method for dynamics-aware IL which avoids adversarial training by learning a single Q-function, implicitly representing both reward and policy. |
Divyansh Garg; Shuvam Chakraborty; Chris Cundy; Jiaming Song; Stefano Ermon; | |
309 | Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Taufe, a novel regularizer that deactivates many undesirable features using OOD examples in the feature extraction layer and thus removes the dependency on the task-specific softmax layer. |
Dongmin Park; Hwanjun Song; Minseok Kim; Jae-Gil Lee; | |
310 | Private Non-smooth ERM and SCO in Subquadratic Steps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. |
Janardhan Kulkarni; Yin Tat Lee; Daogao Liu; | |
311 | Towards Instance-Optimal Offline Reinforcement Learning with Pessimism Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze the \emph{Adaptive Pessimistic Value Iteration} (APVI) algorithm and derive the suboptimality upper bound that nearly matches\[O\left(\sum_{h=1}^H\sum_{s_h, a_h}d^{\pi^\star}_h(s_h, a_h)\sqrt{\frac{\mathrm{Var}_{P_{s_h, a_h}}{(V^\star_{h+1}+r_h)}}{d^\mu_h(s_h, a_h)}}\sqrt{\frac{1}{n}}\right). |
Ming Yin; Yu-Xiang Wang; | |
312 | Speedy Performance Estimation for Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We instead propose to estimate the final test performance based on a simple measure of training speed. |
Robin Ru; Clare Lyle; Lisa Schut; Miroslav Fil; Mark van der Wilk; Yarin Gal; | |
313 | How Tight Can PAC-Bayes Be in The Small Data Regime? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the question: _Given a small number of datapoints, for example $N = 30$, how tight can PAC-Bayes and test set bounds be made? |
Andrew Foong; Wessel Bruinsma; David Burt; Richard Turner; | |
314 | Deep Synoptic Monte-Carlo Planning in Reconnaissance Blind Chess Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces deep synoptic Monte Carlo planning (DSMCP) for large imperfect information games. |
Gregory Clark; | |
315 | Dynamic Analysis of Higher-Order Coordination in Neuronal Assemblies Via De-Sparsified Orthogonal Matching Pursuit Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these shortcomings, we propose an adaptive greedy filtering algorithm based on a discretized mark point-process model of ensemble spiking and a corresponding precise statistical inference framework to identify significant coordinated higher-order spiking activity. |
Shoutik Mukherjee; Behtash Babadi; | |
316 | Efficient Training of Retrieval Models Using Negative Cache Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a novel negative sampling technique for accelerating training with softmax cross-entropy loss. |
Erik Lindgren; Sashank Reddi; Ruiqi Guo; Sanjiv Kumar; | |
317 | Understanding Partial Multi-Label Learning Via Mutual Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of adopting hand-made heuristic strategy, we propose a novel Mutual Information Label Identification for Partial Multilabel Learning (MILI-PML), which is derived from a clear probabilistic formulation and could be easily interpreted theoretically from the mutual information perspective, as well as naturally incorporates the feature/label relevancy considerations. |
Xiuwen Gong; Dong Yuan; Wei Bao; | |
318 | Environment Generation for Zero-Shot Compositional Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we present Compositional Design of Environments (CoDE), which trains a Generator agent to automatically build a series of compositional tasks tailored to the RL agent’s current skill level. |
Izzeddin Gur; Natasha Jaques; Yingjie Miao; Jongwook Choi; Manoj Tiwari; Honglak Lee; Aleksandra Faust; | |
319 | Optimizing Conditional Value-At-Risk of Black-Box Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents two Bayesian optimization (BO) algorithms with theoretical performance guarantee to maximize the conditional value-at-risk (CVaR) of a black-box function: CV-UCB and CV-TS which are based on the well-established principle of optimism in the face of uncertainty and Thompson sampling, respectively. |
Quoc Phong Nguyen; Zhongxiang Dai; Bryan Kian Hsiang Low; Patrick Jaillet; | |
320 | E(n) Equivariant Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs). |
Victor Garcia Satorras; Emiel Hoogeboom; Fabian Fuchs; Ingmar Posner; Max Welling; | |
321 | Revitalizing CNN Attention Via Transformers in Self-Supervised Visual Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL. |
Chongjian GE; Youwei Liang; YIBING SONG; Jianbo Jiao; Jue Wang; Ping Luo; | |
322 | A Critical Look at The Consistency of Causal Estimation with Deep Latent Variable Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate this gap between theory and empirical results with analytical considerations and extensive experiments under multiple synthetic and real-world data sets, using the causal effect variational autoencoder (CEVAE) as a case study. |
Severi Rissanen; Pekka Marttinen; | |
323 | Improving Robustness Using Generated Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how generative models trained solely on the original training set can be leveraged to artificially increase the size of the original training set and improve adversarial robustness to $\ell_p$ norm-bounded perturbations. |
Sven Gowal; Sylvestre-Alvise Rebuffi; Olivia Wiles; Florian Stimberg; Dan Andrei Calian; Timothy A. Mann; | |
324 | An Analysis of Constant Step Size SGD in The Non-convex Regime: Asymptotic Normality and Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to address this shortcoming, in this work, we establish an asymptotic normality result for the constant step size stochastic gradient descent (SGD) algorithm—a widely used algorithm in practice. |
Lu Yu; Krishnakumar Balasubramanian; Stanislav Volgushev; Murat A. Erdogdu; | |
325 | Learning to Learn Graph Topologies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to learn a mapping from node data to the graph structure based on the idea of learning to optimise (L2O). |
Xingyue Pu; Tianyue Cao; Xiaoyun Zhang; Xiaowen Dong; Siheng Chen; | |
326 | Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a generalized GAN framework for tabular synthesis, which combines the adversarial training of GANs and the negative log-density regularization of invertible neural networks. |
JAEHOON LEE; Jihyeon Hyeong; Jinsung Jeon; Noseong Park; Jihoon Cho; | |
327 | Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose new learning-based methods for reducing collision checking to accelerate motion planning by training graph neural networks (GNNs) that perform path exploration and path smoothing. |
Chenning Yu; Sicun Gao; | |
328 | Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike previous works that study ranking from multi-wise comparisons, in this paper, we do not require any parametric model or assumption and work on the fundamental setting where each comparison returns the correct result with probability $1$ or a certain probability larger than $\frac{1}{2}$. |
Wenbo Ren; Jia Liu; Ness Shroff; | |
329 | Efficient Bayesian Network Structure Learning Via Local Markov Boundary Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze the complexity of learning directed acyclic graphical models from observational data in general settings without specific distributional assumptions. |
Ming Gao; Bryon Aragam; | |
330 | Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention. |
Byung-Hoon Kim; Jong Chul Ye; Jae-Jin Kim; | code |
331 | Understanding The Generalization Benefit of Model Invariance from A Data Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the generalization benefit of model invariance by introducing the sample cover induced by transformations, i.e., a representative subset of a dataset that can approximately recover the whole dataset using transformations. |
Sicheng Zhu; Bang An; Furong Huang; | |
332 | Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents new \emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). |
Zihan Zhang; Jiaqi Yang; Xiangyang Ji; Simon S. Du; | |
333 | How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this light, we propose Robust Informative Fine-Tuning (RIFT), a novel adversarial fine-tuning method from an information-theoretical perspective. |
Xinshuai Dong; Anh Tuan Luu; Min Lin; Shuicheng Yan; Hanwang Zhang; | |
334 | Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Recursive Bayesian Networks (RBNs), which generalise and unify PCFGs and DBNs, combining their strengths and containing both as special cases. |
Robert Lieck; Martin Rohrmeier; | |
335 | EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we fix all these deficiencies by proposing and analyzing a new EF mechanism, which we call EF21, which consistently and substantially outperforms EF in practice. |
Peter Richtarik; Igor Sokolov; Ilyas Fatkhullin; | |
336 | Mixture Weights Optimisation for Alpha-Divergence Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses on $\alpha$-divergence minimisation methods for Variational Inference. More precisely, we are interested in algorithms optimising the mixture weights of any given mixture model, without any information on the underlying distribution of its mixture components parameters. |
Kam�lia Daudel; randal douc; | |
337 | Instance-dependent Label-noise Learning Under A Structural Causal Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to model and make use of the causal process in order to correct the label-noise effect.Empirically, the proposed method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets. |
Yu Yao; Tongliang Liu; Mingming Gong; Bo Han; Gang Niu; Kun Zhang; | |
338 | Combining Human Predictions with Model Probabilities Via Confusion Matrices and Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a set of algorithms that combine the probabilistic output of a model with the class-level output of a human. |
Gavin Kerrigan; Padhraic Smyth; Mark Steyvers; | |
339 | $\texttt{LeadCache}$: Regret-Optimal Caching in Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose $\texttt{LeadCache}$ – an efficient online caching policy based on the Follow-the-Perturbed-Leader paradigm. |
Debjit Paria; Abhishek Sinha; | |
340 | Probabilistic Attention for Interactive Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference. |
Prasad Gabbur; Manjot Bilkhu; Javier Movellan; | code |
341 | Influence Patterns for Explaining Information Flow in BERT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce influence patterns, abstractions of sets of paths through a transformer model. |
Kaiji Lu; Zifan Wang; Piotr Mardziel; Anupam Datta; | |
342 | Robust Regression Revisited: Acceleration and Improved Estimation Rates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present nearly-linear time algorithms for robust regression problems with improved runtime or estimation guarantees compared to the state-of-the-art. |
Arun Jambulapati; Jerry Li; Tselil Schramm; Kevin Tian; | |
343 | Automatic Unsupervised Outlier Model Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we tackle the unsupervised outlier model selection (UOMS) problem, and propose MetaOD, a principled, data-driven approach to UOMS based on meta-learning. |
Yue Zhao; Ryan Rossi; Leman Akoglu; | |
344 | Pruning Randomly Initialized Neural Networks with Iterative Randomization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this parameter inefficiency, we introduce a novel framework to prune randomly initialized neural networks with iteratively randomizing weight values (IteRand). |
Daiki Chijiwa; Shin'ya Yamaguchi; Yasutoshi Ida; Kenji Umakoshi; Tomohiro INOUE; | |
345 | Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this, we propose a fully Transformer visual embedding for VLP to better learn visual relation and further promote inter-modal alignment. |
Hongwei Xue; Yupan Huang; Bei Liu; Houwen Peng; Jianlong Fu; Houqiang Li; Jiebo Luo; | |
346 | Stability and Generalization of Bilevel Programming in Hyperparameter Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper attempts to address the issue by presenting an expectation bound w.r.t. the validation set based on uniform stability. |
Fan Bao; Guoqiang Wu; Chongxuan LI; Jun Zhu; Bo Zhang; | |
347 | Regime Switching Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a learning algorithm for this problem, building on spectral method-of-moments estimations for hidden Markov models, belief error control in partially observable Markov decision processes and upper-confidence-bound methods for online learning. |
Xiang Zhou; Yi Xiong; Ningyuan Chen; Xuefeng GAO; | |
348 | MixACM: Mixup-Based Robustness Transfer Via Distillation of Activated Channel Maps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore this question from the perspective of knowledge transfer. |
Awais Muhammad; Fengwei Zhou; Chuanlong Xie; Jiawei Li; Sung-Ho Bae; Zhenguo Li; | |
349 | Localization, Convexity, and Star Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that the offset complexity can be generalized to any loss that satisfies a certain general convexity condition. |
Suhas Vijaykumar; | |
350 | Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we propose a novel target adaptation framework that relies only on silhouette supervision to adapt a source-trained model-based regressor. |
Mugalodi Rakesh; Jogendra Nath Kundu; Varun Jampani; Venkatesh Babu R; | |
351 | Self-Adaptable Point Processes with Nonparametric Time Decays Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we propose SPRITE, a $\underline{S}$elf-adaptable $\underline{P}$oint p$\underline{R}$ocess w$\underline{I}$th nonparametric $\underline{T}$ime d$\underline{E}$cays, which can decouple the influences between every pair of the events and capture various time decays of the influence strengths. |
Zhimeng Pan; Zheng Wang; Jeff M. Phillips; Shandian Zhe; | |
352 | Offline Meta Reinforcement Learning — Identifiability Challenges and Effective Data Collection Strategies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on the recent VariBAD BRL approach, we develop an off-policy BRL method that learns to plan an exploration strategy based on an adaptive neural belief estimate. |
Ron Dorfman; Idan Shenfeld; Aviv Tamar; | code |
353 | RoMA: Robust Model Adaptation for Offline Model-based Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle the issue, we propose a new framework, coined robust model adaptation (RoMA), based on gradient-based optimization of inputs over the DNN. |
Sihyun Yu; Sungsoo Ahn; Le Song; Jinwoo Shin; | |
354 | Flexible Option Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit and extend intra-option learning in the context of deep reinforcement learning, in order to enable updating all options consistent with current primitive action choices, without introducing any additional estimates. |
Martin Klissarov; Doina Precup; | |
355 | Faster Directional Convergence of Linear Neural Networks Under Spherically Symmetric Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study gradient methods for training deep linear neural networks with binary cross-entropy loss. |
Dachao Lin; Ruoyu Sun; Zhihua Zhang; | |
356 | Online Facility Location with Multiple Advice Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the classic facility location problem in the presence of multiple machine-learned advice. |
Matteo Almanza; Flavio Chierichetti; Silvio Lattanzi; Alessandro Panconesi; Giuseppe Re; | |
357 | Credit Assignment in Neural Networks Through Deep Feedback Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce Deep Feedback Control (DFC), a new learning method that uses a feedback controller to drive a deep neural network to match a desired output target and whose control signal can be used for credit assignment. |
Alexander Meulemans; Matilde Tristany Farinha; Javier Garcia Ordonez; Pau Vilimelis Aceituno; Jo�o Sacramento; Benjamin F. Grewe; | |
358 | Robust Online Correlation Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we go beyond worst case analysis, and show that the celebrated Pivot algorithm performs well when given access to a small number of random samples from the input. |
Silvio Lattanzi; Benjamin Moseley; Sergei Vassilvitskii; Yuyan Wang; Rudy Zhou; | |
359 | Neural Additive Models: Interpretable Machine Learning with Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Neural Additive Models (NAMs) which combine some of the expressivity of DNNs with the inherent intelligibility of generalized additive models. |
Rishabh Agarwal; Levi Melnick; Nicholas Frosst; Xuezhou Zhang; Ben Lengerich; Rich Caruana; Geoffrey E. Hinton; | |
360 | Representation Learning for Event-based Visuomotor Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an event variational autoencoder through which compact representations can be learnt directly from asynchronous spatiotemporal event data. |
Sai Vemprala; Sami Mian; Ashish Kapoor; | |
361 | Kernel Functional Optimisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel formulation for kernel selection using efficient Bayesian optimisation to find the best fitting non-parametric kernel. |
Arun Kumar Anjanapura Venkatesh; Alistair Shilton; Santu Rana; Sunil Gupta; Svetha Venkatesh; | |
362 | Generalized Shape Metrics on Neural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A standardized set of analysis tools is now needed to identify how network-level covariates—such as architecture, anatomical brain region, and model organism—impact neural representations (hidden layer activations). Here, we provide a rigorous foundation for these analyses by defining a broad family of metric spaces that quantify representational dissimilarity. |
Alex Williams; Erin Kunz; Simon Kornblith; Scott Linderman; | |
363 | Diverse Message Passing for Attribute with Heterophily Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, the network homophily rate defined with respect to the node labels is extended to attribute homophily rate by taking the attributes as weak labels. |
Liang Yang; Mengzhe Li; Liyang Liu; bingxin niu; Chuan Wang; Xiaochun Cao; Yuanfang Guo; | |
364 | Towards Robust Bisimulation Metric Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we generalize value function approximation bounds for on-policy bisimulation metrics to non-optimal policies and approximate environment dynamics. |
Mete Kemertas; Tristan Aumentado-Armstrong; | |
365 | Beyond BatchNorm: Towards A Unified Understanding of Normalization in Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a first step towards this goal by extending known properties of BatchNorm in randomly initialized deep neural networks (DNNs) to several recently proposed normalization layers. |
Ekdeep Lubana; Robert Dick; Hidenori Tanaka; | |
366 | Representation Learning Beyond Linear Prediction Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that diversity holds even if the target task uses a neural network with multiple layers, as long as source tasks use linear functions. |
Ziping Xu; Ambuj Tewari; | |
367 | Volume Rendering of Neural Implicit Surfaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The goal of this paper is to improve geometry representation and reconstruction in neural volume rendering. |
Lior Yariv; Jiatao Gu; Yoni Kasten; Yaron Lipman; | |
368 | MAUVE: Measuring The Gap Between Neural Text and Human Text Using Divergence Frontiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Mauve, a comparison measure for open-ended text generation, which directly compares the learnt distribution from a text generation model to the distribution of human-written text using divergence frontiers. |
Krishna Pillutla; Swabha Swayamdipta; Rowan Zellers; John Thickstun; Sean Welleck; Yejin Choi; Zaid Harchaoui; | |
369 | Accurately Solving Rod Dynamics with Graph Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this contribution, we introduce a novel method to accelerate iterative solvers for rod dynamics with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations. |
Han Shao; Tassilo Kugelstadt; Torsten H�drich; Wojtek Palubicki; Jan Bender; Soeren Pirk; Dominik Michels; | |
370 | Limiting Fluctuation and Trajectorial Stability of Multilayer Neural Networks with Mean Field Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we initiate the study of the fluctuation in the case of multilayer networks, at any network depth. |
Huy Pham; Phan-Minh Nguyen; | |
371 | Medical Dead-ends and Learning to Identify High-Risk States and Treatments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an inherently different approach that identifies "dead-ends" of a state space. |
Mehdi Fatemi; Taylor W. Killian; Jayakumar Subramanian; Marzyeh Ghassemi; | |
372 | Overcoming The Convex Barrier for Simplex Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Buoyed by this success, we consider the problem of developing similar techniques for verifying robustness to input perturbations within the probability simplex. |
Harkirat Singh Behl; M. Pawan Kumar; Philip Torr; Krishnamurthy Dvijotham; | |
373 | High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider non-convex stochastic optimization using first-order algorithms for which the gradient estimates may have heavy tails. |
Ashok Cutkosky; Harsh Mehta; | |
374 | Batch Normalization Orthogonalizes Representations in Deep Random Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper underlines an elegant property of batch-normalization (BN): Successive batch normalizations with random linear updates make samples increasingly orthogonal. |
Hadi Daneshmand; Amir Joudaki; Francis Bach; | |
375 | Support Vector Machines and Linear Regression Coincide with Very High-dimensional Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the generality of this phenomenon and make the following contributions. |
Navid Ardeshir; Clayton Sanford; Daniel J. Hsu; | |
376 | Coupled Segmentation and Edge Learning Via Dynamic Graph Propagation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a principled end-to-end framework for coupled edge and segmentation learning, where edges are leveraged as pairwise similarity cues to guide segmentation. |
Zhiding Yu; Rui Huang; Wonmin Byeon; Sifei Liu; Guilin Liu; Thomas Breuel; Anima Anandkumar; Jan Kautz; | |
377 | Offline RL Without Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we show that simply doing one step of constrained/regularized policy improvement using an on-policy Q estimate of the behavior policy performs surprisingly well. |
David Brandfonbrener; William F. Whitney; Rajesh Ranganath; Joan Bruna; | |
378 | Continuous Vs. Discrete Optimization of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The extent to which it represents gradient descent is an open question in the theory of deep learning. The current paper studies this question. |
Omer Elkabetz; Nadav Cohen; | |
379 | CrypTen: Secure Multi-Party Computation Meets Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To foster adoption of secure MPC in machine learning, we present CrypTen: a software framework that exposes popular secure MPC primitives via abstractions that are common in modern machine-learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks. |
Brian Knott; Shobha Venkataraman; Awni Hannun; Shubho Sengupta; Mark Ibrahim; Laurens van der Maaten; | |
380 | Can Contrastive Learning Avoid Shortcut Solutions? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we propose implicit feature modification (IFM), a method for altering positive and negative samples in order to guide contrastive models towards capturing a wider variety of predictive features. |
Joshua Robinson; Li Sun; Ke Yu; Kayhan Batmanghelich; Stefanie Jegelka; Suvrit Sra; | |
381 | See More for Scene: Pairwise Consistency Learning for Scene Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to understand scene images and the scene classification CNN models in terms of the focus area. |
Gongwei Chen; Xinhang Song; Bohan Wang; Shuqiang Jiang; | |
382 | Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a loss that performs spectral decomposition on the population augmentation graph and can be succinctly written as a contrastive learning objective on neural net representations. |
Jeff Z. HaoChen; Colin Wei; Adrien Gaidon; Tengyu Ma; | |
383 | Greedy Approximation Algorithms for Active Sequential Hypothesis Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by applications in which the number of hypotheses or actions is massive (e.g., genomics-based cancer detection), we propose efficient (greedy, in fact) algorithms and provide the first approximation guarantees for ASHT, under two types of adaptivity. |
Kyra Gan; Su Jia; Andrew Li; | |
384 | When False Positive Is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose a novel framework on top of the deep learning framework named \textit{Cross-Batch Approximation for Multipartite Ranking (CBA-MR)}. |
Peisong Wen; Qianqian Xu; Zhiyong Yang; Yuan He; Qingming Huang; | |
385 | Convex Polytope Trees and Its Application to VAE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose convex polytope trees (CPT) to expand the family of decision trees by an interpretable generalization of their decision boundary. |
Mohammadreza Armandpour; Ali Sadeghian; Mingyuan Zhou; | |
386 | The Skellam Mechanism for Differentially Private Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the multi-dimensional Skellam mechanism, a discrete differential privacy mechanism based on the difference of two independent Poisson random variables. |
Naman Agarwal; Peter Kairouz; Ziyu Liu; | |
387 | Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$ Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that if the so-called Bernstein condition is satisfied, the term $\Theta(1/\sqrt{n})$ can be avoided, and high probability excess risk bounds of order up to $O(1/n)$ are possible via uniform stability. |
Yegor Klochkov; Nikita Zhivotovskiy; | |
388 | SketchGen: Generating Constrained CAD Sketches Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose SketchGen as a generative model based on a transformer architecture to address the heterogeneity problem by carefully designing a sequential language for the primitives and constraints that allows distinguishing between different primitive or constraint types and their parameters, while encouraging our model to re-use information across related parameters, encoding shared structure. |
Wamiq Para; Shariq Bhat; Paul Guerrero; Tom Kelly; Niloy Mitra; Leonidas J. Guibas; Peter Wonka; | |
389 | CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a simple Contrastive Learning framework for semi-supervised Domain Adaptation (CLDA) that attempts to bridge the intra-domain gap between the labeled and unlabeled target distributions and the inter-domain gap between source and unlabeled target distribution in SSDA. |
Ankit Singh; | |
390 | Differentially Private N-gram Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a new differentially private algorithm for this problem which, in our experiments, significantly outperforms the state-of-the-art. |
Kunho Kim; Sivakanth Gopi; Janardhan Kulkarni; Sergey Yekhanin; | |
391 | Capturing Implicit Hierarchical Structure in 3D Biomedical Images with Self-supervised Hyperbolic Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. |
Joy Hsu; Jeffrey Gu; Gong Wu; Wah Chiu; Serena Yeung; | |
392 | Noisy Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. |
Soon Hoe Lim; N. Benjamin Erichson; Liam Hodgkinson; Michael W. Mahoney; | |
393 | Matrix Encoding Networks for Neural Combinatorial Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Matrix Encoding Network (MatNet) and show how conveniently it takes in and processes parameters of such complex CO problems. |
Yeong-Dae Kwon; Jinho Choo; Iljoo Yoon; Minah Park; Duwon Park; Youngjune Gwon; | |
394 | When Is Unsupervised Disentanglement Possible? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that the assumption of local isometry together with non-Gaussianity of the factors, is sufficient to provably recover disentangled representations from data. |
Daniella Horan; Eitan Richardson; Yair Weiss; | |
395 | Continuous Latent Process Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To optimize our model using maximum likelihood, we propose a novel piecewise construction of a variational posterior process and derive the corresponding variational lower bound using trajectory re-weighting. |
Ruizhi Deng; Marcus A. Brubaker; Greg Mori; Andreas Lehrmann; | |
396 | Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study predictive control in a setting where the dynamics are time-varying and linear, and the costs are time-varying and well-conditioned. |
Yiheng Lin; Yang Hu; Guanya Shi; Haoyuan Sun; Guannan Qu; Adam Wierman; | |
397 | Dataset Distillation with Infinitely Wide Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To that end, we apply a novel distributed kernel-based meta-learning framework to achieve state-of-the-art results for dataset distillation using infinitely wide convolutional neural networks. |
Timothy Nguyen; Roman Novak; Lechao Xiao; Jaehoon Lee; | |
398 | SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simple but efficient memory-disk hybrid indexing and search system, named SPANN, that follows the inverted index methodology. |
Qi Chen; Bing Zhao; Haidong Wang; Mingqin Li; Chuanjie Liu; Zhiyong Zheng; Mao Yang; Jingdong Wang; | code |
399 | Distilling Object Detectors with Feature Richness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above issues, we propose a novel Feature-Richness Score (FRS) method to choose important features that improve generalized detectability during distilling. |
Du Zhixing; Rui Zhang; Ming Chang; xishan zhang; Shaoli Liu; Tianshi Chen; Yunji Chen; | |
400 | Analysis of One-hidden-layer Neural Networks Via The Resolvent Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the asymptotic spectral density of the random feature matrix $M = Y Y^*$ with $Y = f(WX)$ generated by a single-hidden-layer neural network, where $W$ and $X$ are random rectangular matrices with i.i.d. centred entries and $f$ is a non-linear smooth function which is applied entry-wise. |
Vanessa Piccolo; Dominik Schr�der; | |
401 | Grounding Spatio-Temporal Language with Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make progress in this direction, we here introduce a novel spatio-temporal language grounding task where the goal is to learn the meaning of spatio-temporal descriptions of behavioral traces of an embodied agent. |
Tristan Karch; Laetitia Teodorescu; Katja Hofmann; Cl�ment Moulin-Frier; Pierre-Yves Oudeyer; | |
402 | Learning Where to Learn: Gradient Sparsity in Meta and Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this form of meta-learning can be improved by letting the learning algorithm decide which weights to change, i.e., by learning where to learn. |
Johannes von Oswald; Dominic Zhao; Seijin Kobayashi; Simon Schug; Massimo Caccia; Nicolas Zucchet; Jo�o Sacramento; | |
403 | Domain Invariant Representation Learning with Domain Density Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a theoretically grounded method to learn a domain-invariant representation by enforcing the representation network to be invariant under all transformation functions among domains. |
A. Tuan Nguyen; Toan Tran; Yarin Gal; Atilim Gunes Baydin; | |
404 | PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. |
Tao Yu; Cuiling Lan; Wenjun Zeng; Mingxiao Feng; Zhizheng Zhang; Zhibo Chen; | |
405 | Efficient Equivariant Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a general framework of previous equivariant models, which includes G-CNNs and equivariant self-attention layers as special cases. |
Lingshen He; Yuxuan Chen; zhengyang shen; Yiming Dong; Yisen Wang; Zhouchen Lin; | |
406 | Unifying Gradient Estimators for Meta-Reinforcement Learning Via Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide a unifying framework for estimating higher-order derivatives of value functions, based on off-policy evaluation. |
Yunhao Tang; Tadashi Kozuno; Mark Rowland; Remi Munos; Michal Valko; | |
407 | Even Your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed By Self-Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider an iterative variant of self-distillation in a kernel regression setting, in which successive steps incorporate both model outputs and the ground-truth targets. |
Kenneth Borup; Lars Andersen; | |
408 | Compressing Neural Networks: Towards Determining The Optimal Layer-wise Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression. |
Lucas Liebenwein; Alaa Maalouf; Dan Feldman; Daniela Rus; | |
409 | Equilibrium and Non-Equilibrium Regimes in The Learning of Restricted Boltzmann Machines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that this mixing time plays a crucial role in the behavior and stability of the trained model, and that RBMs operate in two well-defined distinct regimes, namely equilibrium and out-of-equilibrium, depending on the interplay between this mixing time of the model and the number of MCMC steps, $k$, used to approximate the gradient. |
Aur�lien Decelle; Cyril Furtlehner; Beatriz Seoane; | |
410 | Imitation with Neural Density Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new framework for Imitation Learning (IL) via density estimation of the expert’s occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. |
Kuno Kim; Akshat Jindal; Yang Song; Jiaming Song; Yanan Sui; Stefano Ermon; | |
411 | Accurate Point Cloud Registration with Robust Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work investigates the use of robust optimal transport (OT) for shape matching. |
Zhengyang Shen; Jean Feydy; Peirong Liu; Ariel Curiale; Ruben San Jose Estepar; Raul San Jose Estepar; Marc Niethammer; | code |
412 | Simple Steps Are All You Need: Frank-Wolfe and Generalized Self-concordant Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We establish the convergence rate of a simple Frank-Wolfe variant that uses the open-loop step size strategy $\gamma_t = 2/(t+2)$, obtaining a $\mathcal{O}(1/t)$ convergence rate for this class of functions in terms of primal gap and Frank-Wolfe gap, where $t$ is the iteration count. |
Alejandro Carderera; Mathieu Besan�on; Sebastian Pokutta; | |
413 | Automatic Data Augmentation for Generalization in Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce three approaches for automatically finding an effective augmentation for any RL task. |
Roberta Raileanu; Maxwell Goldstein; Denis Yarats; Ilya Kostrikov; Rob Fergus; | |
414 | Blending Anti-Aliasing Into Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties. |
Shengju Qian; Hao Shao; Yi Zhu; Mu Li; Jiaya Jia; | |
415 | A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we advocate instead for a hybrid approach based on sparse coding principles that retain the interpretability of classical techniques encoding domain knowledge with handcrafted image priors, while allowing to train model parameters end-to-end without massive amounts of data. |
Theo Bodrito; Alexandre Zouaoui; Jocelyn Chanussot; Julien Mairal; | |
416 | Posterior Collapse and Latent Variable Non-identifiability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider posteriorcollapse as a problem of latent variable non-identifiability. |
Yixin Wang; David Blei; John P. Cunningham; | |
417 | The Benefits of Implicit Regularization from SGD in Least Squares Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we seek to understand these issues in the simpler setting of linear regression (including both underparameterized and overparameterized regimes), where our goal is to make sharp instance-based comparisons of the implicit regularization afforded by (unregularized) average SGD with the explicit regularization of ridge regression. |
Difan Zou; Jingfeng Wu; Vladimir braverman; Quanquan Gu; Dean P. Foster; Sham Kakade; | |
418 | Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the generalization properties of Model-Agnostic Meta-Learning (MAML) algorithms for supervised learning problems. |
Alireza Fallah; Aryan Mokhtari; Asuman Ozdaglar; | |
419 | Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this problem through a factor baseline which exploits independence structure encoded in a novel action-target influence network. |
Thomas Spooner; Nelson Vadori; Sumitra Ganesh; | |
420 | MarioNette: Self-Supervised Sprite Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a deep learning approach that decomposes sprite-based video animations into a disentangled representation of recurring graphic elements in a self-supervised manner. |
Dmitriy Smirnov; MICHAEL GHARBI; Matthew Fisher; Vitor Guizilini; Alexei Efros; Justin M. Solomon; | |
421 | RLlib Flow: Distributed Reinforcement Learning Is A Dataflow Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we re-examine the challenges posed by distributed RL and try to view it through the lens of an old idea: distributed dataflow. |
Eric Liang; Zhanghao Wu; Michael Luo; Sven Mika; Joseph E. Gonzalez; Ion Stoica; | code |
422 | Improve Agents Without Retraining: Parallel Tree Search with Off-Policy Correction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we introduce a novel off-policy correction term that accounts for the mismatch between the pre-trained value and its corresponding TS policy by penalizing under-sampled trajectories. |
Gal Dalal; Assaf Hallak; Steven Dalton; iuri frosio; Shie Mannor; Gal Chechik; | |
423 | Redesigning The Transformer Architecture with Insights from Multi-particle Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the problem of approximating the two central components of the Transformer — multi-head self-attention and point-wise feed-forward transformation, with reduced parameter space and computational complexity. |
Subhabrata Dutta; Tanya Gautam; Soumen Chakrabarti; Tanmoy Chakraborty; | |
424 | Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this gap via a comprehensive investigation on the impact of network width and depth on the robustness of adversarially trained DNNs. |
Hanxun Huang; Yisen Wang; Sarah Erfani; Quanquan Gu; James Bailey; Xingjun Ma; | |
425 | Center Smoothing: Certified Robustness for Networks with Structured Outputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc. |
Aounon Kumar; Tom Goldstein; | |
426 | Breaking The Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on improving the per iteration cost of CGM. |
Zhaozhuo Xu; Zhao Song; Anshumali Shrivastava; | |
427 | Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we perform a large-scale benchmarking of dozens of deep neural network models in mouse visual cortex with both representational similarity analysis and neural regression. |
Colin Conwell; David Mayo; Andrei Barbu; Michael Buice; George Alvarez; Boris Katz; | |
428 | A Topological Perspective on Causal Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs). |
Duligur Ibeling; Thomas Icard; | |
429 | Parameter Inference with Bifurcation Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a gradient-based approach for inferring the parameters of differential equations that produce a user-specified bifurcation diagram. |
Gregory Szep; Neil Dalchau; Attila Csik�sz-Nagy; | |
430 | Scalable Thompson Sampling Using Sparse Gaussian Process Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform a theoretical and empirical analysis of scalable TS. |
Sattar Vakili; Henry Moss; Artem Artemev; Vincent Dutordoir; Victor Picheny; | |
431 | Robust Counterfactual Explanations on Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel method to generate robust counterfactual explanations on GNNs by explicitly modelling the common decision logic of GNNs on similar input graphs. |
Mohit Bajaj; Lingyang Chu; Zi Yu Xue; Jian Pei; Lanjun Wang; Peter Cho-Ho Lam; Yong Zhang; | |
432 | Similarity and Matching of Neural Network Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We employ a toolset — dubbed Dr. Frankenstein — to analyse the similarity of representations in deep neural networks. With this toolset we aim to match the activations on given layers of two trained neural networks by joining them with a stitching layer. |
Adri�n Csisz�rik; P�ter Kor�si-Szab�; �kos Matszangosz; Gergely Papp; D�niel Varga; | |
433 | DOCTOR: A Simple Method for Detecting Misclassification Errors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose DOCTOR, a simple method that aims to identify whether the prediction of a DNN classifier should (or should not) be trusted so that, consequently, it would be possible to accept it or to reject it. |
Federica Granese; Marco Romanelli; Daniele Gorla; Catuscia Palamidessi; Pablo Piantanida; | |
434 | Contrastive Laplacian Eigenmaps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend the celebrated Laplacian Eigenmaps with contrastive learning, and call them COntrastive Laplacian EigenmapS (COLES). |
Hao Zhu; Ke Sun; Peter Koniusz; | |
435 | Machine Learning Structure Preserving Brackets for Forecasting Irreversible Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present a novel parameterization of dissipative brackets from metriplectic dynamical systems appropriate for learning \emph{irreversible} dynamics with unknown a priori model form. |
Kookjin Lee; Nathaniel Trask; Panos Stinis; | |
436 | On The Variance of The Fisher Information for Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In practice, it is almost always estimated based on empirical samples. We investigate two such estimators based on two equivalent representations of the FIM — both unbiased and consistent. |
Alexander Soen; Ke Sun; | |
437 | A$^2$-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Attribute-Aware hashing Network (A$^2$-Net) for generating attribute-aware hash codes to not only make the retrieval process efficient, but also establish explicit correspondences between hash codes and visual attributes. |
Xiu-Shen Wei; Yang Shen; Xuhao Sun; Han-Jia Ye; Jian Yang; | |
438 | Shape Registration in The Time of Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. |
Giovanni Trappolini; Luca Cosmo; Luca Moschella; Riccardo Marin; Simone Melzi; Emanuele Rodol�; | |
439 | Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such a problem, we introduce a novel formulation, combinatorial construction, which requires a building agent to assemble unit primitives (i.e., LEGO bricks) sequentially — every connection between two bricks must follow a fixed rule, while no bricks mutually overlap. |
Hyunsoo Chung; Jungtaek Kim; Boris Knyazev; Jinhwi Lee; Graham W. Taylor; Jaesik Park; Minsu Cho; | |
440 | Dissecting The Diffusion Process in Linear Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we dissect the feature propagation steps of linear GCNs from a perspective of continuous graph diffusion, and analyze why linear GCNs fail to benefit from more propagation steps. |
Yifei Wang; Yisen Wang; Jiansheng Yang; Zhouchen Lin; | |
441 | Dynamic Grained Encoder for Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces sparse queries for vision transformers to exploit the intrinsic spatial redundancy of natural images and save computational costs. |
Lin Song; Songyang Zhang; Songtao Liu; Zeming Li; Xuming He; Hongbin Sun; Jian Sun; Nanning Zheng; | code |
442 | Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a novel framework to analyze this empirical result regarding negative samples using the coupon collector’s problem. |
Kento Nozawa; Issei Sato; | |
443 | On UMAP's True Loss Function Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate UMAP’s sampling based optimization scheme in detail. |
Sebastian Damrich; Fred A. Hamprecht; | |
444 | Fast Pure Exploration Via Frank-Wolfe Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of active pure exploration with fixed confidence in generic stochastic bandit environments. |
Po-An Wang; Ruo-Chun Tzeng; Alexandre Proutiere; | |
445 | IFlow: Numerically Invertible Flows for Efficient Lossless Compression Via A Uniform Coder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss lossless compression using normalizing flows which have demonstrated a great capacity for achieving high compression ratios. |
Shifeng Zhang; Ning Kang; Tom Ryder; Zhenguo Li; | |
446 | History Aware Multimodal Transformer for Vision-and-Language Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we introduce a History Aware Multimodal Transformer (HAMT) to incorporate a long-horizon history into multimodal decision making. |
Shizhe Chen; Pierre-Louis Guhur; Cordelia Schmid; Ivan Laptev; | |
447 | Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two specific algorithms for this task: a generic scheme which improves over baselines, and a more tailored approach which performs even better. |
Feng Liu; Wenkai Xu; Jie Lu; Danica J. Sutherland; | |
448 | Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets, an iterative process to significantly change model behavior by crafting and fine-tuning on a dataset that reflects a predetermined set of target values. |
Irene Solaiman; Christy Dennison; | |
449 | The Lazy Online Subgradient Algorithm Is Universal on Strongly Convex Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study Online Lazy Gradient Descent for optimisation on a strongly convex domain. |
Daron Anderson; Douglas Leith; | |
450 | Computer-Aided Design As Language Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a machine learning model capable of automatically generating such sketches. |
Yaroslav Ganin; Sergey Bartunov; Yujia Li; Ethan Keller; Stefano Saliceti; | |
451 | COHESIV: Contrastive Object and Hand Embedding Segmentation In Video Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we learn to segment hands and hand-held objects from motion. |
Dandan Shan; Richard Higgins; David Fouhey; | |
452 | ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Bayesian Pseudocoresets Exemplar VAE (ByPE-VAE), a new variant of VAE with a prior based on Bayesian pseudocoreset. |
Qingzhong Ai; LIRONG HE; SHIYU LIU; Zenglin Xu; | code |
453 | Recovery Analysis for Plug-and-Play Priors Using The Restricted Eigenvalue Condition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this gap by showing how to establish theoretical recovery guarantees for PnP/RED by assuming that the solution of these methods lies near the fixed-points of a deep neural network. |
Jiaming Liu; Salman Asif; Brendt Wohlberg; Ulugbek Kamilov; | |
454 | Group Equivariant Subsampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we first introduce translation equivariant subsampling/upsampling layers that can be used to construct exact translation equivariant CNNs. We then generalise these layers beyond translations to general groups, thus proposing group equivariant subsampling/upsampling. |
Jin Xu; Hyunjik Kim; Thomas Rainforth; Yee Teh; | |
455 | Data Sharing and Compression for Cooperative Networked Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a solution to learn succinct, highly-compressed forecasts that are co-designed with a modular controller’s task objective. |
Jiangnan Cheng; Marco Pavone; Sachin Katti; Sandeep Chinchali; Ao Tang; | |
456 | Hyperbolic Procrustes Analysis Using Riemannian Geometry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we take a purely geometric approach for label-free alignment of hierarchical datasets and introduce hyperbolic Procrustes analysis (HPA). |
Ya-Wei Eileen Lin; Yuval Kluger; Ronen Talmon; | |
457 | No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model. |
Mi Luo; Fei Chen; Dapeng Hu; Yifan Zhang; Jian Liang; Jiashi Feng; | |
458 | Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an inexpensive preconditioner for the matrix sensing variant of nonconvex matrix factorization that restores the convergence rate of gradient descent back to linear, even in the over-parameterized case, while also making it agnostic to possible ill-conditioning in the ground truth. |
Jialun Zhang; Salar Fattahi; Richard Zhang; | |
459 | Improving Contrastive Learning on Imbalanced Data Via Open-World Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present an open-world unlabeled data sampling framework called Model-Aware K-center (MAK), which follows three simple principles: (1) tailness, which encourages sampling of examples from tail classes, by sorting the empirical contrastive loss expectation (ECLE) of samples over random data augmentations; (2) proximity, which rejects the out-of-distribution outliers that may distract training; and (3) diversity, which ensures diversity in the set of sampled examples. |
Ziyu Jiang; Tianlong Chen; Ting Chen; Zhangyang Wang; | code |
460 | Searching for Efficient Transformers for Language Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we aim to reduce the costs of Transformers by searching for a more efficient variant. |
David So; Wojciech Manke; Hanxiao Liu; Zihang Dai; Noam Shazeer; Quoc Le; | |
461 | Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new training objective which minimizes the reverse KL-divergence to a \emph{Proxy-Dirichlet} target derived from the ensemble. |
Max Ryabinin; Andrey Malinin; Mark Gales; | |
462 | Multi-Person 3D Motion Prediction with Multi-Range Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel framework for multi-person 3D motion trajectory prediction. |
Jiashun Wang; Huazhe Xu; Medhini Narasimhan; Xiaolong Wang; | code |
463 | STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our insights on this trade-off provides guidelines for choosing the four important design elements for FL algorithms, the update frequency, directions, and minibatch sizes to achieve the best performance.} |
Prashant Khanduri; PRANAY SHARMA; Haibo Yang; Mingyi Hong; Jia Liu; Ketan Rajawat; Pramod Varshney; | |
464 | Bubblewrap: Online Tiling and Real-time Flow Prediction on Neural Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a method that combines fast, stable dimensionality reduction with a soft tiling of the resulting neural manifold, allowing dynamics to be approximated as a probability flow between tiles. |
Anne Draelos; Pranjal Gupta; Na Young Jun; Chaichontat Sriworarat; John Pearson; | |
465 | The Semi-Random Satisfaction of Voting Axioms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We initiate the work towards a comprehensive picture of the worst average-case satisfaction of voting axioms in semi-random models, to provide a finer and more realistic foundation for comparing voting rules. |
Lirong Xia; | |
466 | Deep Marching Tetrahedra: A Hybrid Representation for High-Resolution 3D Shape Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce DMTet, a deep 3D conditional generative model that can synthesize high-resolution 3D shapes using simple user guides such as coarse voxels. |
Tianchang Shen; Jun Gao; Kangxue Yin; Ming-Yu Liu; Sanja Fidler; | code |
467 | Learning to Combine Per-Example Solutions for Neural Program Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the Cross Aggregator neural network module based on a multi-head attention mechanism that learns to combine the cues present in these per-example solutions to synthesize a global solution. |
Disha Shrivastava; Hugo Larochelle; Daniel Tarlow; | |
468 | On Success and Simplicity: A Second Look at Transferable Targeted Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we, for the first time, identify that a very simple logit loss can largely surpass the commonly adopted cross-entropy loss, and yield even better results than the resource-intensive state of the art. |
Zhengyu Zhao; Zhuoran Liu; Martha Larson; | code |
469 | Provably Efficient, Succinct, and Precise Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of explaining the predictions of an arbitrary blackbox model $f$: given query access to $f$ and an instance $x$, output a small set of $x$’s features that in conjunction essentially determines $f(x)$. |
Guy Blanc; Jane Lange; Li-Yang Tan; | |
470 | Refined Learning Bounds for Kernel and Approximate $k$-Means Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the statistical properties of kernel $k$-means and Nystr\"{o}m-based kernel $k$-means, and obtain optimal clustering risk bounds, which improve the existing risk bounds. |
Yong Liu; | |
471 | Learning Causal Semantic Representation for Out-of-Distribution Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the problem, we propose a Causal Semantic Generative model (CSG) based on a causal reasoning so that the two factors are modeled separately, and develop methods for OOD prediction from a single training domain, which is common and challenging. |
Chang Liu; Xinwei Sun; Jindong Wang; Haoyue Tang; Tao Li; Tao Qin; Wei Chen; Tie-Yan Liu; | |
472 | A First-order Primal-dual Method with Adaptivity to Local Smoothness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an adaptive version of the Condat-V? algorithm, which alternates between primal gradient steps and dual proximal steps. |
Maria-Luiza Vladarean; Yura Malitsky; Volkan Cevher; | |
473 | A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this theory, we propose a novel self-labeling refinement approach for contrastive learning. |
Pan Zhou; Caiming Xiong; Xiaotong Yuan; Steven Chu Hong Hoi; | |
474 | Adversarial Robustness with Semi-Infinite Constrained Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take a constrained learning approach to address these questions and to provide a theoretical foundation for robust learning. |
Alexander Robey; Luiz Chamon; George Pappas; Hamed Hassani; Alejandro Ribeiro; | code |
475 | Conformal Time-series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend the inductive conformal prediction framework to the time-series forecasting setup, and propose a lightweight algorithm to address all of the above limitations, providing uncertainty estimates with theoretical guarantees for any multi-horizon forecast predictor and any dataset with minimal exchangeability assumptions. |
Kamile Stankeviciute; Ahmed M. Alaa; Mihaela van der Schaar; | |
476 | A 3D Generative Model for Structure-Based Drug Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a 3D generative model that generates molecules given a designated 3D protein binding site. |
Shitong Luo; Jiaqi Guan; Jianzhu Ma; Jian Peng; | |
477 | Bootstrapping The Error of Oja's Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Since estimating the covariance matrix associated with the approximating distribution requires knowledge of unknown model parameters, we propose a multiplier bootstrap algorithm that may be updated in an online manner. |
Robert Lunde; Purnamrita Sarkar; Rachel Ward; | |
478 | Landscape Analysis of An Improved Power Method for Tensor Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the optimization formulation for symmetric tensor decomposition recently introduced in the Subspace Power Method (SPM) of Kileel and Pereira. |
Joe Kileel; Timo Klock; Jo�o Pereira; | |
479 | Curriculum Offline Imitating Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to take advantage of IL but mitigate such a drawback. |
Minghuan Liu; Hanye Zhao; Zhengyu Yang; Jian Shen; Weinan Zhang; Li Zhao; Tie-Yan Liu; | |
480 | Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address those issues, this paper proposes a direct pose-level inference strategy that is free of bounding box detection and keypoint grouping. |
Dongkai Wang; Shiliang Zhang; Gang Hua; | |
481 | Ising Model Selection Using $\ell_{1}$-Regularized Linear Regression: A Statistical Mechanics Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We theoretically analyze the typical learning performance of $\ell_{1}$-regularized linear regression ($\ell_1$-LinR) for Ising model selection using the replica method from statistical mechanics. |
Xiangming Meng; Tomoyuki Obuchi; Yoshiyuki Kabashima; | |
482 | Conformal Prediction Using Conditional Histograms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper develops a conformal method to compute prediction intervals for non-parametric regression that can automatically adapt to skewed data. |
Matteo Sesia; Yaniv Romano; | |
483 | Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a new framework termed Contrastive Graph Poisson Networks (CGPN) for node classification under extremely limited labeled data. |
Sheng Wan; Yibing Zhan; Liu Liu; Baosheng Yu; Shirui Pan; Chen Gong; | |
484 | Collaborative Uncertainty in Multi-Agent Trajectory Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we propose a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from the interaction module. |
Bohan Tang; Yiqi Zhong; Ulrich Neumann; Gang Wang; Siheng Chen; Ya Zhang; | |
485 | Network-to-Network Regularization: Enforcing Occam's Razor to Improve Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by these findings, we propose, in this work, a novel measure of complexity called Kolmogorov Growth (KG), which we use to derive new generalization error bounds that only depend on the final choice of the classification function. |
Rohan Ghosh; Mehul Motani; | |
486 | Generalized and Discriminative Few-Shot Object Detection Via SVD-Dictionary Enhancement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore employing Singular Value Decomposition (SVD) to boost both the generalization and discrimination abilities. |
Aming WU; Suqi Zhao; Cheng Deng; Wei Liu; | |
487 | Conditioning Sparse Variational Gaussian Processes for Online Decision-making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose online variational conditioning (OVC), a procedure for efficiently conditioning SVGPs in an online setting that does not require re-training through the evidence lower bound with the addition of new data. |
Wesley J. Maddox; Samuel Stanton; Andrew G. Wilson; | |
488 | Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network Using SGD and Weight Decay Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we comprehensively reveal the learning dynamics of normalized neural network using Stochastic Gradient Descent (with momentum) and Weight Decay (WD), named as Spherical Motion Dynamics (SMD). |
Ruosi Wan; Zhanxing Zhu; Xiangyu Zhang; Jian Sun; | |
489 | Imitating Deep Learning Dynamics Via Locally Elastic Stochastic Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we model the evolution of features during deep learning training using a set of stochastic differential equations (SDEs) that each corresponding to a training sample. |
Jiayao Zhang; Hua Wang; Weijie Su; | |
490 | Probabilistic Forecasting: A Level-Set Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we therefore present Level Set Forecaster (LSF), a simple yet effective general approach to transform a point estimator into a probabilistic one. |
Hilaf Hasson; Bernie Wang; Tim Januschowski; Jan Gasthaus; | |
491 | Roto-translated Local Coordinate Frames For Interacting Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As ignoring these invariances leads to worse generalization, in this work we propose local coordinate systems per node-object to induce roto-translation invariance to the geometric graph of the interacting dynamical system. |
Miltiadis Kofinas; Naveen Nagaraja; Efstratios Gavves; | |
492 | ParK: Sound and Efficient Kernel Ridge Regression By Feature Space Partitions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce ParK, a new large-scale solver for kernel ridge regression. |
Luigi Carratino; Stefano Vigogna; Daniele Calandriello; Lorenzo Rosasco; | |
493 | Scaling Gaussian Processes with Derivative Information Using Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce methods to achieve fully scalable Gaussian process regression with derivatives using variational inference. |
Misha Padidar; Xinran Zhu; Leo Huang; Jacob Gardner; David Bindel; | |
494 | On The Representation of Solutions to Elliptic PDEs in Barron Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper derives complexity estimates of the solutions of d-dimensional second-order elliptic PDEs in the Barron space, that is a set of functions admitting the integral of certain parametric ridge function against a probability measure on the parameters. |
Ziang Chen; Jianfeng Lu; Yulong Lu; | |
495 | A/B Testing for Recommender Systems in A Two-sided Marketplace Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose (i) a quantification of the quality of a producer side experiment design, and (ii) a new experiment design mechanism that generates high-quality experiments based on this quantification. |
Preetam Nandy; Divya Venugopalan; Chun Lo; Shaunak Chatterjee; | |
496 | Retiring Adult: New Datasets for Fair Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our primary contribution is a suite of new datasets derived from US Census surveys that extend the existing data ecosystem for research on fair machine learning. |
Frances Ding; Moritz Hardt; John Miller; Ludwig Schmidt; | |
497 | Cardinality Constrained Submodular Maximization for Random Streams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of maximizing submodular functions in single-pass streaming and secretaries-with-shortlists models, both with random arrival order. |
Paul Liu; Aviad Rubinstein; Jan Vondrak; Junyao Zhao; | |
498 | Self-Instantiated Recurrent Units with Dynamic Soft Recursion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given diverse and even growing data modalities (e.g., logic, algorithmic input and output, music, code, images, and language) that can be expressed in sequences and may benefit from more architectural flexibility, we propose the self-instantiated recurrent unit (Self-IRU) with a novel inductive bias towards dynamic soft recursion. |
Aston Zhang; Yi Tay; Yikang Shen; Alvin Chan Guo Wei; SHUAI ZHANG; | |
499 | Sparse Uncertainty Representation in Deep Learning with Inducing Weights Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we augment each weight matrix with a small inducing weight matrix, projecting the uncertainty quantification into a lower dimensional space. |
Hippolyt Ritter; Martin Kukla; Cheng Zhang; Yingzhen Li; | |
500 | Scalable Inference of Sparsely-changing Gaussian Markov Random Fields Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we introduce a new class of constrained optimization problems for the inference of sparsely-changing Gaussian MRFs (GMRFs). |
Salar Fattahi; Andres Gomez; | |
501 | Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel conditional neural process-based approach for few-shot text classification that learns to transfer from other diverse tasks with rich annotation. |
Jixuan Wang; Kuan-Chieh Wang; Frank Rudzicz; Michael Brudno; | |
502 | Learnability of Linear Thresholds from Label Proportions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of properly learning linear threshold functions (LTFs) in the learning from label proportions (LLP) framework. |
Rishi Saket; | |
503 | A Variational Approximate Posterior for The Deep Wishart Process Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we give a novel approach to obtaining flexible distributions over positive semi-definite matrices by generalising the Bartlett decomposition of the Wishart probability density. |
Sebastian Ober; Laurence Aitchison; | |
504 | Neural Pseudo-Label Optimism for The Bank Loan Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Pseudo-Label Optimism (PLOT), a conceptually and computationally simple method for this setting applicable to DNNs. |
Aldo Pacchiano; Shaun Singh; Edward Chou; Alex Berg; Jakob Foerster; | |
505 | Visualizing The Emergence of Intermediate Visual Patterns in DNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. |
Mingjie Li; Shaobo Wang; Quanshi Zhang; | |
506 | Learning 3D Dense Correspondence Via Canonical Point Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category. |
An-Chieh Cheng; Xueting Li; Min Sun; Ming-Hsuan Yang; Sifei Liu; | |
507 | Speech-T: Transducer for Text to Speech and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Considering that monotonic alignments are also critical to text to speech (TTS) synthesis and streaming TTS is also an important application scenario, in this work, we explore the possibility of applying Transducer to TTS and more. |
Jiawei Chen; Xu Tan; Yichong Leng; Jin Xu; Guihua Wen; Tao Qin; Tie-Yan Liu; | |
508 | Multi-modal Dependency Tree for Video Captioning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate a graph-structured model for caption generation by explicitly modeling the hierarchical structure in the sentences to further improve the fluency and relevance of sentences. |
Wentian Zhao; Xinxiao Wu; Jiebo Luo; | |
509 | Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we follow Rodomanov and Nesterov’s work to study quasi-Newton methods. |
Dachao Lin; Haishan Ye; Zhihua Zhang; | |
510 | Neural Tangent Kernel Maximum Mean Discrepancy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel neural network Maximum Mean Discrepancy (MMD) statistic by identifying a new connection between neural tangent kernel (NTK) and MMD. |
Xiuyuan Cheng; Yao Xie; | |
511 | Subgraph Federated Learning with Missing Neighbor Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, towards the novel yet realistic setting of subgraph federated learning, we propose two major techniques: (1) FedSage, which trains a GraphSage model based on FedAvg to integrate node features, link structures, and task labels on multiple local subgraphs; (2) FedSage+, which trains a missing neighbor generator along FedSage to deal with missing links across local subgraphs. |
Ke ZHANG; Carl Yang; Xiaoxiao Li; Lichao Sun; Siu Ming Yiu; | |
512 | Bellman-consistent Pessimism for Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the notion of Bellman-consistent pessimism for general function approximation: instead of calculating a point-wise lower bound for the value function, we implement pessimism at the initial state over the set of functions consistent with the Bellman equations. |
Tengyang Xie; Ching-An Cheng; Nan Jiang; Paul Mineiro; Alekh Agarwal; | |
513 | Can You Learn An Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that recurrent networks trained to solve simple problems with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference. |
Avi Schwarzschild; Eitan Borgnia; Arjun Gupta; Furong Huang; Uzi Vishkin; Micah Goldblum; Tom Goldstein; | |
514 | Sub-Linear Memory: How to Make Performers SLiM Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We conduct a thorough complexity analysis of Performers, a class which includes most recent linear Transformer mechanisms. |
Valerii Likhosherstov; Krzysztof M. Choromanski; Jared Quincy Davis; Xingyou Song; Adrian Weller; | |
515 | Efficient Learning of Discrete-Continuous Computation Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: First, we show that increasing the scale parameter of the Gumbel noise perturbations during training improves the learning behavior. Second, we propose dropout residual connections specifically tailored to stochastic, discrete-continuous computation graphs. |
David Friede; Mathias Niepert; | |
516 | VQ-GNN: A Universal Framework to Scale Up Graph Neural Networks Using Vector Quantization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a principled and fundamentally different approach, VQ-GNN, a universal framework to scale up any convolution-based GNNs using Vector Quantization (VQ) without compromising the performance. |
Mucong Ding; Kezhi Kong; Jingling Li; Chen Zhu; John Dickerson; Furong Huang; Tom Goldstein; | |
517 | Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning By Finding Flat Minima Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose to search for flat local minima of the base training objective function and then fine-tune the model parameters within the flat region on new tasks. |
Guangyuan SHI; JIAXIN CHEN; Wenlong Zhang; Li-Ming Zhan; Xiao-Ming Wu; | code |
518 | Functional Neural Networks for Parametric Image Restoration Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel system called functional neural network (FuncNet) to solve a parametric image restoration problem with a single model. |
Fangzhou Luo; Xiaolin Wu; Yanhui Guo; | |
519 | Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we consider this problem from the lens of topological data analysis (TDA) and develop a generic computational tool that is built on rigorous mathematical foundations. |
Tolga Birdal; Aaron Lou; Leonidas J. Guibas; Umut Simsekli; | |
520 | GemNet: Universal Directional Graph Neural Networks for Molecules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that GNNs with directed edge embeddings and two-hop message passing are indeed universal approximators for predictions that are invariant to translation, and equivariant to permutation and rotation. We then leverage these insights and multiple structural improvements to propose the geometric message passing neural network (GemNet). |
Johannes Klicpera; Florian Becker; Stephan G�nnemann; | |
521 | Loss Function Based Second-order Jensen Inequality and Its Application to Particle Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we tackle this problem in light of PAC-Bayesian analysis. |
Futoshi Futami; Tomoharu Iwata; naonori ueda; Issei Sato; Masashi Sugiyama; | |
522 | Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of online learning in the presence of distribution shifts that occur at an unknown rate and of unknown intensity. |
Aodong Li; Alex Boyd; Padhraic Smyth; Stephan Mandt; | |
523 | Asynchronous Decentralized SGD with Quantized and Local Updates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider decentralized optimization in the simpler, but harder to analyze, \emph{asynchronous gossip} model, in which communication occurs in discrete, randomly chosen pairings among nodes. |
Giorgi Nadiradze; Amirmojtaba Sabour; Peter Davies; Shigang Li; Dan Alistarh; | |
524 | Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of learning in the stochastic shortest path (SSP) setting, where an agent seeks to minimize the expected cost accumulated before reaching a goal state. |
Jean Tarbouriech; Runlong Zhou; Simon S. Du; Matteo Pirotta; Michal Valko; Alessandro Lazaric; | |
525 | Nested Counterfactual Identification from Arbitrary Surrogate Experiments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. |
Juan Correa; Sanghack Lee; Elias Bareinboim; | |
526 | Sim and Real: Better Together Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an algorithm for balancing the large number of samples from the high throughput but less accurate simulation and the low-throughput, high-fidelity and costly samples from the real environment. |
Shirli Di-Castro Shashua; Dotan Di Castro; Shie Mannor; | |
527 | Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we are devoted to trustworthy multimodal regression which is critical in cost-sensitive domains. |
Huan Ma; Zongbo Han; Changqing Zhang; Huazhu Fu; Joey Tianyi Zhou; Qinghua Hu; | |
528 | An Empirical Study of Adder Neural Networks for Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an empirical study of AdderNets for object detection. |
Xinghao Chen; Chang Xu; Minjing Dong; Chunjing XU; Yunhe Wang; | |
529 | Does Knowledge Distillation Really Work? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that while knowledge distillation can improve student generalization, it does not typically work as it is commonly understood: there often remains a surprisingly large discrepancy between the predictive distributions of the teacher and the student, even in cases when the student has the capacity to perfectly match the teacher. |
Samuel Stanton; Pavel Izmailov; Polina Kirichenko; Alexander A. Alemi; Andrew G. Wilson; | |
530 | Teachable Reinforcement Learning Via Advice Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new supervision paradigm for interactive learning based on teachable decision-making systems, which learn from structured advice provided by an external teacher. |
Olivia Watkins; Abhishek Gupta; Trevor Darrell; Pieter Abbeel; Jacob Andreas; | |
531 | Antipodes of Label Differential Privacy: PATE and ALIBI Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate their effectiveness on standard benchmarks. |
Mani Malek Esmaeili; Ilya Mironov; Karthik Prasad; Igor Shilov; Florian Tramer; | code |
532 | Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To elucidate the mechanisms responsible for asymmetry in visual search, we propose a computational model that takes a target and a search image as inputs and produces a sequence of eye movements until the target is found. |
Shashi Kant Gupta; Mengmi Zhang; CHIA-CHIEN WU; Jeremy Wolfe; Gabriel Kreiman; | code |
533 | On The Universality of Graph Neural Networks on Large Random Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the approximation power of Graph Neural Networks (GNNs) on latent position random graphs. |
Nicolas Keriven; Alberto Bietti; Samuel Vaiter; | |
534 | Inverse Reinforcement Learning in A Continuous State Space with Formal Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide a new IRL algorithm for the continuous state space setting with unknown transition dynamics by modeling the system using a basis of orthonormal functions. |
Gregory Dexter; Kevin Bello; Jean Honorio; | |
535 | Adversarial Attacks on Graph Classifiers Via Bayesian Optimisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel Bayesian optimisation-based attack method for graph classification models. |
Xingchen Wan; Henry Kenlay; Robin Ru; Arno Blaas; Michael Osborne; Xiaowen Dong; | |
536 | Regulating Algorithmic Filtering on Social Media Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine three questions. First, given a regulation, how would one design an audit to enforce it? Second, does the audit impose a performance cost on the platform? Third, how does the audit affect the content that the platform is incentivized to filter? |
Sarah Cen; Devavrat Shah; | |
537 | Argmax Centroid Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general method to construct centroid approximation for the distribution of maximum points of a random function (a.k.a. argmax distribution), which finds broad applications in machine learning. |
Chengyue Gong; Mao Ye; Qiang Liu; | |
538 | Contrastive Learning of Global and Local Video Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to learn video representations that generalize to both the tasks which require global semantic information (e.g., classification) and the tasks that require local fine-grained spatio-temporal information (e.g., localization). |
Shuang Ma; Zhaoyang Zeng; Daniel McDuff; Yale Song; | |
539 | BooVI: Provably Efficient Bootstrapped Value Iteration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a variant of \underline{boo}tstrapped LS\underline{VI}, namely BooVI, which bridges such a gap between practice and theory. |
Boyi Liu; Qi Cai; Zhuoran Yang; Zhaoran Wang; | |
540 | Do Wider Neural Networks Really Help Adversarial Robustness? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we carefully examine the relationship between network width and model robustness. |
Boxi Wu; Jinghui Chen; Deng Cai; Xiaofei He; Quanquan Gu; | |
541 | Exploring The Limits of Out-of-Distribution Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For multi-modal image-text pre-trained transformers such as CLIP, we explore a new way of using just the names of outlier classes as a sole source of information without any accompanying images, and show that this outperforms previous SOTA on standard OOD benchmark tasks. |
Stanislav Fort; Jie Ren; Balaji Lakshminarayanan; | |
542 | ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a scalable class-imbalanced SSL algorithm that can effectively use unlabeled data, while mitigating class imbalance by introducing an auxiliary balanced classifier (ABC) of a single layer, which is attached to a representation layer of an existing SSL algorithm. |
Hyuck Lee; Seungjae Shin; Heeyoung Kim; | |
543 | BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Bayesian Causal Discovery Nets (BCD Nets), a variational inference framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM. |
Chris Cundy; Aditya Grover; Stefano Ermon; | |
544 | Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Improving upon this, our proposed model learns nodes that dynamically attach to well-delimited salient regions, which are relevant for a higher-level task, without using any object-level supervision. |
Iulia Duta; Andrei Nicolicioiu; Marius Leordeanu; | |
545 | Information-constrained Optimization: Can Adaptive Processing of Gradients Help? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit first-order optimization under local information constraints such as local privacy, gradient quantization, and computational constraints limiting access to a few coordinates of the gradient. |
Jayadev Acharya; Clement Canonne; Prathamesh Mayekar; Himanshu Tyagi; | |
546 | Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The naïve models supervised by such datasets would prefer dominant labels, encounter a serious generalization challenge and become poorly calibrated. We propose two novel methods from the prior perspective to alleviate this dilemma. |
Zhengzhuo Xu; zenghao chai; Chun Yuan; | |
547 | Learning to Draw: Emergent Communication Through Sketching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore a visual communication channel between agents that are allowed to draw with simple strokes. |
Daniela Mihai; Jonathon Hare; | |
548 | Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We focus on the complex task of learning to estimate optical flow from event-based camera inputs in a self-supervised manner, and modify the state-of-the-art ANN training pipeline to encode minimal temporal information in its inputs. |
Jesse Hagenaars; Federico Paredes-Valles; Guido de Croon; | |
549 | On The Value of Infinite Gradients in Variational Autoencoder Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we examine how unbounded gradients relate to the regularization of a broad class of autoencoder-based architectures, including VAE models, as applied to data lying on or near a low-dimensional manifold (e.g., natural images). |
Bin Dai; Li Wenliang; David Wipf; | |
550 | Online Robust Reinforcement Learning with Model Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on model-free robust RL, where the uncertainty set is defined to be centering at a misspecified MDP that generates samples, and is assumed to be unknown. |
Yue Wang; Shaofeng Zou; | |
551 | Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is a learning framework, neural view synthesis and matching, that can transfer the 3D pose annotation from the labelled to unlabelled images reliably, despite unseen 3D views and nuisance variations such as the object shape, texture, illumination or scene context. |
Angtian Wang; Shenxiao Mei; Alan L. Yuille; Adam Kortylewski; | |
552 | Sharp Impossibility Results for Hyper-graph Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a result on standard minimax lower bound theory and a result on Region of Impossibility (which is more informative than the minimax lower bound). |
Jiashun Jin; Tracy Ke; Jiajun Liang; | |
553 | Evaluating Gradient Inversion Attacks and Defenses in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the clients’ private data. This paper evaluates existing attacks and defenses. |
Yangsibo Huang; Samyak Gupta; Zhao Song; Kai Li; Sanjeev Arora; | |
554 | Faster Non-asymptotic Convergence for Double Q-learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a substantial step toward the full understanding of the fast convergence of double-Q learning. |
Lin Zhao; Huaqing Xiong; Yingbin Liang; | |
555 | Towards Tight Communication Lower Bounds for Distributed Optimisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider a standard distributed optimisation setting where $N$ machines, each holding a $d$-dimensional function $f_i$, aim to jointly minimise the sum of the functions $\sum_{i = 1}^N f_i (x)$. |
Janne H. Korhonen; Dan Alistarh; | |
556 | Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel recursive approach, XR-Transformer to accelerate the procedure through recursively fine-tuning transformer models on a series of multi-resolution objectives related to the original XMC objective function. |
Jiong Zhang; Wei-Cheng Chang; Hsiang-Fu Yu; Inderjit Dhillon; | |
557 | HRFormer: High-Resolution Vision Transformer for Dense Predict Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost. |
YUHUI YUAN; Rao Fu; Lang Huang; Weihong Lin; Chao Zhang; Xilin Chen; Jingdong Wang; | code |
558 | Manifold Topology Divergence: A Framework for Comparing Data Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. |
Serguei Barannikov; Ilya Trofimov; Grigorii Sotnikov; Ekaterina Trimbach; Alexander Korotin; Alexander Filippov; Evgeny Burnaev; | |
559 | Weak-shot Fine-grained Classification Via Similarity Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories. |
Junjie Chen; Li Niu; Liu Liu; Liqing Zhang; | |
560 | Shape Your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple and end-to-end trainable deterministic autoencoding framework, that efficiently shapes the latent space of the model during training and utilizes the capacity of expressive multi-modal latent distributions. |
Amrutha Saseendran; Kathrin Skubch; Stefan Falkner; Margret Keuper; | code |
561 | An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present and analyze an algorithm for optimizing smooth and convex or strongly convex objectives using minibatch stochastic gradient estimates. |
Blake E. Woodworth; Nathan Srebro; | |
562 | Indexed Minimum Empirical Divergence for Unimodal Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce IMED-UB, an algorithm that exploits provably optimally the unimodal-structure, by adapting to this setting the Indexed Minimum Empirical Divergence (IMED) algorithm introduced by Honda and Takemura (2015). |
Hassan SABER; Pierre M�nard; Odalric-Ambrym Maillard; | |
563 | SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a transformer-based vision-and-language navigation (VLN) agent that uses two different visual encoders — a scene classification network and an object detector — which produce features that match these two distinct types of visual cues. |
Abhinav Moudgil; Arjun Majumdar; Harsh Agrawal; Stefan Lee; Dhruv Batra; | |
564 | A Normative and Biologically Plausible Algorithm for Independent Component Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a novel objective function for ICA from which we derive a biologically plausible NN, including both the neural architecture and the synaptic learning rules. |
Yanis Bahroun; Dmitri Chklovskii; Anirvan Sengupta; | |
565 | Regret Bounds for Gaussian-Process Optimization in Large Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The goal of this paper is to characterize Gaussian-Process optimization in the setting where the function domain is large relative to the number of admissible function evaluations, i.e., where it is impossible to find the global optimum. |
Manuel Wuethrich; Bernhard Sch�lkopf; Andreas Krause; | |
566 | Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a recursive convolution block design and training method, in which a recursively shareable part, or a filter basis, is separated and learned while effectively avoiding the vanishing/exploding gradients problem during training. |
Woochul Kang; Daeyeon Kim; | |
567 | On Optimal Robustness to Adversarial Corruption in Online Decision Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The main contribution of this paper is to show that optimal robustness can be expressed by a square-root dependency on the amount of corruption. |
Shinji Ito; | |
568 | Directed Spectrum Measures Improve Latent Network Models Of Neural Populations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we develop a novel spectral measure of directed communication called the Directed Spectrum (DS). |
Neil Gallagher; Kafui Dzirasa; David Carlson; | |
569 | Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an uncertainty-based offline RL method that takes into account the confidence of the Q-value prediction and does not require any estimation or sampling of the data distribution. |
Gaon An; Seungyong Moon; Jang-Hyun Kim; Hyun Oh Song; | |
570 | Distribution-free Inference for Regression: Discrete, Continuous, and in Between Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the problem in settings in between these two extremes. We find that there are several distinct regimes in between the finite setting and the continuous setting, where vanishing-width confidence intervals are achievable if and only if the effective support size of the distribution of X is smaller than the square of the sample size. |
Yonghoon Lee; Rina Barber; | |
571 | Statistical Inference with M-Estimators on Adaptively Collected Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop theory justifying the use of M-estimators—which includes estimators based on empirical risk minimization as well as maximum likelihood—on data collected with adaptive algorithms, including (contextual) bandit algorithms. |
Kelly Zhang; Lucas Janson; Susan Murphy; | |
572 | NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving The Traveling Salesman Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem. |
Liang Xin; Wen Song; Zhiguang Cao; Jie Zhang; | |
573 | LSH-SMILE: Locality Sensitive Hashing Accelerated Simulation and Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Locality Sensitive Hashing Accelerated Simulation and Learning (LSH-SMILE), a unified framework to scale up both forward simulation and backward learning of physics systems. |
Chonghao Sima; Yexiang Xue; | |
574 | Meta-learning with An Adaptive Task Scheduler Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To prevent the meta-model from being corrupted by such detrimental tasks or dominated by tasks in the majority, in this paper, we propose an adaptive task scheduler (ATS) for the meta-training process. |
Huaxiu Yao; Yu Wang; Ying Wei; Peilin Zhao; Mehrdad Mahdavi; Defu Lian; Chelsea Finn; | |
575 | Neural Active Learning with Performance Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the problem of active learning in the streaming setting in non-parametric regimes, where the labels are stochastically generated from a class of functions on which we make no assumptions whatsoever. |
Zhilei Wang; Pranjal Awasthi; Christoph Dann; Ayush Sekhari; Claudio Gentile; | |
576 | A Gradient Method for Multilevel Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we have developed a gradient-based algorithm for multilevel optimization with $n$ levels based on their idea and proved that our reformulation asymptotically converges to the original multilevel problem. |
Ryo Sato; Mirai Tanaka; Akiko Takeda; | |
577 | Edge Representation Learning with Hypergraphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel edge representation learning framework based on Dual Hypergraph Transformation (DHT), which transforms the edges of a graph into the nodes of a hypergraph. |
Jaehyeong Jo; Jinheon Baek; Seul Lee; Dongki Kim; Minki Kang; Sung Ju Hwang; | |
578 | One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or knowledge sources. |
Akari Asai; Xinyan Yu; Jungo Kasai; Hanna Hajishirzi; | |
579 | LEADS: Learning Dynamical Systems That Generalize Across Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose LEADS, a novel framework that leverages the commonalities and discrepancies among known environments to improve model generalization. |
Yuan Yin; Ibrahim Ayed; Emmanuel de B�zenac; Nicolas Baskiotis; Patrick Gallinari; | |
580 | Storchastic: A Framework for General Stochastic Automatic Differentiation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we introduce Storchastic, a new framework for AD of stochastic computation graphs. |
Emile Krieken; Jakub Tomczak; Annette Ten Teije; | |
581 | Concentration Inequalities Under Sub-Gaussian and Sub-exponential Conditions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove analogues of the popular bounded difference inequality (also called McDiarmid’s inequality) for functions of independent random variables under sub-gaussian and sub-exponential conditions. |
Andreas Maurer; Massimiliano Pontil; | |
582 | Variance-Aware Off-Policy Evaluation with Linear Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: More specifically, for time-inhomogeneous episodic linear Markov decision processes (MDPs), we propose an algorithm, \texttt{VA-OPE}, which uses the estimated variance of the value function to reweight the Bellman residual in Fitted Q-Iteration. |
Yifei Min; Tianhao Wang; Dongruo Zhou; Quanquan Gu; | |
583 | A Provably Efficient Sample Collection Strategy for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to tackle the exploration-exploitation problem following a decoupled approach composed of: 1) An "objective-specific" algorithm that (adaptively) prescribes how many samples to collect at which states, as if it has access to a generative model (i.e., a simulator of the environment); 2) An "objective-agnostic" sample collection exploration strategy responsible for generating the prescribed samples as fast as possible. |
Jean Tarbouriech; Matteo Pirotta; Michal Valko; Alessandro Lazaric; | |
584 | Improved Regret Bounds for Tracking Experts with Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the problem of sequential prediction with expert advice in a non-stationary environment with long-term memory guarantees in the sense of Bousquet and Warmuth [4]. |
James Robinson; Mark Herbster; | |
585 | Robustness of Graph Neural Networks at Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two sparsity-aware first-order optimization attacks that maintain an efficient representation despite optimizing over a number of parameters which is quadratic in the number of nodes. |
Simon Geisler; Tobias Schmidt; Hakan Sirin; Daniel Z�gner; Aleksandar Bojchevski; Stephan G�nnemann; | |
586 | Random Noise Defense Against Query-Based Black-Box Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study a lightweight defense method, dubbed Random Noise Defense (RND), which adds proper Gaussian noise to each query. |
Zeyu Qin; Yanbo Fan; Hongyuan Zha; Baoyuan Wu; | |
587 | SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Focusing on the above two key issues, we propose a \emph{Structure-Aware Dual Graph Aggregation Network} (SADGA) for cross-domain Text-to-SQL. |
Ruichu Cai; Jinjie Yuan; Boyan Xu; Zhifeng Hao; | |
588 | Near-Optimal Offline Reinforcement Learning Via Double Variance Reduction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose \emph{Off-Policy Double Variance Reduction} (OPDVR), a new variance reduction-based algorithm for offline RL. |
Ming Yin; Yu Bai; Yu-Xiang Wang; | |
589 | Joint Modeling of Visual Objects and Relations for Scene Graph Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a principled approach to jointly predict the entire scene graph by fully capturing the dependency between different objects and between their relations. |
Minghao Xu; Meng Qu; Bingbing Ni; Jian Tang; | |
590 | Going Beyond Linear Transformers with Recurrent Fast Weight Programmers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In existing linear Transformers, both NNs are feedforward and consist of a single layer. Here we explore new variations by adding recurrence to the slow and fast nets. |
Kazuki Irie; Imanol Schlag; R�bert Csord�s; J�rgen Schmidhuber; | |
591 | Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we present a Bayesian variant of DQN with the following three features: (i) It learns a distribution of Q-networks as AFs based on the Kullback-Leibler regularization framework. |
Bing-Jing Hsieh; Ping-Chun Hsieh; Xi Liu; | |
592 | Forster Decomposition and Learning Halfspaces with Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As the main application of this result, we obtain the first polynomial-time algorithm for distribution-independent PAC learning of halfspaces in the Massart noise model with strongly polynomial sample complexity, i.e., independent of the bit complexity of the examples. |
Ilias Diakonikolas; Daniel Kane; Christos Tzamos; | |
593 | Cortico-cerebellar Networks As Decoupling Neural Interfaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose that a specialised brain region, the cerebellum, helps the cerebral cortex solve similar locking problems akin to DNIs. |
Joseph Pemberton; Ellen Boven; Richard Apps; Rui Ponte Costa; | |
594 | To The Point: Correspondence-driven Monocular 3D Category Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences given only foreground masks, a category specific template and optionally sparse keypoints for supervision. |
Filippos Kokkinos; Iasonas Kokkinos; | |
595 | Proper Value Equivalence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A fundamental question underlying the VE principle is thus how to select the smallest sets of policies and functions that are sufficient for planning. In this paper we take an important step towards answering this question. |
Christopher Grimm; Andre Barreto; Greg Farquhar; David Silver; Satinder Singh; | |
596 | Challenges and Opportunities in High Dimensional Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a conceptual framework and set of experimental tools to understand the effects of these choices, which we leverage to propose best practices for maximizing posterior approximation accuracy. |
Akash Kumar Dhaka; Alejandro Catalina; Manushi Welandawe; Michael R. Andersen; Jonathan Huggins; Aki Vehtari; | |
597 | On The Expressivity of Markov Reward Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. |
David Abel; Will Dabney; Anna Harutyunyan; Mark K. Ho; Michael Littman; Doina Precup; Satinder Singh; | |
598 | One More Step Towards Reality: Cooperative Bandits with Imperfect Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study cooperative bandit learning under three typical real-world communication scenarios, namely, (a) message-passing over stochastic time-varying networks, (b) instantaneous reward-sharing over a network with random delays, and (c) message-passing with adversarially corrupted rewards, including byzantine communication. |
Udari Madhushani; Abhimanyu Dubey; Naomi Leonard; Alex Pentland; | |
599 | Multi-Agent Reinforcement Learning in Stochastic Networked Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Scalable Actor Critic framework that applies in settings where the dependencies can be non-local and stochastic, and provide a finite-time error bound that shows how the convergence rate depends on the speed of information spread in the network. |
Yiheng Lin; Guannan Qu; Longbo Huang; Adam Wierman; | |
600 | Neural Scene Flow Prior Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper revisits the scene flow problem that relies predominantly on runtime optimization and strong regularization. |
Xueqian Li; Jhony Kaesemodel Pontes; Simon Lucey; | |
601 | The Future Is Log-Gaussian: ResNets and Their Infinite-depth-and-width Limit at Initialization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on our analysis, we introduce \emph{Balanced ResNets}, a simple architecture modification, which eliminates hypoactivation and interlayer correlations and is more amenable to theoretical analysis. |
Mufan Li; Mihai Nica; Dan Roy; | |
602 | Grammar-Based Grounded Lexicon Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Grammar-Based Grounded Language Learning (G2L2), a lexicalist approach toward learning a compositional and grounded meaning representation of language from grounded data, such as paired images and texts. |
Jiayuan Mao; Haoyue Shi; Jiajun Wu; Roger Levy; Josh Tenenbaum; | |
603 | Distributed Deep Learning In Open Collaborations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we carefully analyze these constraints and propose a novel algorithmic framework designed specifically for collaborative training. |
Michael Diskin; Alexey Bukhtiyarov; Max Ryabinin; Lucile Saulnier; quentin lhoest; Anton Sinitsin; Dmitry Popov; Dmitry Pyrkin; Maxim Kashirin; Alexander Borzunov; Albert Villanova del Moral; Denis Mazur; Ilia Kobelev; Yacine Jernite; Thomas Wolf; Gennady Pekhimenko; | |
604 | Neural Ensemble Search for Uncertainty Estimation and Dataset Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we propose two methods for automatically constructing ensembles with varying architectures, which implicitly trade-off individual architectures’ strengths against the ensemble’s diversity and exploit architectural variation as a source of diversity. |
Sheheryar Zaidi; Arber Zela; Thomas Elsken; Chris C. Holmes; Frank Hutter; Yee Teh; | code |
605 | Finding Bipartite Components in Hypergraphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study a new heat diffusion process in hypergraphs, and employ this process to design a polynomial-time algorithm that approximately finds bipartite components in a hypergraph. |
Peter Macgregor; He Sun; | |
606 | Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these challenges, we propose a novel RL framework that generates pharmacochemically acceptable molecules with large docking scores. |
Soojung Yang; Doyeong Hwang; Seul Lee; Seongok Ryu; Sung Ju Hwang; | |
607 | Proxy Convexity: A Unified Framework for The Analysis of Neural Networks Trained By Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this drawback in the literature, we propose a unified non-convex optimization framework for the analysis of neural network training. |
Spencer Frei; Quanquan Gu; | |
608 | Covariance-Aware Private Mean Estimation Without Private Covariance Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two sample-efficient differentially private mean estimators for $d$-dimensional (sub)Gaussian distributions with unknown covariance. |
Gavin Brown; Marco Gaboardi; Adam Smith; Jonathan Ullman; Lydia Zakynthinou; | |
609 | Label Consistency in Overfitted Generalized $k$-means Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide theoretical guarantees for label consistency in generalized $k$-means problems, with an emphasis on the overfitted case where the number of clusters used by the algorithm is more than the ground truth. |
Linfan Zhang; Arash Amini; | |
610 | Open-set Label Noise Can Improve Robustness Against Inherent Label Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we empirically show that open-set noisy labels can be non-toxic and even benefit the robustness against inherent noisy labels. |
Hongxin Wei; Lue Tao; RENCHUNZI XIE; Bo An; | |
611 | The Complexity of Sparse Tensor PCA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For the highly sparse regime of $k \leq \sqrt{n}$, we present a family of algorithms that smoothly interpolates between a simple polynomial-time algorithm and the exponential-time exhaustive search algorithm. |
Davin Choo; Tommaso d'Orsi; | |
612 | Learning to Elect Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that set-input neural network architectures such as Set Transformers, fully-connected graph networks and DeepSets are both theoretically and empirically well-suited for learning voting rules. |
Cem Anil; Xuchan Bao; | |
613 | KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a particle implementation of the flow given initial samples from the source and the target distribution, which we use to empirically confirm the KALE’s properties. |
Pierre Glaser; Michael Arbel; Arthur Gretton; | |
614 | When Is Generalizable Reinforcement Learning Tractable? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To capture this, we introduce Weak Proximity, a natural structural condition that requires the environments to have highly similar transition and reward functions and share a policy providing optimal value. |
Dhruv Malik; Yuanzhi Li; Pradeep Ravikumar; | |
615 | Relational Self-Attention: What's Missing in Attention for Video Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a relational feature transform, dubbed the relational self-attention (RSA), that leverages rich structures of spatio-temporal relations in videos by dynamically generating relational kernels and aggregating relational contexts. |
Manjin Kim; Heeseung Kwon; CHUNYU WANG; Suha Kwak; Minsu Cho; | |
616 | Towards Enabling Meta-Learning from Target Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper looks into this special evaluation method and takes a step towards putting it into practice. |
Su Lu; Han-Jia Ye; Le Gan; De-Chuan Zhan; | |
617 | A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs), which we prove to be near-optimal by bounding its excess Bayes risk. |
Ibrahim M. Alabdulmohsin; Mario Lucic; | |
618 | GENESIS-V2: Inferring Unordered Object Representations Without Iterative Refinement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to established paradigms, this work proposes an embedding-based approach in which embeddings of pixels are clustered in a differentiable fashion using a stochastic stick-breaking process. |
Martin Engelcke; Oiwi Parker Jones; Ingmar Posner; | |
619 | How Data Augmentation Affects Optimization for Linear Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the spirit of classical convex optimization and recent work on implicit bias, the present work analyzes the effect of augmentation on optimization in the simple convex setting of linear regression with MSE loss. |
Boris Hanin; Yi Sun; | |
620 | An Exact Characterization of The Generalization Error for The Gibbs Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is an exact characterization of the expected generalization error of the well-known Gibbs algorithm (a.k.a. Gibbs posterior) using symmetrized KL information between the input training samples and the output hypothesis. |
Gholamali Aminian; Yuheng Bu; Laura Toni; Miguel Rodrigues; Gregory Wornell; | |
621 | Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the theoretical properties of the IS estimator by deriving a novel anticoncentration bound that formalizes the intuition behind its undesired behavior. |
Alberto Maria Metelli; Alessio Russo; Marcello Restelli; | |
622 | Rethinking Gradient Sparsification As Total Error Minimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that to further the benefits of gradient sparsification, especially for DNNs, a different perspective is necessary – one that moves from per-iteration optimality to consider optimality for the entire training. |
Atal Sahu; Aritra Dutta; Ahmed M. Abdelmoniem; Trambak Banerjee; Marco Canini; Panos Kalnis; | |
623 | Approximate Optimization of Convex Functions with Outlier Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of minimizing a convex function given by a zeroth order oracle that is possibly corrupted by {\em outlier noise}. |
Anindya De; Sanjeev Khanna; Huan Li; MohammadHesam NikpeySalekde; | |
624 | Fair Classification with Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is an optimization framework to learn fair classifiers in this adversarial setting that comes with provable guarantees on accuracy and fairness. |
L. Elisa Celis; Anay Mehrotra; Nisheeth Vishnoi; | |
625 | Distributed Saddle-Point Problems Under Data Similarity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study solution methods for (strongly-)convex-(strongly)-concave Saddle-Point Problems (SPPs) over networks of two type–master/workers (thus centralized) architectures and mesh (thus decentralized) networks. |
Aleksandr Beznosikov; Gesualdo Scutari; Alexander Rogozin; Alexander Gasnikov; | |
626 | Combining Latent Space and Structured Kernels for Bayesian Optimization Over Combinatorial Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this drawback, this paper proposes a principled approach referred as LADDER. |
Aryan Deshwal; Jana Doppa; | |
627 | Gradual Domain Adaptation Without Indexed Intermediate Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Concretely, we propose a coarse-to-fine framework, which starts with a coarse domain discovery step via progressive domain discriminator training. |
Hong-You Chen; Wei-Lun Chao; | code |
628 | K-level Reasoning for Zero-Shot Coordination in Hanabi Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we show that through a simple adaption of k-level reasoning (KLR) \cite{Costa-Gomes2006-K-level}, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. |
Brandon Cui; Hengyuan Hu; Luis Pineda; Jakob Foerster; | |
629 | Learning Markov State Abstractions for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel set of conditions and prove that they are sufficient for learning a Markov abstract state representation. |
Cameron Allen; Neev Parikh; Omer Gottesman; George Konidaris; | |
630 | Towards Deeper Deep Reinforcement Learning with Spectral Normalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern networks with skip connections and normalization, focusing specifically on actor-critic algorithms. |
Nils Bjorck; Carla P. Gomes; Kilian Q. Weinberger; | |
631 | Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To accommodate these wildly different assays and capture the similarity between assays, we propose a functional rationalized meta-learning algorithm FRML for such knowledge transfer. |
Huaxiu Yao; Ying Wei; Long-Kai Huang; Ding Xue; Junzhou Huang; Zhenhui (Jessie) Li; | |
632 | Memory-Efficient Approximation Algorithms for Max-k-Cut and Correlation Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop simple polynomial-time Gaussian sampling-based algorithms for these two problems that use $\mathcal{O}(n+|E|)$ memory and nearly achieve the best existing approximation guarantees. |
Nimita Shinde; Vishnu Narayanan; James Saunderson; | |
633 | Panoptic 3D Scene Reconstruction From A Single RGB Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new approach for holistic 3D scene understanding from a single RGB image which learns to lift and propagate 2D features from an input image to a 3D volumetric scene representation. |
Manuel Dahnert; Ji Hou; Matthias Niessner; Angela Dai; | |
634 | Measuring Generalization with Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop margin-based generalization bounds, where the margins are normalized with optimal transport costs between independent random subsets sampled from the training distribution. |
Ching-Yao Chuang; Youssef Mroueh; Kristjan Greenewald; Antonio Torralba; Stefanie Jegelka; | |
635 | Uniform Concentration Bounds Toward A Unified Framework for Robust Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Toward addressing these issues in a principled way, this paper proposes a cohesive robust framework for center-based clustering under a general class of dissimilarity measures. |
Debolina Paul; Saptarshi Chakraborty; Swagatam Das; Jason Xu; | |
636 | Learning Signal-Agnostic Implicit Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By enforcing coverage of the manifold, local linearity, and local isometry, our model — dubbed GEM — learns to capture the underlying structure of datasets across modalities. |
Yilun Du; Katherine Collins; Josh Tenenbaum; Vincent Sitzmann; | |
637 | Low-dimensional Structure in The Space of Language Representations Is Reflected in Brain Responses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: How related are the representations learned by neural language models, translation models, and language tagging tasks? We answer this question by adapting an encoder-decoder transfer learning method from computer vision to investigate the structure among 100 different feature spaces extracted from hidden representations of various networks trained on language tasks. |
Richard Antonello; Javier S. Turek; Vy Vo; Alexander Huth; | |
638 | On The Suboptimality of Thompson Sampling in High Dimensions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we consider Thompson Sampling for combinatorial semi-bandits. |
Raymond Zhang; Richard Combes; | |
639 | Learning Debiased and Disentangled Representations for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a model-agnostic and stochastic training scheme for semantic segmentation, which facilitates the learning of debiased and disentangled representations. |
Sanghyeok Chu; Dongwan Kim; Bohyung Han; | |
640 | Diversity Matters When Learning From Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple approach for reducing this gap, i.e., making the distilled performance close to the full ensemble. |
Giung Nam; Jongmin Yoon; Yoonho Lee; Juho Lee; | |
641 | Locally Valid and Discriminative Prediction Intervals for Deep Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building upon recent advances in conformal prediction [13, 33] and leveraging the classical idea of kernel regression, we propose Locally Valid and Discriminative prediction intervals (LVD), a simple, efficient, and lightweight method to construct discriminative prediction intervals (PIs) for almost any DL model. |
Zhen Lin; Shubhendu Trivedi; Jimeng Sun; | |
642 | Personalized Federated Learning With Gaussian Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we present pFedGP, a solution to PFL that is based on Gaussian processes (GPs) with deep kernel learning. |
Idan Achituve; Aviv Shamsian; Aviv Navon; Gal Chechik; Ethan Fetaya; | |
643 | Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study this "benign overfitting" phenomenon of the maximum margin classifier for linear classification problems. |
Yuan Cao; Quanquan Gu; Mikhail Belkin; | |
644 | Implicit SVD for Graph Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we make GRL more computationally tractable for those with modest hardware. |
Sami Abu-El-Haija; Hesham Mostafa; Marcel Nassar; Valentino Crespi; Greg Ver Steeg; Aram Galstyan; | code |
645 | Offline Model-based Adaptable Policy Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to release the potential of offline policy learning, we investigate the decision-making problems in out-of-support regions directly and propose offline Model-based Adaptable Policy LEarning (MAPLE). |
Xiong-Hui Chen; Yang Yu; Qingyang Li; Fan-Ming Luo; Zhiwei Qin; Wenjie Shang; Jieping Ye; | |
646 | Multilingual Pre-training with Universal Dependency Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus we propose a novel multilingual PrLM that supports both explicit universal dependency parsing and implicit language modeling. |
Kailai Sun; Zuchao Li; Hai Zhao; | |
647 | Parameter-free HE-friendly Logistic Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose an effective privacy-preserving logistic regression method that is free from the approximation of the sigmoid function and hyperparameter selection. |
Junyoung Byun; WOOJIN LEE; Jaewook Lee; | |
648 | Active Clustering for Labeling Training Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus motivated, we propose a setting for training data gathering where the human experts perform the comparatively cheap task of answering pairwise queries, and the computer groups the items into classes (which can be labeled cheaply at the very end of the process). |
Quentin Lutz; Elie De Panafieu; Maya Stein; Alex Scott; | |
649 | Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we argue that one of the typical formulations of VAEs in multi-agent modeling suffers from an issue we refer to as social posterior collapse, i.e., the model is prone to ignoring historical social context when predicting the future trajectory of an agent. |
Chen Tang; Wei Zhan; Masayoshi Tomizuka; | |
650 | Ensembling Graph Predictions for AMR Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we formalize this problem as mining the largest graph that is the most supported by a collection of graph predictions. |
Thanh Lam Hoang; Gabriele Picco; Yufang Hou; Young-Suk Lee; Lam Nguyen; Dzung Phan; Vanessa Lopez; Ramon Fernandez Astudillo; | |
651 | On The Interplay Between Data Structure and Loss Function in Classification Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider an analytically solvable setup to investigate how properties of data impact learning in classification problems, and compare the results obtained for quadratic loss and logistic loss. |
St�phane d'Ascoli; Marylou Gabri�; Levent Sagun; Giulio Biroli; | |
652 | Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we improve existing results for learning nonlinear systems in a number of ways: a) we provide the first offline algorithm that can learn non-linear dynamical systems without the mixing assumption, b) we significantly improve upon the sample complexity of existing results for mixing systems, c) in the much harder one-pass, streaming setting we study a SGD with Reverse Experience Replay (SGD-RER) method, and demonstrate that for mixing systems, it achieves the same sample complexity as our offline algorithm, d) we justify the expansivity assumption by showing that for the popular ReLU link function — a non-expansive but easy to learn link function with i.i.d. samples — any method would require exponentially many samples (with respect to dimension of $X_t$) from the dynamical system. |
Suhas Kowshik; Dheeraj Nagaraj; Prateek Jain; Praneeth Netrapalli; | |
653 | Mixture Proportion Estimation and PU Learning:A Modern Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose two simple techniques: Best Bin Estimation (BBE) (for MPE); and Conditional Value Ignoring Risk (CVIR), a simple objective for PU-learning. |
Saurabh Garg; Yifan Wu; Alexander J. Smola; Sivaraman Balakrishnan; Zachary Lipton; | |
654 | Escape Saddle Points By A Simple Gradient-descent Based Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple gradient-based algorithm such that for a smooth function $f\colon\mathbb{R}^n\to\mathbb{R}$, it outputs an $\epsilon$-approximate second-order stationary point in $\tilde{O}(\log n/\epsilon^{1.75})$ iterations. |
Chenyi Zhang; Tongyang Li; | |
655 | AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a general approach called Alternating Compressed/DeCompressed (AC/DC) training of DNNs, demonstrate convergence for a variant of the algorithm, and show that AC/DC outperforms existing sparse training methods in accuracy at similar computational budgets; at high sparsity levels, AC/DC even outperforms existing methods that rely on accurate pre-trained dense models. |
Alexandra Peste; Eugenia Iofinova; Adrian Vladu; Dan Alistarh; | |
656 | HyperSPNs: Compact and Expressive Probabilistic Circuits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose HyperSPNs: a new paradigm of generating the mixture weights of large PCs using a small-scale neural network. |
Andy Shih; Dorsa Sadigh; Stefano Ermon; | |
657 | Scaling Vision with Sparse Mixture of Experts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a Vision MoE (V-MoE), a sparse version of the Vision Transformer, that is scalable and competitive with the largest dense networks. |
Carlos Riquelme; Joan Puigcerver; Basil Mustafa; Maxim Neumann; Rodolphe Jenatton; Andr� Susano Pinto; Daniel Keysers; Neil Houlsby; | |
658 | Two-sided Fairness in Rankings Via Lorenz Dominance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to generate rankings by maximizing concave welfare functions, and develop an efficient inference procedure based on the Frank-Wolfe algorithm. |
Virginie Do; Sam Corbett-Davies; Jamal Atif; Nicolas Usunier; | |
659 | Stability & Generalisation of Gradient Descent for Shallow Neural Networks Without The Neural Tangent Kernel Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit on-average algorithmic stability of Gradient Descent (GD) for training overparameterised shallow neural networks and prove new generalisation and excess risk bounds without the Neural Tangent Kernel (NTK) or Polyak-?ojasiewicz (PL) assumptions. |
Dominic Richards; Ilja Kuzborskij; | |
660 | Adversarial Intrinsic Motivation for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate whether one such objective, the Wasserstein-1 distance between a policy’s state visitation distribution and a target distribution, can be utilized effectively for reinforcement learning (RL) tasks. |
Ishan Durugkar; Mauricio Tec; Scott Niekum; Peter Stone; | |
661 | Machine Learning for Variance Reduction in Online Experiments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a machine learning regression-adjusted treatment effect estimator, which we call MLRATE. |
Yongyi Guo; Dominic Coey; Mikael Konutgan; Wenting Li; Chris Schoener; Matt Goldman; | |
662 | L2ight: Enabling On-Chip Learning for Optical Neural Networks Via Efficient In-situ Subspace Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a closed-loop ONN on-chip learning framework L2ight to enable scalable ONN mapping and efficient in-situ learning. |
Jiaqi Gu; Hanqing Zhu; Chenghao Feng; Zixuan Jiang; Ray Chen; David Pan; | |
663 | Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new algorithmic framework, named Initialization Auxiliary and Pessimistic Trajectory Truncated Gradient Method (IAPTT-GM), to partially address the above issues. |
Risheng Liu; Yaohua Liu; Shangzhi Zeng; Jin Zhang; | |
664 | Multi-Facet Clustering Variational Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Multi-Facet Clustering Variational Autoencoders (MFCVAE), a novel class of variational autoencoders with a hierarchy of latent variables, each with a Mixture-of-Gaussians prior, that learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end. |
Fabian Falck; Haoting Zhang; Matthew Willetts; George Nicholson; Christopher Yau; Chris C. Holmes; | |
665 | Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose several methods for choosing the set of treated units in conjunction with the weights. |
Nick Doudchenko; Khashayar Khosravi; Jean Pouget-Abadie; S�bastien Lahaie; Miles Lubin; Vahab Mirrokni; Jann Spiess; guido imbens; | |
666 | Ranking Policy Decisions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given a trained policy, we propose a novel black-box method based on statistical fault localisation that ranks the states of the environment according to the importance of decisions made in those states. |
Hadrien Pouget; Hana Chockler; Youcheng Sun; Daniel Kroening; | |
667 | Searching The Search Space of Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to use neural architecture search to automate this process, by searching not only the architecture but also the search space. |
Minghao Chen; Kan Wu; Bolin Ni; Houwen Peng; Bei Liu; Jianlong Fu; Hongyang Chao; Haibin Ling; | code |
668 | Relative Stability Toward Diffeomorphisms Indicates Performance in Deep Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit this question by defining a maximum-entropy distribution on diffeomorphisms, that allows to study typical diffeomorphisms of a given norm. |
Leonardo Petrini; Alessandro Favero; Mario Geiger; Matthieu Wyart; | |
669 | Raw Nav-merge Seismic Data to Subsurface Properties with MLP Based Multi-Modal Information Unscrambler Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we go beyond convolution and propose a novel SI method. |
Aditya Desai; Zhaozhuo Xu; Menal Gupta; Anu Chandran; Antoine Vial-Aussavy; Anshumali Shrivastava; | |
670 | Inverse Problems Leveraging Pre-trained Contrastive Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a supervised inversion method that uses a contrastive objective to obtain excellent representations for highly corrupted images. |
Sriram Ravula; Georgios Smyrnis; Matt Jordan; Alexandros G. Dimakis; | |
671 | The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this issue, we introduce two Unbalanced Gromov-Wasserstein formulations: a distance and a more tractable upper-bounding relaxation. |
Thibault Sejourne; Francois-Xavier Vialard; Gabriel Peyr�; | |
672 | Diffusion Models Beat GANs on Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. |
Prafulla Dhariwal; Alexander Nichol; | |
673 | Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making By Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the predict-then-optimize framework in the context of sequential decision problems (formulated as MDPs) that are solved via reinforcement learning. |
Kai Wang; Sanket Shah; Haipeng Chen; Andrew Perrault; Finale Doshi-Velez; Milind Tambe; | |
674 | A Closer Look at The Worst-case Behavior of Multi-armed Bandit Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides new results on the arm-sampling behavior of UCB, leading to several important insights. |
Anand Kalvit; Assaf Zeevi; | |
675 | SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Spatially Adaptive Progressive Encoding (SAPE) layers, which gradually unmask signal components with increasing frequencies as a function of time and space. |
Amir Hertz; Or Perel; Raja Giryes; Olga Sorkine-hornung; Daniel Cohen-or; | |
676 | A Biased Graph Neural Network Sampler with Near-Optimal Regret Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we build upon existing work and treat GNN neighbor sampling as a multi-armed bandit problem but with a newly-designed reward function that introduces some degree of bias designed to reduce variance and avoid unstable, possibly-unbounded pay outs. |
Qingru Zhang; David Wipf; Quan Gan; Le Song; | |
677 | Equilibrium Refinement for The Age of Machines: The One-Sided Quasi-Perfect Equilibrium Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we initiate the study of equilibrium refinements for settings where one of the players is perfectly rational (the “machine”) and the other may make mistakes. |
Gabriele Farina; Tuomas Sandholm; | |
678 | Interpreting Representation Quality of DNNs for 3D Point Cloud Processing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. |
Wen Shen; Qihan Ren; Dongrui Liu; Quanshi Zhang; | |
679 | How Fine-Tuning Allows for Effective Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a theoretical framework for analyzing a MAML-like algorithm, assuming all available tasks require approximately the same representation. |
Kurtland Chua; Qi Lei; Jason D. Lee; | |
680 | Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We resolve this issue by proposing a novel two-stage learning algorithm, called $\texttt{CO-LCB}$ algorithm, whose regret is a function of aggregate action frequency of agents containing the $\textit{optimal}$ arm. |
lin yang; Yu-Zhen Janice Chen; Stephen Pasteris; Mohammad Hajiesmaili; John C. S. Lui; Don Towsley; | |
681 | Multiple Descent: Design Your Own Generalization Curve Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper explores the generalization loss of linear regression in variably parameterized families of models, both under-parameterized and over-parameterized. |
Lin Chen; Yifei Min; Mikhail Belkin; Amin Karbasi; | |
682 | On Empirical Risk Minimization with Dependent and Heavy-Tailed Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we establish risk bounds for Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. |
Abhishek Roy; Krishnakumar Balasubramanian; Murat A. Erdogdu; | |
683 | Gone Fishing: Neural Active Learning with Fisher Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper motivates and revisits a classic, Fisher-based active selection objective, and proposes BAIT, a practical, tractable, and high-performing algorithm that makes it viable for use with neural models. |
Jordan Ash; Surbhi Goel; Akshay Krishnamurthy; Sham Kakade; | |
684 | On Riemannian Optimization Over Positive Definite Matrices with The Bures-Wasserstein Geometry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we comparatively analyze the Bures-Wasserstein (BW) geometry with the popular Affine-Invariant (AI) geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold. |
Andi Han; Bamdev Mishra; Pratik Kumar Jawanpuria; Junbin Gao; | |
685 | Refining Language Models with Compositional Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to refine a learned language model for a target domain by collecting human-provided compositional explanations regarding observed biases. |
Huihan Yao; Ying Chen; Qinyuan Ye; Xisen Jin; Xiang Ren; | |
686 | Going Beyond Linear RL: Sample Efficient Neural Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This is the focus of this work, where we study function approximation with two-layer neural networks (considering both ReLU and polynomial activation functions). |
Baihe Huang; Kaixuan Huang; Sham Kakade; Jason D. Lee; Qi Lei; Runzhe Wang; Jiaqi Yang; | |
687 | Scalable Neural Data Server: A Data Recommender for Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose Scalable Neural Data Server (SNDS), a large-scale search engine that can theoretically index thousands of datasets to serve relevant ML data to end users. |
Tianshi Cao; Sasha (Alexandre) Doubov; David Acuna; Sanja Fidler; | |
688 | What Can Linearized Neural Networks Actually Say About Generalization? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our work, we provide strong empirical evidence to determine the practical validity of such approximation by conducting a systematic comparison of the behavior of different neural networks and their linear approximations on different tasks. |
Guillermo Ortiz-Jimenez; Seyed-Mohsen Moosavi-Dezfooli; Pascal Frossard; | |
689 | CATs: Cost Aggregation Transformers for Visual Correspondence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric variations. |
Seokju Cho; Sunghwan Hong; Sangryul Jeon; Yunsung Lee; Kwanghoon Sohn; Seungryong Kim; | code |
690 | Asynchronous Stochastic Optimization Robust to Arbitrary Delays Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of stochastic optimization with delayed gradients in which, at each time step $t$, the algorithm makes an update using a stale stochastic gradient from step $t – d_t$ for some arbitrary delay $d_t$. |
Alon Cohen; Amit Daniely; Yoel Drori; Tomer Koren; Mariano Schain; | |
691 | Consistent Non-Parametric Methods for Maximizing Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this limitation by proposing a new limit classifier, called the neighborhood optimal classifier, that extends the Bayes optimal classifier outside its support by using the label of the closest in-support point. |
Robi Bhattacharjee; Kamalika Chaudhuri; | |
692 | Generalizable Multi-linear Attention Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this concern, we propose a new method called generalizable multi-linear attention network (MAN), which can associate as many modalities as possible in linear complexity with hierarchical approximation decomposition (HAD). |
Tao Jin; Zhou Zhao; | |
693 | Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of more than one node). |
Muhan Zhang; Pan Li; Yinglong Xia; Kai Wang; Long Jin; | |
694 | SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we propose a faster and universal framework of adaptive gradients(\emph{i.e.}, SUPER-ADAM) by introducing a universal adaptive matrix that includes most existing adaptive gradient forms. |
Feihu Huang; Junyi Li; Heng Huang; | code |
695 | General Nonlinearities in SO(2)-Equivariant CNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a novel FFT-based algorithm for computing representations of non-linearly transformed activations while maintaining band-limitation. |
Daniel Franzen; Michael Wand; | |
696 | Denoising Normalizing Flow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose a novel method – called Denoising Normalizing Flow (DNF) – that estimates the density on the low-dimensional manifold while learning the manifold as well. |
Christian Horvat; Jean-Pascal Pfister; | |
697 | Attention Over Learned Object Embeddings Enables Complex Visual Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a more general neural-network-based approach to dynamic visual reasoning problems that obtains state-of-the-art performance on three different domains, in each case outperforming bespoke modular approaches tailored specifically to the task. |
David Ding; Felix Hill; Adam Santoro; Malcolm Reynolds; Matt Botvinick; | |
698 | Differentially Private Federated Bayesian Optimization with Distributed Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following this general DP framework, our work here integrates DP into FTS to preserve user-level privacy. |
Zhongxiang Dai; Bryan Kian Hsiang Low; Patrick Jaillet; | |
699 | Differentiable Learning Under Triage Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we start by formally characterizing under which circumstances a predictive model may benefit from algorithmic triage. |
Nastaran Okati; Abir De; Manuel Rodriguez; | |
700 | A New Theoretical Framework for Fast and Accurate Online Decision-Making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. |
Nicol� Cesa-Bianchi; Tom Cesari; Yishay Mansour; Vianney Perchet; | |
701 | When Expressivity Meets Trainability: Fewer Than $n$ Neurons Can Work Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide partially affirmative answers to both questions for 1-hidden-layer networks with fewer than $n$ (sample size) neurons. |
Jiawei Zhang; Yushun Zhang; Mingyi Hong; Ruoyu Sun; Zhi-Quan Luo; | |
702 | Analyzing The Confidentiality of Undistillable Teachers in Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that transferring knowledge to a shallow sub-section of a student can largely reduce a teacher’s influence. |
Souvik Kundu; Qirui Sun; Yao Fu; Massoud Pedram; Peter Beerel; | code |
703 | High Probability Complexity Bounds for Line Search Based on Stochastic Oracles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider a line-search method for continuous optimization under a stochastic setting where the function values and gradients are available only through inexact probabilistic zeroth and first-order oracles. |
Billy Jin; Katya Scheinberg; Miaolan Xie; | |
704 | Pay Attention to MLPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose a simple network architecture, gMLP, based solely on MLPs with gating, and show that it can perform as well as Transformers in key language and vision applications. |
Hanxiao Liu; Zihang Dai; David So; Quoc Le; | |
705 | An Image Is Worth More Than A Thousand Words: Towards Disentanglement in The Wild Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a method for disentangling a set of factors which are only partially labeled, as well as separating the complementary set of residual factors that are never explicitly specified. |
Aviv Gabbay; Niv Cohen; Yedid Hoshen; | |
706 | Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By introducing hyperparameters that depend on the number of samples, we propose a new algorithm sDANA (stochastic dimension adjusted Nesterov acceleration) which obtains an asymptotically optimal average-case complexity while remaining linearly convergent in the strongly convex setting without adjusting parameters. |
Courtney Paquette; Elliot Paquette; | |
707 | Adversarial Examples in Multi-Layer Random ReLU Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the phenomenon of adversarial examples in ReLU networks with independent Gaussian parameters. |
Peter Bartlett; Sebastien Bubeck; Yeshwanth Cherapanamjeri; | |
708 | Efficient Statistical Assessment of Neural Network Corruption Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We quantify the robustness of a trained network to input uncertainties with a stochastic simulation inspired by the field of Statistical Reliability Engineering. |
Karim TIT; Teddy Furon; Mathias ROUSSET; | |
709 | A Highly-Efficient Group Elastic Net Algorithm with An Application to Function-On-Scalar Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Straddling these two areas, we propose a new highly efficient algorithm to perform Group Elastic Net with application to function-on-scalar feature selection, where a functional response is modeled against a very large number of potential scalar predictors. |
Tobia Boschi; Matthew Reimherr; Francesca Chiaromonte; | |
710 | Hierarchical Clustering: $O(1)$-Approximation for Well-Clustered Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study the cost function for hierarchical clustering introduced by Dasgupta, and present two polynomial-time approximation algorithms: Our first result is an $O(1)$-approximation algorithm for graphs of high conductance. |
Bogdan-Adrian Manghiuc; He Sun; | |
711 | Realistic Evaluation of Transductive Few-shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce and study the effect of arbitrary class distributions within the query sets of few-shot tasks at inference, removing the class-balance artefact. |
Olivier Veilleux; Malik Boudiaf; Pablo Piantanida; Ismail Ben Ayed; | |
712 | Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To study this hypothesis, we weaponize quantization-aware training and propose a new training framework to implement adversarial quantization outcomes. |
Sanghyun Hong; Michael-Andrei Panaitescu-Liess; Yigitcan Kaya; Tudor Dumitras; | code |
713 | Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study differentially private stochastic optimization in convex and non-convex settings. |
Raef Bassily; Crist�bal Guzm�n; Michael Menart; | |
714 | TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. |
Minchao Wu; Michael Norrish; Christian Walder; Amir Dezfouli; | |
715 | Integrating Tree Path in Transformer for Code Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate two representative path encoding methods shown in previous research work and integrate them into the attention module of Transformer. |
Han Peng; Ge Li; Wenhan Wang; YunFei Zhao; Zhi Jin; | code |
716 | Twins: Revisiting The Design of Spatial Attention in Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we revisit the design of the spatial attention and demonstrate that a carefully devised yet simple spatial attention mechanism performs favorably against the state-of-the-art schemes. |
Xiangxiang Chu; Zhi Tian; Yuqing Wang; Bo Zhang; Haibing Ren; Xiaolin Wei; Huaxia Xia; Chunhua Shen; | |
717 | Evaluating State-of-the-Art Classification Models Against Bayes Optimality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While generally an intractable quantity, we show that we can compute the exact Bayes error of generative models learned using normalizing flows. |
Ryan Theisen; Huan Wang; Lav R. Varshney; Caiming Xiong; Richard Socher; | |
718 | Data-Efficient Instance Generation from Instance Discrimination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a data-efficient Instance Generation ($\textit{InsGen}$) method based on instance discrimination. |
Ceyuan Yang; Yujun Shen; Yinghao Xu; Bolei Zhou; | |
719 | Reliable Post Hoc Explanations: Modeling Uncertainty in Explainability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the aforementioned challenges by developing a novel Bayesian framework for generating local explanations along with their associated uncertainty. |
Dylan Slack; Anna Hilgard; Sameer Singh; Himabindu Lakkaraju; | |
720 | Learning Graph Models for Retrosynthesis Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on this viewpoint, this paper introduces a graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during a chemical reaction. |
Vignesh Ram Somnath; Charlotte Bunne; Connor Coley; Andreas Krause; Regina Barzilay; | |
721 | Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address Stackelberg models of combinatorial congestion games (CCGs); we aim to optimize the parameters of CCGs so that the selfish behavior of non-atomic players attains desirable equilibria. |
Shinsaku Sakaue; Kengo Nakamura; | |
722 | Inverse Optimal Control Adapted to The Noise Characteristics of The Human Sensorimotor System Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce inverse optimal control with signal-dependent noise, which allows inferring the cost function from observed behavior. |
Matthias Schultheis; Dominik Straub; Constantin A. Rothkopf; | |
723 | Deep Neural Networks As Point Estimates for Deep Gaussian Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we establish an equivalence between the forward passes of neural networks and (deep) sparse Gaussian process models. |
Vincent Dutordoir; James Hensman; Mark van der Wilk; Carl Henrik Ek; Zoubin Ghahramani; Nicolas Durrande; | |
724 | Locality Defeats The Curse of Dimensionality in Convolutional Teacher-student Scenarios Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study this problem within a teacher-student framework for kernel regression, using ‘convolutional’ kernels inspired by the neural tangent kernel of simple convolutional architectures of given filter size. |
Alessandro Favero; Francesco Cagnetta; Matthieu Wyart; | |
725 | Causal Identification with Matrix Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a new causal identification algorithm which utilizes both graphical criteria and matrix equations. |
Sanghack Lee; Elias Bareinboim; | |
726 | Private and Non-private Uniformity Testing for Ranking Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a central DP algorithm that requires $O\left(\max \{ 1/\epsilon_0, 1/\sqrt{m} \} \right)$ where $\epsilon_0$ is the privacy budget parameter. |
R�bert Busa-Fekete; Dimitris Fotakis; Emmanouil Zampetakis; | |
727 | Model-Based Reinforcement Learning Via Imagination with Derived Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the memory prosthesis proposed by neuroscientists, we present a novel model-based reinforcement learning framework called Imagining with Derived Memory (IDM). |
Yao Mu; Yuzheng Zhuang; Bin Wang; Guangxiang Zhu; Wulong Liu; Jianyu Chen; Ping Luo; Shengbo Li; Chongjie Zhang; Jianye Hao; | |
728 | Compositional Transformers for Scene Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the GANformer2 model, an iterative object-oriented transformer, explored for the task of generative modeling. |
Dor Arad Hudson; Larry Zitnick; | code |
729 | An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work resolves this subsequent question, showing that an exponential sample complexity lower bound still holds even if a constant gap is assumed. |
Yuanhao Wang; Ruosong Wang; Sham Kakade; | |
730 | Combating Noise: Semi-supervised Learning By Region Uncertainty Quantification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we delve into semi-supervised learning for object detection, where labeled data are more labor-intensive to collect. |
Zhenyu Wang; Ya-Li Li; Ye Guo; Shengjin Wang; | |
731 | Reducing The Covariate Shift By Mirror Samples in Cross Domain Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To relieve the limitations and conflicts, we introduce a novel concept named (virtual) mirror, which represents the equivalent sample in another domain. |
Yin Zhao; minquan wang; Longjun Cai; | |
732 | Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we address this issue by proposing a permutation-invariant variational autoencoder for graph structured data. |
Robin Winter; Frank Noe; Djork-Arn� Clevert; | |
733 | Causal Abstractions of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new structural analysis method grounded in a formal theory of causal abstraction that provides rich characterizations of model-internal representations and their roles in input/output behavior. |
Atticus Geiger; Hanson Lu; Thomas Icard; Christopher Potts; | |
734 | Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop new parameter-free and scale-free algorithms for solving convex-concave saddle-point problems. |
Julien Grand-Cl�ment; Christian Kroer; | |
735 | 3DP3: 3D Scene Perception Via Probabilistic Programming Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present 3DP3, a framework for inverse graphics that uses inference in a structured generative model of objects, scenes, and images. |
Nishad Gothoskar; Marco Cusumano-Towner; Ben Zinberg; Matin Ghavamizadeh; Falk Pollok; Austin Garrett; Josh Tenenbaum; Dan Gutfreund; Vikash Mansinghka; | |
736 | Novel Upper Bounds for The Constrained Most Probable Explanation Task Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose several schemes for upper bounding the optimal value of the constrained most probable explanation (CMPE) problem. |
Tahrima Rahman; Sara Rouhani; Vibhav Gogate; | |
737 | Why Spectral Normalization Stabilizes GANs: Analysis and Improvements Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that SN controls two important failure modes of GAN training: exploding and vanishing gradients. |
Zinan Lin; Vyas Sekar; Giulia Fanti; | |
738 | $(\textrm{Implicit})^2$: Implicit Layers for Implicit Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that these two seemingly orthogonal concepts are remarkably well-suited for each other. |
Zhichun Huang; Shaojie Bai; J. Zico Kolter; | |
739 | Best Arm Identification in Contaminated Stochastic Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes two algorithms, a gap-based algorithm and one based on the successive elimination, for best arm identification in sub-Gaussian bandits. |
Arpan Mukherjee; Ali Tajer; Pin-Yu Chen; Payel Das; | |
740 | MADE: Exploration Via Maximizing Deviation from Explored Regions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose a new exploration approach via maximizing the deviation of the occupancy of the next policy from the explored regions. |
Tianjun Zhang; Paria Rashidinejad; Jiantao Jiao; Yuandong Tian; Joseph E. Gonzalez; Stuart Russell; | |
741 | Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an automatic curriculum algorithm, Variational Automatic Curriculum Learning (VACL), for solving challenging goal-conditioned cooperative multi-agent reinforcement learning problems. |
Jiayu Chen; Yuanxin Zhang; Yuanfan Xu; Huimin Ma; Huazhong Yang; Jiaming Song; Yu Wang; Yi Wu; | |
742 | Align Before Fuse: Vision and Language Representation Learning with Momentum Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning. |
Junnan Li; Ramprasaath Selvaraju; Akhilesh Gotmare; Shafiq Joty; Caiming Xiong; Steven Chu Hong Hoi; | code |
743 | Variational Model Inversion Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide a probabilistic interpretation of model inversion attacks, and formulate a variational objective that accounts for both diversity and accuracy. |
Kuan-Chieh Wang; YAN FU; Ke Li; Ashish Khisti; Richard Zemel; Alireza Makhzani; | |
744 | Graph Neural Networks with Adaptive Residual Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we discover an interesting phenomenon that although residual connections in the message passing of GNNs help improve the performance, they immensely amplify GNNs’ vulnerability against abnormal node features. |
Xiaorui Liu; Jiayuan Ding; Wei Jin; Han Xu; Yao Ma; Zitao Liu; Jiliang Tang; | |
745 | Efficient Active Learning for Gaussian Process Classification By Error Reduction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study both active learning scenarios for Gaussian Process Classification (GPC). |
Guang Zhao; Edward Dougherty; Byung-Jun Yoon; Francis Alexander; Xiaoning Qian; | |
746 | Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop novel techniques to address the above challenges and explicitly characterize the non-asymptotic error bound for the general off-policy setting with i.i.d. or Markovian samples, and show that it converges as fast as $\mathcal O(1/\sqrt T)$ (up to a factor of $\mathcal O(\log T)$). |
Yue Wang; Shaofeng Zou; Yi Zhou; | |
747 | A Little Robustness Goes A Long Way: Leveraging Robust Features for Targeted Transfer Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we show that training the source classifier to be slightly robust-that is, robust to small-magnitude adversarial examples—substantially improves the transferability of class-targeted and representation-targeted adversarial attacks, even between architectures as different as convolutional neural networks and transformers. |
Jacob Springer; Melanie Mitchell; Garrett Kenyon; | |
748 | TriBERT: Human-centric Audio-visual Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce TriBERT — a transformer-based architecture, inspired by ViLBERT, which enables contextual feature learning across three modalities: vision, pose, and audio, with the use of flexible co-attention. |
Tanzila Rahman; Mengyu Yang; Leonid Sigal; | |
749 | How Does A Neural Network's Architecture Impact Its Robustness to Noisy Labels? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore an area understudied by previous works — how the network’s architecture impacts its robustness to noisy labels. |
Jingling Li; Mozhi Zhang; Keyulu Xu; John Dickerson; Jimmy Ba; | |
750 | Calibration and Consistency of Adversarial Surrogate Losses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an extensive study of this question, including a detailed analysis of the $\mathcal{H}$-calibration and $\mathcal{H}$-consistency of adversarial surrogate losses. |
Pranjal Awasthi; Natalie Frank; Anqi Mao; Mehryar Mohri; Yutao Zhong; | |
751 | The Value of Information When Deciding What to Learn Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, building upon the seminal design principle of information-directed sampling (Russo & Van Roy, 2014), we address this shortcoming directly to couple optimal information acquisition with the optimal design of learning targets. |
Dilip Arumugam; Benjamin Van Roy; | |
752 | Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on a series of off-policy inference-based actor-critic algorithms — MPO, AWR, and SAC — to decouple their algorithmic innovations and implementation decisions. |
Hiroki Furuta; Tadashi Kozuno; Tatsuya Matsushima; Yutaka Matsuo; Shixiang (Shane) Gu; | |
753 | Can FMRI Reveal The Representation of Syntactic Structure in The Brain? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose novel multi-dimensional features that encode information about the syntactic structure of sentences. |
Aniketh Janardhan Reddy; Leila Wehbe; | code |
754 | Robust Implicit Networks Via Non-Euclidean Contractions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides a new framework, which we call Non-Euclidean Monotone Operator Network (NEMON), to design well-posed and robust implicit neural networks based upon contraction theory for the non-Euclidean norm $\ell_\infty$. |
Saber Jafarpour; Alexander Davydov; Anton Proskurnikov; Francesco Bullo; | code |
755 | A Kernel-based Test of Independence for Cluster-correlated Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose a novel HSIC-based independence test to evaluate the dependence between two multivariate variables based on cluster-correlated data. |
Hongjiao Liu; Anna Plantinga; Yunhua Xiang; Michael Wu; | |
756 | Efficient Methods for Gaussian Markov Random Fields Under Sparse Linear Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new class of methods to overcome these challenges in the common case of sparse constraints, where one has a large number of constraints and each only involves a few elements. |
David Bolin; Jonas Wallin; | |
757 | Sparse Is Enough in Scaling Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study sparse variants for all layers in the Transformer and propose Scaling Transformers, a family of next generation Transformer models that use sparse layers to scale efficiently and perform unbatched decoding much faster than the standard Transformer as we scale up the model size. |
Sebastian Jaszczur; Aakanksha Chowdhery; Afroz Mohiuddin; Lukasz Kaiser; Wojciech Gajewski; Henryk Michalewski; Jonni Kanerva; | |
758 | Sparse Training Via Boosting Pruning Plasticity with Neuroregeneration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design a novel gradual magnitude pruning (GMP) method, named gradual pruning with zero-cost neuroregeneration (GraNet), that advances state of the art. |
Shiwei Liu; Tianlong Chen; Xiaohan Chen; Zahra Atashgahi; Lu Yin; Huanyu Kou; Li Shen; Mykola Pechenizkiy; Zhangyang Wang; Decebal Constantin Mocanu; | |
759 | Low-Fidelity Video Encoder Optimization for Temporal Action Localization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we resolve this challenge by introducing a novel low-fidelity (LoFi) video encoder optimization method. |
Mengmeng Xu; Juan Manuel Perez Rua; Xiatian Zhu; Bernard Ghanem; Brais Martinez; | |
760 | On Provable Benefits of Depth in Training Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by these findings, we propose a decoupled structure for GCNs that detaches weight matrices from feature propagation to preserve the expressive power and ensure good generalization performance. |
Weilin Cong; Morteza Ramezani; Mehrdad Mahdavi; | |
761 | Practical Near Neighbor Search Via Group Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new algorithm for the approximate near neighbor problem that combines classical ideas from group testing with locality-sensitive hashing (LSH). |
Joshua Engels; Benjamin Coleman; Anshumali Shrivastava; | |
762 | Baby Intuitions Benchmark (BIB): Discerning The Goals, Preferences, and Actions of Others Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The Baby Intuitions Benchmark (BIB) challenges machines to predict the plausibility of an agent’s behavior based on the underlying causes of its actions. |
Kanishk Gandhi; Gala Stojnic; Brenden M. Lake; Moira Dillon; | |
763 | Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces Neural Hybrid Automata (NHAs), a recipe for learning SHS dynamics without a priori knowledge on the number, mode parameters, and inter-modal transition dynamics. |
Michael Poli; Stefano Massaroli; Luca Scimeca; Sanghyuk Chun; Seong Joon Oh; Atsushi Yamashita; Hajime Asama; Jinkyoo Park; Animesh Garg; | |
764 | Fast Projection Onto The Capped Simplex with Applications to Sparse Regression in Bioinformatics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of projecting a vector onto the so-called k-capped simplex, which is a hyper-cube cut by a hyperplane. |
Man Shun Ang; Jianzhu Ma; Nianjun Liu; Kun Huang; Yijie Wang; | |
765 | The Many Faces of Adversarial Risk Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit these definitions, make them rigorous, and critically examine their similarities and differences. |
Muni Sreenivas Pydi; Varun Jog; | |
766 | Meta-Adaptive Nonlinear Control: Theory and Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). |
Guanya Shi; Kamyar Azizzadenesheli; Michael O'Connell; Soon-Jo Chung; Yisong Yue; | |
767 | Compositional Reinforcement Learning from Logical Specifications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a compositional learning approach, called DIRL, that interleaves high-level planning and reinforcement learning. |
Kishor Jothimurugan; Suguman Bansal; Osbert Bastani; Rajeev Alur; | |
768 | Differentiable Quality Diversity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the differentiable quality diversity (DQD) problem, a special case of QD, where both the objective and measure functions are first order differentiable. |
Matthew Fontaine; Stefanos Nikolaidis; | code |
769 | Credit Assignment Through Broadcasting A Global Error Vector Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present both a learning rule, called global error-vector broadcasting (GEVB), and a class of DNNs, called vectorized nonnegative networks (VNNs), in which this learning rule operates. |
David Clark; L Abbott; Sueyeon Chung; | |
770 | An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a practical online method for solving a class of distributional robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural networks. |
Qi Qi; Zhishuai Guo; Yi Xu; Rong Jin; Tianbao Yang; | |
771 | A Single Gradient Step Finds Adversarial Examples on Random Two-layers Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In fact we prove that a single step of gradient descent suffices. We also show this result for any subexponential width random neural network with smooth activation function. |
Sebastien Bubeck; Yeshwanth Cherapanamjeri; Gauthier Gidel; Remi Tachet des Combes; | |
772 | Parameterized Knowledge Transfer for Personalized Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients. |
Jie Zhang; Song Guo; Xiaosong Ma; Haozhao Wang; Wenchao Xu; Feijie Wu; | |
773 | Contrastively Disentangled Sequential Variational Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel sequence representation learning method, named Contrastively Disentangled Sequential Variational Autoencoder (C-DSVAE), to extract and separate the static (time-invariant) and dynamic (time-variant) factors in the latent space. |
Junwen Bai; Weiran Wang; Carla P. Gomes; | |
774 | Recursive Causal Structure Learning in The Presence of Latent Variables and Selection Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel computationally efficient recursive constraint-based method that is sound and complete. |
Sina Akbari; Ehsan Mokhtarian; AmirEmad Ghassami; Negar Kiyavash; | |
775 | Generalization Error Rates in Kernel Regression: The Crossover from The Noiseless to Noisy Regime Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this manuscript we consider Kernel Ridge Regression (KRR) under the Gaussian design. |
Hugo Cui; Bruno Loureiro; Florent Krzakala; Lenka Zdeborov�; | |
776 | Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this manuscript, we characterise the learning of a mixture of $K$ Gaussians with generic means and covariances via empirical risk minimisation (ERM) with any convex loss and regularisation. |
Bruno Loureiro; Gabriele Sicuro; Cedric Gerbelot; Alessandro Pacco; Florent Krzakala; Lenka Zdeborov�; | |
777 | Spectral Embedding for Dynamic Networks with Stability Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of embedding a dynamic network, to obtain time-evolving vector representations of each node, which can then be used to describe changes in behaviour of individual nodes, communities, or the entire graph. |
Ian Gallagher; Andrew Jones; Patrick Rubin-Delanchy; | |
778 | Infinite Time Horizon Safety of Bayesian Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of verifying safety when running a Bayesian neural network policy in a feedback loop with infinite time horizon systems. |
Mathias Lechner; �orde �ikelic; Krishnendu Chatterjee; Thomas Henzinger; | |
779 | Towards Understanding Retrosynthesis By Energy-based Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. |
Ruoxi Sun; Hanjun Dai; Li Li; Steven Kearnes; Bo Dai; | |
780 | List-Decodable Mean Estimation in Nearly-PCA Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the fundamental task of list-decodable mean estimation in high dimensions. Our main result is a new algorithm for bounded covariance distributions with optimal sample complexity and near-optimal error guarantee, running in {\em nearly-PCA time}. |
Ilias Diakonikolas; Daniel Kane; Daniel Kongsgaard; Jerry Li; Kevin Tian; | |
781 | Distributed Zero-Order Optimization Under Adversarial Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a distributed zero-order projected gradient descent algorithm to solve the problem. |
Arya Akhavan; Massimiliano Pontil; Alexandre Tsybakov; | |
782 | Reliable Estimation of KL Divergence Using A Discriminator in Reproducing Kernel Hilbert Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we look at this issue from statistical learning theory and function space complexity perspective to understand why this happens and how to solve it. |
Sandesh Ghimire; Aria Masoomi; Jennifer Dy; | |
783 | Latent Matters: Learning Deep State-Space Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore propose a constrained optimisation framework as a general approach for training DSSMs. |
Alexej Klushyn; Richard Kurle; Maximilian Soelch; Botond Cseke; Patrick van der Smagt; | |
784 | On The Estimation Bias in Double Q-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that such underestimation bias may lead to multiple non-optimal fixed points under an approximate Bellman operator. |
Zhizhou Ren; Guangxiang Zhu; Hao Hu; Beining Han; Jianglun Chen; Chongjie Zhang; | |
785 | Mitigating Forgetting in Online Continual Learning with Neuron Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel method which attempts to mitigate catastrophic forgetting in online continual learning from a new perspective, i.e., neuron calibration. |
Haiyan Yin; peng yang; Ping Li; | |
786 | Escaping Saddle Points with Compressed SGD Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we extend these results to convergence to an $\varepsilon$-second-order stationary point ($\varepsilon$-SOSP), which is to the best of our knowledge the first result of this type. |
Dmitrii Avdiukhin; Grigory Yaroslavtsev; | |
787 | Non-Gaussian Gaussian Processes for Few-Shot Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this limitation by leveraging the flexibility of Normalizing Flows to modulate the posterior predictive distribution of the GP. |
Marcin Sendera; Jacek Tabor; Aleksandra Nowak; Andrzej Bedychaj; Massimiliano Patacchiola; Tomasz Trzcinski; Przemyslaw Spurek; Maciej Zieba; | |
788 | Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), which effectively alleviates the extrapolation error by only trusting the state-action pairs given in the dataset for value estimation. |
Yiqin Yang; Xiaoteng Ma; Li Chenghao; Zewu Zheng; Qiyuan Zhang; Gao Huang; Jun Yang; Qianchuan Zhao; | code |
789 | Online Learning in Periodic Zero-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze the robustness of these online learning behaviors in the case of periodic zero-sum games with a time-invariant equilibrium. |
Tanner Fiez; Ryann Sim; Stratis Skoulakis; Georgios Piliouras; Lillian Ratliff; | |
790 | K-Net: Towards Unified Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a unified, simple, and effective framework for these essentially similar tasks. |
Wenwei Zhang; Jiangmiao Pang; Kai Chen; Chen Change Loy; | code |
791 | Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper leverages machine-learned predictions to design competitive algorithms for online conversion problems with the goal of improving the competitive ratio when predictions are accurate (i.e., consistency), while also guaranteeing a worst-case competitive ratio regardless of the prediction quality (i.e., robustness). |
Bo Sun; Russell Lee; Mohammad Hajiesmaili; Adam Wierman; Danny Tsang; | |
792 | Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Dynaboard, an evaluation-as-a-service framework for hosting benchmarks and conducting holistic model comparison, integrated with the Dynabench platform. |
Zhiyi Ma; Kawin Ethayarajh; Tristan Thrush; Somya Jain; Ledell Wu; Robin Jia; Christopher Potts; Adina Williams; Douwe Kiela; | |
793 | NTopo: Mesh-free Topology Optimization Using Implicit Neural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a novel machine learning approach for topology optimization—an important class of inverse problems with high-dimensional parameter spaces and highly nonlinear objective landscapes. |
Jonas Zehnder; Yue Li; Stelian Coros; Bernhard Thomaszewski; | |
794 | Generalization Bounds for (Wasserstein) Robust Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive generalization bounds for robust optimization and Wasserstein robust optimization for Lipschitz and piecewise Hölder smooth loss functions under both stochastic and adversarial setting, assuming that the underlying data distribution satisfies transportation-information inequalities. |
Yang An; RUI GAO; | |
795 | Faster Matchings Via Learned Duals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We take a first step in this direction by combining the idea of machine-learned predictions with the idea of warm-starting primal-dual algorithms. |
Michael Dinitz; Sungjin Im; Thomas Lavastida; Benjamin Moseley; Sergei Vassilvitskii; | |
796 | Online Learning in MDPs with Linear Function Approximation and Bandit Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is developing an algorithm whose expected regret after $T$ episodes is bounded by $\widetilde{\mathcal{O}}(\sqrt{dHT})$, where $H$ is the number of steps in each episode and $d$ is the dimensionality of the feature map. |
Gergely Neu; Julia Olkhovskaya; | |
797 | Learning Collaborative Policies to Solve NP-hard Routing Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel hierarchical problem-solving strategy, termed learning collaborative policies (LCP), which can effectively find the near-optimum solution using two iterative DRL policies: the seeder and reviser. |
Minsu Kim; Jinkyoo Park; joungho kim; | |
798 | Efficient Mirror Descent Ascent Methods for Nonsmooth Minimax Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the paper, we propose a class of efficient mirror descent ascent methods to solve the nonsmooth nonconvex-strongly-concave minimax problems by using dynamic mirror functions, and introduce a convergence analysis framework to conduct rigorous theoretical analysis for our mirror descent ascent methods. |
Feihu Huang; Xidong Wu; Heng Huang; | |
799 | CO-PILOT: COllaborative Planning and ReInforcement Learning On Sub-Task Curriculum Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that RL and planning can collaboratively learn from each other to overcome their own drawbacks. |
Shuang Ao; Tianyi Zhou; Guodong Long; Qinghua Lu; Liming Zhu; Jing Jiang; | |
800 | Modality-Agnostic Topology Aware Localization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a data-driven approach for the indoor localization of an observer on a 2D topological map of the environment. |
Farhad Ghazvinian Zanjani; Ilia Karmanov; Hanno Ackermann; Daniel Dijkman; Simone Merlin; Max Welling; Fatih Porikli; | |
801 | Scalable Quasi-Bayesian Inference for Instrumental Variable Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present a scalable quasi-Bayesian procedure for IV regression, building upon the recently developed kernelized IV models. |
Ziyu Wang; Yuhao Zhou; Tongzheng Ren; Jun Zhu; | |
802 | Kernel Identification Through Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Drawing inspiration from recent progress in deep learning, we introduce a novel approach named KITT: Kernel Identification Through Transformers. |
Fergus Simpson; Ian Davies; Vidhi Lalchand; Alessandro Vullo; Nicolas Durrande; Carl Edward Rasmussen; | |
803 | Curriculum Design for Teaching Via Demonstrations: Theory and Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of teaching via demonstrations in sequential decision-making settings. |
Gaurav Yengera; Rati Devidze; Parameswaran Kamalaruban; Adish Singla; | |
804 | Revenue Maximization Via Machine Learning with Noisy Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to help place mechanism design via machine learning on firm foundations, we investigate the extent to which this learning process is robust to noise. |
Ellen Vitercik; Tom Yan; | |
805 | Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we bring secure computation techniques into social recommendation, and propose S3Rec, a sparsity-aware secure cross-platform social recommendation framework. |
Jinming Cui; Chaochao Chen; Lingjuan Lyu; Carl Yang; Wang Li; | |
806 | Parallelizing Thompson Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a batch Thompson Sampling framework for two canonical online decision-making problems with partial feedback, namely, stochastic multi-arm bandit and linear contextual bandit. |
Amin Karbasi; Vahab Mirrokni; Mohammad Shadravan; | |
807 | Dynamic Causal Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of performing a sequence of optimal interventions in a dynamic causal system where both the target variable of interest, and the inputs, evolve over time. |
Virginia Aglietti; Neil Dhir; Javier Gonz�lez; Theodoros Damoulas; | |
808 | Local Differential Privacy for Regret Minimization in Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we study privacy in the context of finite-horizon Markov Decision Processes (MDPs) by requiring information to be obfuscated on the user side. |
Evrard Garcelon; Vianney Perchet; Ciara Pike-Burke; Matteo Pirotta; | |
809 | Emergent Discrete Communication in Semantic Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by word embedding techniques from natural language processing, we propose neural agent architectures that enables them to communicate via discrete tokens derived from a learned, continuous space. |
Mycal Tucker; Huao Li; Siddharth Agrawal; Dana Hughes; Katia Sycara; Michael Lewis; Julie A. Shah; | |
810 | Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce a novel unsupervised approach for learning disentangled representations of neural activity called Swap-VAE. |
Ran Liu; Mehdi Azabou; Max Dabagia; Chi-Heng Lin; Mohammad Gheshlaghi Azar; Keith Hengen; Michal Valko; Eva Dyer; | |
811 | Equivariant Manifold Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we lay the theoretical foundations for learning symmetry-invariant distributions on arbitrary manifolds via equivariant manifold flows. |
Isay Katsman; Aaron Lou; Derek Lim; Qingxuan Jiang; Ser Nam Lim; Christopher M. De Sa; | |
812 | Scalable Bayesian GPFA with Automatic Relevance Determination and Discrete Noise Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To enable the analysis of continuous recordings without trial structure, we introduce a novel variational inference strategy that scales near-linearly in time and also allows for non-Gaussian noise models appropriate for electrophysiological recordings. |
Kristopher Jensen; Ta-Chu Kao; Jasmine Stone; Guillaume Hennequin; | |
813 | Recurrence Along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a concept of layer aggregation to describe how information from previous layers can be reused to better extract features at the current layer. |
Jingyu Zhao; Yanwen Fang; Guodong Li; | |
814 | Independent Prototype Propagation for Zero-Shot Compositionality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To be able to deal with underspecified datasets while still leveraging contextual clues during classification, we propose ProtoProp, a novel prototype propagation graph method. |
Frank Ruis; Gertjan Burghouts; Doina Bucur; | |
815 | Universal Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we develop a new universal GCN framework, namely U-GCN. |
Di Jin; Zhizhi Yu; Cuiying Huo; Rui Wang; Xiao Wang; Dongxiao He; Jiawei Han; | code |
816 | Adversarial Feature Desensitization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. |
Pouya Bashivan; Reza Bayat; Adam Ibrahim; Kartik Ahuja; Mojtaba Faramarzi; Touraj Laleh; Blake Richards; Irina Rish; | code |
817 | Few-Shot Data-Driven Algorithms for Low Rank Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop new data-driven low rank approximation algorithms with better computational efficiency in the training phase, alleviating these drawbacks. |
Piotr Indyk; Tal Wagner; David Woodruff; | |
818 | Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel reflectance decomposition network that can estimate shape, BRDF, and per-image illumination given a set of object images captured under varying illumination. |
Mark Boss; Varun Jampani; Raphael Braun; Ce Liu; Jonathan Barron; Hendrik Lensch; | code |
819 | Asymptotics of The Bootstrap Via Stability with Applications to Inference with Model Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive general stability conditions under which the empirical bootstrap estimator is consistent and quantify the speed of convergence. |
Morgane Austern; Vasilis Syrgkanis; | |
820 | Dynamic Influence Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the {\em incremental model}, the social network gets enlarged over time and one only introduces new users and establishes new social links, we design an algorithm that achieves $(1-1/e-\epsilon)$-approximation to the optimal solution and has $k \cdot\mathsf{poly}(\log n, \epsilon^{-1})$ amortized running time, which matches the state-of-art offline algorithm with only poly-logarithmic overhead. |
Binghui Peng; | |
821 | Risk Monotonicity in Statistical Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive the first consistent and risk-monotonic algorithms for a general statistical learning setting under weak assumptions, consequently resolving an open problem Viering et al. (2019) on how to avoid non-monotonic behavior of risk curves. |
Zakaria Mhammedi; | |
822 | Information Is Power: Intrinsic Control Via Information Capture Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study this question in dynamic partially-observed environments, and argue that a compact and general learning objective is to minimize the entropy of the agent’s state visitation estimated using a latent state-space model. |
Nicholas Rhinehart; Jenny Wang; Glen Berseth; John Co-Reyes; Danijar Hafner; Chelsea Finn; Sergey Levine; | |
823 | Extracting Deformation-Aware Local Features By Learning to Deform Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new approach to compute features from still images that are robust to non-rigid deformations to circumvent the problem of matching deformable surfaces and objects. |
Guilherme Potje; Renato Martins; Felipe Chamone; Erickson Nascimento; | code |
824 | Object-Centric Representation Learning with Generative Spatial-Temporal Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose Dynamics-aware Multi-Object Network (DyMON), a method that broadens the scope of multi-view object-centric representation learning to dynamic scenes. |
Nanbo Li; Muhammad Ahmed Raza; Wenbin Hu; Zhaole Sun; Robert Fisher; | |
825 | Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Taking traffic simulation as the testing bed, in this work we develop a novel MARL method called Coordinated Policy Optimization (CoPO), which incorporates social psychology principle to learn neural controller for SDP. |
Zhenghao Peng; quanyi li; Ka Ming Hui; Chunxiao Liu; Bolei Zhou; | code |
826 | Gradient-based Hyperparameter Optimization Over Long Horizons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose forward-mode differentiation with sharing (FDS), a simple and efficient algorithm which tackles memory scaling issues with forward-mode differentiation, and gradient degradation issues by sharing hyperparameters that are contiguous in time. |
Paul Micaelli; Amos J. Storkey; | |
827 | Stochastic Bias-Reduced Gradient Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a new primitive for stochastic optimization: a low-bias, low-cost estimator of the minimizer $x_\star$ of any Lipschitz strongly-convex function $f$. |
Hilal Asi; Yair Carmon; Arun Jambulapati; Yujia Jin; Aaron Sidford; | |
828 | The Causal-Neural Connection: Expressiveness, Learnability, and Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show this is not the case by disentangling the notions of expressivity and learnability. Specifically, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020), which describes the limits of what can be learned from data, still holds for neural models. |
Kevin Xia; Kai-Zhan Lee; Yoshua Bengio; Elias Bareinboim; | |
829 | Validation Free and Replication Robust Volume-based Data Valuation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formalize diversity via the volume of the data matrix (determinant of its left Gram). This allows us to formally connect the diversity of data to the learning performance without requiring validation. |
Xinyi Xu; Zhaoxuan Wu; Chuan Sheng Foo; Bryan Kian Hsiang Low; | |
830 | Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a generic template for developing regret minimization algorithms in the Stochastic Shortest Path (SSP) model, which achieves minimax optimal regret as long as certain properties are ensured. |
Liyu Chen; Mehdi Jafarnia-Jahromi; Rahul Jain; Haipeng Luo; | |
831 | A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This leaves open the possibility of achieving the same attack results using poisoning attacks that do not have the full knowledge of the clean training set.In this work, we initiate a theoretical study of the problem above. |
Samuel Deng; Sanjam Garg; Somesh Jha; Saeed Mahloujifar; Mohammad Mahmoody; Abhradeep Guha Thakurta; | |
832 | Deep Learning Through The Lens of Example Difficulty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we adopt a perspective based on the role of individual examples. |
Robert Baldock; Hartmut Maennel; Behnam Neyshabur; | |
833 | R-Drop: Regularized Dropout for Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a simple consistency training strategy to regularize dropout, namely R-Drop, which forces the output distributions of different sub models generated by dropout to be consistent with each other. |
xiaobo liang; Lijun Wu; Juntao Li; Yue Wang; Qi Meng; Tao Qin; Wei Chen; Min Zhang; Tie-Yan Liu; | code |
834 | Diversity Enhanced Active Learning with Strictly Proper Scoring Rules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to allow better experimentation with the new acquisition functions, we develop a complementary batch AL algorithm, which encourages diversity in the vector of expected changes in scores for unlabelled data. |
Wei Tan; Lan Du; Wray Buntine; | |
835 | SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To better address these challenges, we propose a new method, dubbed as SSUL-M (Semantic Segmentation with Unknown Label with Memory), by carefully combining several techniques tailored for semantic segmentation. |
Sungmin Cha; beomyoung kim; YoungJoon Yoo; Taesup Moon; | code |
836 | Lower and Upper Bounds on The Pseudo-Dimension of Tensor Network Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we derive upper and lower bounds on the VC dimension and pseudo-dimension of a large class of tensor network models for classification, regression and completion. |
Behnoush Khavari; Guillaume Rabusseau; | |
837 | What Makes Multi-Modal Learning Better Than Single (Provably) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we answer this question under a most popular multi-modal fusion framework, which firstly encodes features from different modalities into a common latent space and seamlessly maps the latent representations into the task space. |
Yu Huang; Chenzhuang Du; Zihui Xue; Xuanyao Chen; Hang Zhao; Longbo Huang; | |
838 | Quantifying and Improving Transferability in Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formally define transferability that one can quantify and compute in domain generalization. |
Guojun Zhang; Han Zhao; Yaoliang Yu; Pascal Poupart; | |
839 | Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop new quantile methods that address these shortcomings. |
Youngseog Chung; Willie Neiswanger; Ian Char; Jeff Schneider; | |
840 | Dynamic Inference with Neural Interpreters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules, which we call functions. |
Nasim Rahaman; Muhammad Waleed Gondal; Shruti Joshi; Peter Gehler; Yoshua Bengio; Francesco Locatello; Bernhard Sch�lkopf; | |
841 | Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate these shortcomings, we extend the Gumbel-Max trick to define distributions over structured domains. |
Kirill Struminsky; Artyom Gadetsky; Denis Rakitin; Danil Karpushkin; Dmitry P. Vetrov; | |
842 | Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a fundamentally different approach to this problem via a new Hamiltonian dynamics with a non-Newtonian momentum. |
Greg Ver Steeg; Aram Galstyan; | |
843 | Dynamic Normalization and Relay for Video Action Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Dynamic Normalization and Relay (DNR), an improved normalization design, to augment the spatial-temporal representation learning of any deep action recognition model, adapting to small batch size training settings. |
Dongqi Cai; Anbang Yao; Yurong Chen; | code |
844 | Robust Visual Reasoning Via Language Guided Neural Module Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this limitation by introducing a language-guided adaptive convolution layer (LG-Conv) into NMN, in which the filter weights of convolutions are explicitly multiplied with a spatially varying language-guided kernel. |
Arjun Akula; Varun Jampani; Soravit Changpinyo; Song-Chun Zhu; | |
845 | True Few-Shot Learning with Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Overall, our findings suggest that prior work significantly overestimated the true few-shot ability of LMs given the difficulty of few-shot model selection. |
Ethan Perez; Douwe Kiela; Kyunghyun Cho; | |
846 | Selective Sampling for Online Best-arm Identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work considers the problem of selective-sampling for best-arm identification. |
Romain Camilleri; Zhihan Xiong; Maryam Fazel; Lalit Jain; Kevin G. Jamieson; | |
847 | Multi-task Learning of Order-Consistent Causal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Under the multi-task learning setting, we propose a $l_1/l_2$-regularized maximum likelihood estimator (MLE) for learning $K$ linear structural equation models. |
Xinshi Chen; Haoran Sun; Caleb Ellington; Eric Xing; Le Song; | |
848 | Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. |
Yining Ma; Jingwen Li; Zhiguang Cao; Wen Song; Le Zhang; Zhenghua Chen; Jing Tang; | |
849 | Learning Interaction Rules from Multi-animal Trajectories Via Augmented Behavioral Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new framework for learning Granger causality from multi-animal trajectories via augmented theory-based behavioral models with interpretable data-driven models. |
Keisuke Fujii; Naoya Takeishi; Kazushi Tsutsui; Emyo Fujioka; Nozomi Nishiumi; Ryoya Tanaka; Mika Fukushiro; Kaoru Ide; Hiroyoshi Kohno; Ken Yoda; Susumu Takahashi; Shizuko Hiryu; Yoshinobu Kawahara; | |
850 | Differentiable Synthesis of Program Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to encode program architecture search as learning the probability distribution over all possible program derivations induced by a context-free grammar. |
Guofeng Cui; He Zhu; | |
851 | Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this direction, we first introduce a general formulation of probabilistic specifications for neural networks, which captures both probabilistic networks (e.g., Bayesian neural networks, MC-Dropout networks) and uncertain inputs (distributions over inputs arising from sensor noise or other perturbations). We then propose a general technique to verify such specifications by generalizing the notion of Lagrangian duality, replacing standard Lagrangian multipliers with functional multipliers that can be arbitrary functions of the activations at a given layer. |
Leonard Berrada; Sumanth Dathathri; Krishnamurthy Dvijotham; Robert Stanforth; Rudy R. Bunel; Jonathan Uesato; Sven Gowal; M. Pawan Kumar; | |
852 | Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the first algorithm that learns the structure of the FMDP while minimizing the regret. |
Aviv Rosenberg; Yishay Mansour; | |
853 | Linear-Time Probabilistic Solution of Boundary Value Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a fast algorithm for the probabilistic solution of boundary value problems (BVPs), which are ordinary differential equations subject to boundary conditions. |
Nicholas Kr�mer; Philipp Hennig; | |
854 | Lifelong Domain Adaptation Via Consolidated Internal Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop an algorithm to address unsupervised domain adaptation (UDA) in continual learning (CL) settings. |
Mohammad Rostami; | |
855 | Counterbalancing Learning and Strategic Incentives in Allocation Markets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider a setting where a benevolent social planner decides whether and how to allocate a single indivisible object to a queue of strategic agents. |
Jamie Kang; Faidra Monachou; Moran Koren; Itai Ashlagi; | |
856 | Controlling Neural Networks with Rule Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel training method that integrates rules into deep learning, in a way the strengths of the rules are controllable at inference. |
Sungyong Seo; Sercan Arik; Jinsung Yoon; Xiang Zhang; Kihyuk Sohn; Tomas Pfister; | |
857 | Making The Most of Your Day: Online Learning for Optimal Allocation of Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study online learning for optimal allocation when the resource to be allocated is time. |
Etienne Boursier; Tristan Garrec; Vianney Perchet; Marco Scarsini; | |
858 | Federated Reconstruction: Partially Local Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale. |
Karan Singhal; Hakim Sidahmed; Zachary Garrett; Shanshan Wu; John Rush; Sushant Prakash; | |
859 | Optimal Prediction of Markov Chains with and Without Spectral Gap Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the following learning problem with dependent data: Given a trajectory of length $n$ from a stationary Markov chain with $k$ states, the goal is to predict the distribution of the next state. |
Yanjun Han; Soham Jana; Yihong Wu; | |
860 | Subquadratic Overparameterization for Shallow Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide an analytical framework that allows us to adopt standard initialization strategies, possibly avoid lazy training, and train all layers simultaneously in basic shallow neural networks while attaining a desirable subquadratic scaling on the network width. |
ChaeHwan Song; Ali Ramezani-Kebrya; Thomas Pethick; Armin Eftekhari; Volkan Cevher; | |
861 | Continuous Doubly Constrained Batch Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. |
Rasool Fakoor; Jonas W. Mueller; Kavosh Asadi; Pratik Chaudhari; Alexander J. Smola; | |
862 | Bridging Explicit and Implicit Deep Generative Models Via Neural Stein Estimators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To take full advantages of both models and enable mutual compensation, we propose a novel joint training framework that bridges an explicit (unnormalized) density estimator and an implicit sample generator via Stein discrepancy. |
Qitian Wu; RUI GAO; Hongyuan Zha; | |
863 | Score-based Generative Modeling in Latent Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose the Latent Score-based Generative Model (LSGM), a novel approach that trains SGMs in a latent space, relying on the variational autoencoder framework. |
Arash Vahdat; Karsten Kreis; Jan Kautz; | |
864 | Deep Conditional Gaussian Mixture Model for Constrained Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following recent advances in deep generative models, we propose a novel framework for constrained clustering that is intuitive, interpretable, and can be trained efficiently in the framework of stochastic gradient variational inference. |
Laura Manduchi; Kieran Chin-Cheong; Holger Michel; Sven Wellmann; Julia Vogt; | |
865 | Bootstrap Your Object Detector Via Mixed Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. |
Mengde Xu; Zheng Zhang; Fangyun Wei; Yutong Lin; Yue Cao; Stephen Lin; Han Hu; Xiang Bai; | |
866 | Tensor Decompositions of Higher-order Correlations By Nonlinear Hebbian Plasticity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce a simple family of generalized nonlinear Hebbian learning rules. |
Gabriel Ocker; Michael Buice; | |
867 | Online Adaptation to Label Distribution Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually changing and the model must dynamically adapt to it without observing the true label. |
Ruihan Wu; Chuan Guo; Yi Su; Kilian Q. Weinberger; | |
868 | One Explanation Is Not Enough: Structured Attention Graphs for Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to utilize a beam search algorithm to systematically search for multiple explanations for each image. |
Vivswan Shitole; Fuxin Li; Minsuk Kahng; Prasad Tadepalli; Alan Fern; | |
869 | Integrating Expert ODEs Into Neural ODEs: Pharmacology and Disease Progression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To close this gap, we propose the latent hybridisation model (LHM) that integrates a system of expert-designed ODEs with machine-learned Neural ODEs to fully describe the dynamics of the system and to link the expert and latent variables to observable quantities. |
Zhaozhi Qian; William Zame; Lucas Fleuren; Paul Elbers; Mihaela van der Schaar; | |
870 | Shifted Chunk Transformer for Spatio-Temporal Representational Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the training difficulty and enhance the spatio-temporal learning, we construct a shifted chunk Transformer with pure self-attention blocks. |
Xuefan Zha; Wentao Zhu; Lv Xun; Sen Yang; Ji Liu; | |
871 | Faster Proximal Algorithms for Matrix Optimization Using Jacobi-based Eigenvalue Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose to use an old and surprisingly simple method due to Jacobi to compute these eigenvalue and singular value decompositions, and we demonstrate that it can lead to substantial gains in terms of computation time compared to standard approaches. |
Hamza Fawzi; Harry Goulbourne; | |
872 | Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles As A Target for NLP Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: First, we present a dataset of cryptic clues as a challenging new benchmark for NLP systems that seek to process compositional language in more creative, human-like ways. After showing that three non-neural approaches and T5, a state-of-the-art neural language model, do not achieve good performance, we make our second main contribution: a novel curriculum approach, in which the model is first fine-tuned on related tasks such as unscrambling words. |
Josh Rozner; Christopher Potts; Kyle Mahowald; | |
873 | An Improved Analysis of Gradient Tracking for Decentralized Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a tighter analysis of the GT method in the stochastic strongly convex, convex and non-convex settings. |
Anastasiia Koloskova; Tao Lin; Sebastian U. Stich; | |
874 | Entropic Desired Dynamics for Intrinsic Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By situating these latent codes in a globally consistent coordinate system, we show that agents can reliably reach more states in the long term while still optimizing a local objective. |
Steven Hansen; Guillaume Desjardins; Kate Baumli; David Warde-Farley; Nicolas Heess; Simon Osindero; Volodymyr Mnih; | |
875 | Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose to explore additional cross-video and cross-modality supervisory signals to facilitate weakly-supervised audio-visual video parsing. |
Yan-Bo Lin; Hung-Yu Tseng; Hsin-Ying Lee; Yen-Yu Lin; Ming-Hsuan Yang; | |
876 | Littlestone Classes Are Privately Online Learnable Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of online classification under a privacy constraint. |
Noah Golowich; Roi Livni; | |
877 | Dual Parameterization of Sparse Variational Gaussian Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we improve their computational efficiency by using a dual parameterization where each data example is assigned dual parameters, similarly to site parameters used in expectation propagation. |
Vincent ADAM; Paul Chang; Mohammad Emtiyaz E. Khan; Arno Solin; | |
878 | Learning to Dehaze with Polarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generalized physical formation model of hazy images and a robust polarization-based dehazing pipeline without the above assumption or requirement, along with a neural network tailored to the pipeline. |
Chu Zhou; Minggui Teng; Yufei Han; Chao Xu; Boxin Shi; | |
879 | Conservative Data Sharing for Multi-Task Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that a natural use case of offline RL is in settings where we can pool large amounts of data collected in various scenarios for solving different tasks, and utilize all of this data to learn behaviors for all the tasks more effectively rather than training each one in isolation. |
Tianhe Yu; Aviral Kumar; Yevgen Chebotar; Karol Hausman; Sergey Levine; Chelsea Finn; | |
880 | Universal Rate-Distortion-Perception Representations for Lossy Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove that the corresponding information-theoretic universal rate-distortion-perception function is operationally achievable in an approximate sense. |
George Zhang; Jingjing Qian; Jun Chen; Ashish Khisti; | |
881 | What’s A Good Imputation to Predict with Missing Values? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose such a procedure, adapting NeuMiss, a neural network capturing the conditional links across observed and unobserved variables whatever the missing-value pattern. |
Marine Le Morvan; Julie Josse; Erwan Scornet; Gael Varoquaux; | |
882 | Replacing Rewards with Examples: Example-Based Policy Search Via Recursive Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive a control algorithm that maximizes the future probability of these successful outcome examples. |
Ben Eysenbach; Sergey Levine; Russ R. Salakhutdinov; | |
883 | Hierarchical Skills for Efficient Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze this trade-off for low-level policy pre-training with a new benchmark suite of diverse, sparse-reward tasks for bipedal robots. |
Jonas Gehring; Gabriel Synnaeve; Andreas Krause; Nicolas Usunier; | |
884 | Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present ev-softmax, a sparse normalization function that preserves the multimodality of probability distributions. |
Phil Chen; Mikhal Itkina; Ransalu Senanayake; Mykel J. Kochenderfer; | |
885 | Submodular + Concave Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we initiate the study of the maximization of functions of the form $F(x) = G(x) +C(x)$ over a solvable convex body $P$, where $G$ is a smooth DR-submodular function and $C$ is a smooth concave function. |
Siddharth Mitra; Moran Feldman; Amin Karbasi; | |
886 | DeepGEM: Generalized Expectation-Maximization for Blind Inversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the problem of blind inversion: solving an inverse problem with unknown or imperfect knowledge of the forward model parameters. |
Angela Gao; Jorge Castellanos; Yisong Yue; Zachary Ross; Katherine Bouman; | |
887 | Learning to Generate Visual Questions with Noisy Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel learning approach for double-hints based VQG, which can be cast as a weakly supervised learning problem with noises. |
Shen Kai; Lingfei Wu; Siliang Tang; Yueting Zhuang; zhen he; Zhuoye Ding; Yun Xiao; Bo Long; | |
888 | Pure Exploration in Kernel and Neural Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the curse of dimensionality, we propose to adaptively embed the feature representation of each arm into a lower-dimensional space and carefully deal with the induced model misspecifications. |
Yinglun Zhu; Dongruo Zhou; Ruoxi Jiang; Quanquan Gu; Rebecca Willett; Robert Nowak; | |
889 | Numerical Composition of Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give a fast algorithm to compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. |
Sivakanth Gopi; Yin Tat Lee; Lukas Wutschitz; | |
890 | Coresets for Classification – Simplified and Strengthened Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give relative error coresets for training linear classifiers with a broad class of loss functions, including the logistic loss and hinge loss. |
Tung Mai; Cameron Musco; Anup Rao; | |
891 | Sequential Algorithms for Testing Closeness of Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Focusing on the problem of testing whether two distributions $\mathcal{D}_1$ and $\mathcal{D}_2$ on $\{1,\dots, n\}$ are equal or $\epsilon$-far, we give several answers to this question. |
Aadil Oufkir; Omar Fawzi; Nicolas Flammarion; Aur�lien Garivier; | |
892 | Overlapping Spaces for Compact Graph Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We generalize the concept of product space and introduce an overlapping space that does not have the configuration search problem. |
Kirill Shevkunov; Liudmila Prokhorenkova; | |
893 | Hyperparameter Tuning Is All You Need for LISTA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that adding momentum to intermediate variables in the LISTA network achieves a better convergence rate and, in particular, the network with instance-optimal parameters is superlinearly convergent. |
Xiaohan Chen; Jialin Liu; Zhangyang Wang; Wotao Yin; | code |
894 | Foundations of Symbolic Languages for Model Interpretability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We do this in a principled way by rooting such a language in a logic called FOIL, which allows for expressing many simple but important explainability queries, and might serve as a core for more expressive interpretability languages. |
Marcelo Arenas; Daniel B�ez; Pablo Barcel�; Jorge P�rez; Bernardo Subercaseaux; | |
895 | Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge this gap, we present a new offline RL framework that smoothly interpolates between the two extremes of data composition, hence unifying imitation learning and vanilla offline RL. |
Paria Rashidinejad; Banghua Zhu; Cong Ma; Jiantao Jiao; Stuart Russell; | |
896 | Impression Learning: Online Representation Learning with Synaptic Plasticity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we derive an unsupervised local synaptic plasticity rule that trains neural circuits to infer latent structure from sensory stimuli via a novel loss function for approximate online Bayesian inference. |
Colin Bredenberg; Benjamin Lyo; Eero Simoncelli; Cristina Savin; | |
897 | How Well Do Feature Visualizations Support Causal Understanding of CNN Activations? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Taken together, we propose an objective psychophysical task to quantify the benefit of unit-level interpretability methods for humans, and find no evidence that a widely-used feature visualization method provides humans with better "causal understanding" of unit activations than simple alternative visualizations. |
Roland Zimmermann; Judy Borowski; Robert Geirhos; Matthias Bethge; Thomas Wallis; Wieland Brendel; | |
898 | Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Models in these systems are often developed and trained independently, which raises an obvious concern: Can improving a machine-learning model make the overall system worse? We answer this question affirmatively by showing that improving a model can deteriorate the performance of downstream models, even after those downstream models are retrained. |
Ruihan Wu; Chuan Guo; Awni Hannun; Laurens van der Maaten; | |
899 | Coarse-to-fine Animal Pose and Shape Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we propose a coarse-to-fine approach to reconstruct 3D animal mesh from a single image. |
Chen Li; Gim Hee Lee; | |
900 | Meta-Learning Sparse Implicit Neural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose to leverage a meta-learning approach in combination with network compression under a sparsity constraint, such that it renders a well-initialized sparse parameterization that evolves quickly to represent a set of unseen signals in the subsequent training. |
Jaeho Lee; Jihoon Tack; Namhoon Lee; Jinwoo Shin; | |
901 | Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. |
Ho Kei Cheng; Yu-Wing Tai; Chi-Keung Tang; | |
902 | Sparse Spiking Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present here the first sparse SNN backpropagation algorithm which achieves the same or better accuracy as current state of the art methods while being significantly faster and more memory efficient. |
Nicolas Perez-Nieves; Dan Goodman; | |
903 | Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our study, we empirically found that despite the predictions obtained from these regularized models are better calibrated, they suffer from not being as calibratable, namely, it is harder to further calibrate their predictions with post-hoc calibration methods like temperature scaling and histogram binning. |
Deng-Bao Wang; Lei Feng; Min-Ling Zhang; | |
904 | Towards Efficient and Effective Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we bridge this performance gap by introducing a novel Nuclear-Norm regularizer on network predictions to enforce function smoothing in the vicinity of data samples. |
Gaurang Sriramanan; Sravanti Addepalli; Arya Baburaj; Venkatesh Babu R; | |
905 | Intriguing Properties of Contrastive Losses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study three intriguing properties of contrastive learning. |
Ting Chen; Calvin Luo; Lala Li; | |
906 | Detecting Moments and Highlights in Videos Via Natural Language Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we present the Query-based Video Highlights (QVHighlights) dataset. |
Jie Lei; Tamara Berg; Mohit Bansal; | code |
907 | Stochastic Optimization Under Time Drift: Iterate Averaging, Step-decay Schedules, and High Probability Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of minimizing a convex function that is evolving in time according to unknown and possibly stochastic dynamics. |
Joshua Cutler; Dmitriy Drusvyatskiy; Zaid Harchaoui; | |
908 | Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As we will demonstrate, initialization of unobserved augmented states can become a key problem for neural ODEs. To alleviate this issue, we propose to augment the system’s state with its history. |
Andreas Schlaginhaufen; Philippe Wenk; Andreas Krause; Florian Dorfler; | |
909 | An Uncertainty Principle Is A Price of Privacy-Preserving Microdata Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present lower bounds for pure, approximate, and concentrated differential privacy. |
John Abowd; Robert Ashmead; Ryan Cumings-Menon; Simson Garfinkel; Daniel Kifer; Philip Leclerc; William Sexton; Ashley Simpson; Christine Task; Pavel Zhuravlev; | |
910 | Fairness in Ranking Under Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our primary point is that it is more principled to acknowledge and model the uncertainty explicitly. |
Ashudeep Singh; David Kempe; Thorsten Joachims; | |
911 | Generalized Proximal Policy Optimization with Sample Reuse Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we combine the theoretically supported stability benefits of on-policy algorithms with the sample efficiency of off-policy algorithms. |
James Queeney; Ioannis Paschalidis; Christos Cassandras; | |
912 | Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we attempt to tackle an ambitious task, termed as \emph{out-of-domain} knowledge distillation~(OOD-KD), which allows us to conduct KD using only OOD data that can be readily obtained at a very low cost. |
Gongfan Fang; Yifan Bao; Jie Song; Xinchao Wang; Donglin Xie; Chengchao Shen; Mingli Song; | code |
913 | Batch Active Learning at Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze an efficient active learning algorithm, which focuses on the large batch setting. |
Gui Citovsky; Giulia DeSalvo; Claudio Gentile; Lazaros Karydas; Anand Rajagopalan; Afshin Rostamizadeh; Sanjiv Kumar; | |
914 | Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The key insight in this effort is the idea of maintaining per-pixel pseudo-labels with iterative refinements by reconciling the multimodal input signals in our joint semantic mining (JSM). |
Jingjing Li; Wei Ji; Qi Bi; Cheng Yan; Miao Zhang; Yongri Piao; Huchuan Lu; Li cheng; | |
915 | Not All Images Are Worth 16×16 Words: Dynamic Transformers for Efficient Image Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that every image has its own characteristics, and ideally the token number should be conditioned on each individual input. |
Yulin Wang; Rui Huang; Shiji Song; Zeyi Huang; Gao Huang; | code |
916 | Contrastive Learning for Neural Topic Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address those issues, we revisit the adversarial topic architecture in the view point of mathematical analysis, propose a novel approach to re-formulate discriminative goal as an optimization problem, and design a novel sampling method which facilitates the integration of external variables. |
Thong Nguyen; Anh Tuan Luu; | |
917 | Learning in Two-player Zero-sum Partially Observable Markov Games with Perfect Recall Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of learning a Nash equilibrium (NE) in an extensive game with imperfect information (EGII) through self-play. |
Tadashi Kozuno; Pierre M�nard; Remi Munos; Michal Valko; | |
918 | A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we identify a geometric structure satisfied by a wide range of first-order accelerated methods. |
Jongmin Lee; Chanwoo Park; Ernest Ryu; | |
919 | ATISS: Autoregressive Transformers for Indoor Scene Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present ATISS, a novel autoregressive transformer architecture for creating diverse and plausible synthetic indoor environments, given only the room type and its floor plan. |
Despoina Paschalidou; Amlan Kar; Maria Shugrina; Karsten Kreis; Andreas Geiger; Sanja Fidler; | |
920 | Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we propose the method of Generalized Depthwise-Separable (GDWS) convolution – an efficient, universal, post-training approximation of a standard 2D convolution. |
Hassan Dbouk; Naresh Shanbhag; | code |
921 | A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce novel proof techniques to show that under suitable conditions, the worst-case regret of our posterior sampling method matches the best known results of optimization based methods. |
Christoph Dann; Mehryar Mohri; Tong Zhang; Julian Zimmert; | |
922 | Fast Federated Learning in The Presence of Arbitrary Device Unavailability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we study federated learning algorithms in the presence of arbitrary device unavailability and propose an algorithm named Memory-augmented Impatient Federated Averaging (MIFA). |
Xinran Gu; Kaixuan Huang; Jingzhao Zhang; Longbo Huang; | |
923 | On The Structure of Parametric Tournaments with Application to Ranking from Pairwise Comparisons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on our understanding of the rank-$2$ tournament class, we propose a very general and flexible parametric pairwise preference model called the local-global model which subsumes the popular Bradley-Terry-Luce/Thurstone classes to capture locally cyclic as well as globally acyclic preference relations. |
Vishnu Veerathu; Arun Rajkumar; | |
924 | SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perceptron (MLP) decoders. |
Enze Xie; Wenhai Wang; Zhiding Yu; Anima Anandkumar; Jose M. Alvarez; Ping Luo; | |
925 | Fairness Via Representation Neutralization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new mitigation technique, namely, Representation Neutralization for Fairness (RNF) that achieves fairness by debiasing only the task-specific classification head of DNN models. |
Mengnan Du; Subhabrata Mukherjee; Guanchu Wang; Ruixiang Tang; Ahmed Awadallah; Xia Hu; | |
926 | Residual Relaxation for Multi-view Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we notice that some other useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift that is too large to be aligned well. |
Yifei Wang; Zhengyang Geng; Feng Jiang; Chuming Li; Yisen Wang; Jiansheng Yang; Zhouchen Lin; | |
927 | Do Vision Transformers See Like Convolutional Neural Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more uniform representations across all layers. |
Maithra Raghu; Thomas Unterthiner; Simon Kornblith; Chiyuan Zhang; Alexey Dosovitskiy; | |
928 | Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the complementary problem of learning to coarsen graphs for a multigrid solver, a necessary step in developing fully learnable AMG methods. |
Ali Taghibakhshi; Scott MacLachlan; Luke Olson; Matthew West; | |
929 | Delayed Propagation Transformer: A Universal Computation Engine Towards Practical Control in Cyber-Physical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the Delayed Propagation Transformer (DePT), a new transformer-based model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world. |
Wenqing Zheng; Qiangqiang Guo; Hao Yang; Peihao Wang; Zhangyang Wang; | code |
930 | Explaining Latent Representations with A Corpus of Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To that aim, we propose SimplEx: a user-centred method that provides example-based explanations with reference to a freely selected set of examples, called the corpus. |
Jonathan Crabbe; Zhaozhi Qian; Fergus Imrie; Mihaela van der Schaar; | |
931 | Explaining Heterogeneity in Medial Entorhinal Cortex with Task-driven Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: How should the response profiles of these more heterogeneous cells be described, and how do they contribute to behavior?In this work, we took a computational approach to addressing these questions. |
Aran Nayebi; Alexander Attinger; Malcolm Campbell; Kiah Hardcastle; Isabel Low; Caitlin Mallory; Gabriel Mel; Ben Sorscher; Alex Williams; Surya Ganguli; Lisa Giocomo; Dan Yamins; | |
932 | Beyond Smoothness: Incorporating Low-Rank Analysis Into Nonparametric Density Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we investigate the theoretical implications of incorporating a multi-view latent variable model, a type of low-rank model, into nonparametric density estimation. |
Robert A. Vandermeulen; Antoine Ledent; | |
933 | Multi-View Representation Learning Via Total Correlation Objective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a variational approach which casts MVRL as maximizing the amount of total correlation reduced by the representation, aiming to learn a shared latent representation that is informative yet succinct to capture the correlation among multiple views. |
HyeongJoo Hwang; Geon-Hyeong Kim; Seunghoon Hong; Kee-Eung Kim; | |
934 | FACMAC: Factored Multi-Agent Centralised Policy Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. |
Bei Peng; Tabish Rashid; Christian Schroeder de Witt; Pierre-Alexandre Kamienny; Philip Torr; Wendelin Boehmer; Shimon Whiteson; | |
935 | EDGE: Explaining Deep Reinforcement Learning Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel self-explainable model that augments a Gaussian process with a customized kernel function and an interpretable predictor. |
Wenbo Guo; Xian Wu; Usmann Khan; Xinyu Xing; | |
936 | Learning to Assimilate in Chaotic Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a self-supervised framework, which we call \textit{amortized assimilation}, for learning to assimilate in dynamical systems. |
John McCabe; Jed Brown; | |
937 | Object-aware Contrastive Learning for Debiased Scene Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the issue, we develop a novel object-aware contrastive learning framework that first (a) localizes objects in a self-supervised manner and then (b) debias scene correlations via appropriate data augmentations considering the inferred object locations. |
Sangwoo Mo; Hyunwoo Kang; Kihyuk Sohn; Chun-Liang Li; Jinwoo Shin; | code |
938 | Evaluating Efficient Performance Estimators of Neural Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct an extensive and organized assessment of OSEs and ZSEs on five NAS benchmarks: NAS-Bench-101/201/301, and NDS ResNet/ResNeXt-A. |
Xuefei Ning; Changcheng Tang; Wenshuo Li; Zixuan Zhou; Shuang Liang; Huazhong Yang; Yu Wang; | code |
939 | A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to learn a generative neural body model from unlabelled monocular videos by extending Neural Radiance Fields (NeRFs). |
Shih-Yang Su; Frank Yu; Michael Zollhoefer; Helge Rhodin; | |
940 | Differential Privacy Over Riemannian Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we consider the problem of releasing a differentially private statistical summary that resides on a Riemannian manifold. |
Matthew Reimherr; Karthik Bharath; Carlos Soto; | |
941 | How Can Classical Multidimensional Scaling Go Wrong? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive a formula, based on the eigenvalues of a matrix obtained from $D$, for the Frobenius norm of the difference between $D$ and the metric $D_{\text{cmds}}$ returned by cMDS. |
Rishi Sonthalia; Greg Van Buskirk; Benjamin Raichel; Anna Gilbert; | |
942 | Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph. |
Yushi Bai; Zhitao Ying; Hongyu Ren; Jure Leskovec; | |
943 | Non-asymptotic Error Bounds for Bidirectional GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive nearly sharp bounds for the bidirectional GAN (BiGAN) estimation error under the Dudley distance between the latent joint distribution and the data joint distribution with appropriately specified architecture of the neural networks used in the model. |
Shiao Liu; Yunfei Yang; Jian Huang; Yuling Jiao; Yang Wang; | |
944 | Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a general framework to learn from demonstrations with varying optimality that jointly learns the confidence score and a well-performing policy. |
Songyuan Zhang; ZHANGJIE CAO; Dorsa Sadigh; Yanan Sui; | |
945 | Answering Complex Causal Queries With The Maximum Causal Set Effect Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article proposes a framework for parameterizing such complex causal queries as the maximum difference in causal effects associated with two sets of causal variables that have a researcher specified probability of occurring. |
Zachary Markovich; | |
946 | Identifiability in Inverse Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a resolution to this non-identifiability for problems with entropy regularization. |
Haoyang Cao; Samuel Cohen; Lukasz Szpruch; | |
947 | A Probabilistic State Space Model for Joint Inference from Differential Equations and Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recent work in probabilistic numerics has developed a new class of solvers for ordinary differential equations (ODEs) that phrase the solution process directly in terms of Bayesian filtering. We here show that this allows such methods to be combined very directly, with conceptual and numerical ease, with latent force models in the ODE itself. |
Jonathan Schmidt; Nicholas Kr�mer; Philipp Hennig; | |
948 | On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we show that, when using weight decay, weights in successive layers of a deep network may become "mutually frozen". |
Julian Zilly; Alessandro Achille; Andrea Censi; Emilio Frazzoli; | |
949 | Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new class of attacks named action poisoning attacks, where an adversary can change the action signal selected by the agent. |
Guanlin Liu; Lifeng LAI; | |
950 | Fast Approximation of The Sliced-Wasserstein Distance Using Concentration of Random Projections Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We adopt a new perspective to approximate SW by making use of the concentration of measure phenomenon: under mild assumptions, one-dimensional projections of a high-dimensional random vector are approximately Gaussian. |
Kimia Nadjahi; Alain Durmus; Pierre E. Jacob; Roland Badeau; Umut Simsekli; | |
951 | Causal Navigation By Continuous-time Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a theoretical and experimental framework for learning causal representations using continuous-time neural networks, specifically over their discrete-time counterparts. |
Charles Vorbach; Ramin Hasani; Alexander Amini; Mathias Lechner; Daniela Rus; | |
952 | Global Convergence of Online Optimization for Nonlinear Model Predictive Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a real-time iteration (RTI) scheme for solving online optimization problem appeared in nonlinear optimal control. |
Sen Na; | |
953 | Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces two extensions of flows and diffusion for categorical data such as language or image segmentation: Argmax Flows and Multinomial Diffusion. |
Emiel Hoogeboom; Didrik Nielsen; Priyank Jaini; Patrick Forr�; Max Welling; | |
954 | Learning with User-Level Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. |
Daniel Levy; Ziteng Sun; Kareem Amin; Satyen Kale; Alex Kulesza; Mehryar Mohri; Ananda Theertha Suresh; | |
955 | Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. |
Tianshi Cao; Alex Bie; Arash Vahdat; Sanja Fidler; Karsten Kreis; | |
956 | Keeping Your Eye on The Ball: Trajectory Attention in Video Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new drop-in block for video transformers – trajectory attention – that aggregates information along implicitly determined motion paths. |
Mandela Patrick; Dylan Campbell; Yuki Asano; Ishan Misra; Florian Metze; Christoph Feichtenhofer; Andrea Vedaldi; Jo�o F. Henriques; | |
957 | Variational Bayesian Optimistic Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider online sequential decision problems where an agent must balance exploration and exploitation. |
Brendan O'Donoghue; Tor Lattimore; | |
958 | Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider a more cost-efficient setting of visual-input sim-to-real where only low-dimensional states are simulated. |
Xiong-Hui Chen; Shengyi Jiang; Feng Xu; Zongzhang Zhang; Yang Yu; | |
959 | D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes Diffusion-Decoding models with Contrastive representations (D2C), a paradigm for training unconditional variational autoencoders (VAE) for few-shot conditional image generation. |
Abhishek Sinha; Jiaming Song; Chenlin Meng; Stefano Ermon; | code |
960 | Continual Auxiliary Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate a reinforcement learning system designed to learn a collection of auxiliary tasks, with a behavior policy learning to take actions to improve those auxiliary predictions. |
Matthew McLeod; Chunlok Lo; Matthew Schlegel; Andrew Jacobsen; Raksha Kumaraswamy; Martha White; Adam White; | |
961 | Constrained Two-step Look-Ahead Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a computationally efficient two-step lookahead constrained Bayesian optimization acquisition function (2-OPT-C) supporting both sequential and batch settings. |
Yunxiang Zhang; Xiangyu Zhang; Peter Frazier; | |
962 | Learning with Labeling Induced Abstentions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a formalization of this setting, and give an algorithm that simultaneously learns a model and decides when to request a label by leveraging ideas from both the abstention and active learning literatures. |
Kareem Amin; Giulia DeSalvo; Afshin Rostamizadeh; | |
963 | SQALER: Scaling Question Answering By Decoupling Multi-Hop and Logical Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this issue by showing that multi-hop and more complex logical reasoning can be accomplished separately without losing expressive power. |
Mattia Atzeni; Jasmina Bogojeska; Andreas Loukas; | |
964 | Out-of-Distribution Generalization in Kernel Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present applications of our theory to real and synthetic datasets and for many kernels. |
Abdulkadir Canatar; Blake Bordelon; Cengiz Pehlevan; | |
965 | FL-WBC: Enhancing Robustness Against Model Poisoning Attacks in Federated Learning from A Client Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a client-based defense, named White Blood Cell for Federated Learning (FL-WBC), which can mitigate model poisoning attacks that have already polluted the global model. |
Jingwei Sun; Ang Li; Louis DiValentin; Amin Hassanzadeh; Yiran Chen; Hai Li; | |
966 | Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for The Weighted Majority Vote Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new second-order oracle bound for the expected risk of a weighted majority vote. |
Yi-Shan Wu; Andres Masegosa; Stephan Lorenzen; Christian Igel; Yevgeny Seldin; | |
967 | A Multi-Implicit Neural Representation for Fonts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the observation that complex fonts can be represented by a superposition of a set of simpler occupancy functions, we introduce multi-implicits to represent fonts as a permutation-invariant set of learned implict functions, without losing features (e.g., edges and corners). |
Pradyumna Reddy; Zhifei Zhang; Matthew Fisher; Hailin Jin; Zhaowen Wang; Niloy Mitra; | |
968 | OctField: Hierarchical Implicit Functions for 3D Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a learnable hierarchical implicit representation for 3D surfaces, coded OctField, that allows high-precision encoding of intricate surfaces with low memory and computational budget. |
Jia-Heng Tang; Weikai Chen; jie Yang; Bo Wang; Songrun Liu; Bo Yang; Lin Gao; | |
969 | The Inductive Bias of Quantum Kernels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work, we analyze function classes defined via quantum kernels. |
Jonas K�bler; Simon Buchholz; Bernhard Sch�lkopf; | |
970 | An Exponential Improvement on The Memorization Capacity of Deep Threshold Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we improve the dependence on $\delta$ from exponential to almost linear, proving that $\widetilde{\mathcal{O}}(\frac{1}{\delta}+\sqrt{n})$ neurons and $\widetilde{\mathcal{O}}(\frac{d}{\delta}+n)$ weights are sufficient. |
Shashank Rajput; Kartik Sreenivasan; Dimitris Papailiopoulos; Amin Karbasi; | |
971 | Pretraining Representations for Data-Efficient Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. |
Max Schwarzer; Nitarshan Rajkumar; Michael Noukhovitch; Ankesh Anand; Laurent Charlin; R Devon Hjelm; Philip Bachman; Aaron C. Courville; | |
972 | Universal Approximation Using Well-Conditioned Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that any log-concave distribution can be approximated using well-conditioned affine-coupling flows. |
Holden Lee; Chirag Pabbaraju; Anish Prasad Sevekari; Andrej Risteski; | |
973 | On The Validity of Modeling SGD with Stochastic Differential Equations (SDEs) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The current paper clarifies the picture with the following contributions: (a) An efficient simulation algorithm SVAG that provably converges to the conventionally used Itô SDE approximation. (b) A theoretically motivated testable necessary condition for the SDE approximation and its most famous implication, the linear scaling rule (Goyal et al., 2017), to hold. |
Zhiyuan Li; Sadhika Malladi; Sanjeev Arora; | |
974 | Proportional Participatory Budgeting with Additive Utilities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study voting rules for participatory budgeting, where a group of voters collectively decides which projects should be funded using a common budget. |
Grzegorz Pierczynski; Piotr Skowron; Dominik Peters; | |
975 | Disentangling The Roles of Curation, Data-Augmentation and The Prior in The Cold Posterior Effect Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we provide novel and nuanced evidence relevant to existing explanations for the cold posterior effect, disentangling three hypotheses: 1. |
Lorenzo Noci; Kevin Roth; Gregor Bachmann; Sebastian Nowozin; Thomas Hofmann; | |
976 | Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win The Jackpot? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reconcile such, we revisit the definition of lottery ticket hypothesis, with comprehensive and more rigorous conditions. Under our new definition, we show concrete evidence to clarify whether the winning ticket exists across the major DNN architectures and/or applications. |
Xiaolong Ma; Geng Yuan; Xuan Shen; Tianlong Chen; Xuxi Chen; Xiaohan Chen; Ning Liu; Minghai Qin; Sijia Liu; Zhangyang Wang; Yanzhi Wang; | code |
977 | Collaborative Causal Discovery with Atomic Interventions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new Collaborative Causal Discovery problem, through which we model a common scenario in which we have multiple independent entities each with their own causal graph, and the goal is to simultaneously learn all these causal graphs. |
Raghavendra Addanki; Shiva Kasiviswanathan; | |
978 | Towards Optimally Abstaining from Prediction with OOD Test Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider a model where one may abstain from predicting, at a fixed cost. |
Adam Kalai; Varun Kanade; | |
979 | TokenLearner: Adaptive Space-Time Tokenization for Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. |
Michael Ryoo; AJ Piergiovanni; Anurag Arnab; Mostafa Dehghani; Anelia Angelova; | |
980 | Learning in Multi-Stage Decentralized Matching Markets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an efficient algorithm, built upon concepts of "lower uncertainty bound" and "calibrated decentralized matching," for maximizing the participants’ expected payoff. |
Xiaowu Dai; Michael Jordan; | |
981 | Non-asymptotic Convergence Bounds for Wasserstein Approximation Using Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide explicit upper bounds for the convergence speed of this Lloyd-type algorithm, starting from a cloud of points sufficiently far from each other. |
Quentin M�rigot; Filippo Santambrogio; Cl�ment SARRAZIN; | |
982 | Understanding Interlocking Dynamics of Cooperative Rationalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we reveal a major problem with such cooperative rationalization paradigm — model interlocking. |
Mo Yu; Yang Zhang; Shiyu Chang; Tommi Jaakkola; | |
983 | Adversarial Robustness Without Adversarial Training: A Teacher-Guided Curriculum Learning Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a non-iterative method that enforces the following ideas during training. |
Anindya Sarkar; Anirban Sarkar; Sowrya Gali; Vineeth N Balasubramanian; | |
984 | Tactical Optimism and Pessimism for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that the most effective degree of optimism can vary both across tasks and over the course of learning. |
Ted Moskovitz; Jack Parker-Holder; Aldo Pacchiano; Michael Arbel; Michael Jordan; | |
985 | Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design hyperparameter-free algorithms for policy selection based on BVFT [XJ21], a recent theoretical advance in value-function selection, and demonstrate their effectiveness in discrete-action benchmarks such as Atari. |
Siyuan Zhang; Nan Jiang; | |
986 | FjORD: Fair and Accurate Federated Learning Under Heterogeneous Targets with Ordered Dropout Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce Ordered Dropout, a mechanism that achieves an ordered, nested representation of knowledge in Neural Networks and enables the extraction of lower footprint submodels without the need for retraining. |
Samuel Horv�th; Stefanos Laskaridis; Mario Almeida; Ilias Leontiadis; Stylianos Venieris; Nicholas Lane; | |
987 | Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we establish an $\Omega(H^2 S/d_m\epsilon^2)$ lower bound (over model-based family) for the global uniform OPE and our main result establishes an upper bound of $\tilde{O}(H^2/d_m\epsilon^2)$ for the \emph{local} uniform convergence that applies to all \emph{near-empirically optimal} policies for the MDPs with \emph{stationary} transition. |
Ming Yin; Yu-Xiang Wang; | |
988 | MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the power of Seq2seq and its variants on the modeling of time series data, we propose Mixture of Seq2seq (MixSeq), an end2end mixture model to cluster microscopic time series, where all the components come from a family of Seq2seq models parameterized by different parameters. |
Zhibo Zhu; Ziqi Liu; Ge Jin; Zhiqiang Zhang; Lei Chen; Jun Zhou; Jianyong Zhou; | |
989 | Pareto Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we rethink the optimization scheme for DA from a gradient-based perspective. |
fangrui lv; Jian Liang; Kaixiong Gong; Shuang Li; Chi Liu; Han Li; Di Liu; Guoren Wang; | |
990 | Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We establish non-asymptotic bounds on the sample complexity of divergence frontiers. |
Lang Liu; Krishna Pillutla; Sean Welleck; Sewoong Oh; Yejin Choi; Zaid Harchaoui; | |
991 | Consistency Regularization for Variational Auto-Encoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a regularization method to enforce consistency in VAEs. |
Samarth Sinha; Adji Bousso Dieng; | |
992 | Score-based Generative Neural Networks for Large-Scale Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel framework for learning the Sinkhorn coupling between two distributions in the form of a score-based generative model. |
Grady Daniels; Tyler Maunu; Paul Hand; | |
993 | Interactive Label Cleaning with Example-based Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose CINCER, a novel approach that cleans both new and past data by identifying \emph{pairs of mutually incompatible examples}. |
Stefano Teso; Andrea Bontempelli; Fausto Giunchiglia; Andrea Passerini; | |
994 | Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The current paper is able to establish this global optimality for two-layer Leaky ReLU nets trained with gradient flow on linearly separable and symmetric data, regardless of the width. |
Kaifeng Lyu; Zhiyuan Li; Runzhe Wang; Sanjeev Arora; | |
995 | Glance-and-Gaze Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new vision Transformer, named Glance-and-Gaze Transformer (GG-Transformer), to address the aforementioned issues. |
Qihang Yu; Yingda Xia; Yutong Bai; Yongyi Lu; Alan L. Yuille; Wei Shen; | |
996 | Stochastic $L^\natural$-convex Function Minimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study an extension of the stochastic submodular minimization problem, namely, the stochastic $L^\natural$-convex minimization problem. |
Haixiang Zhang; Zeyu Zheng; Javad Lavaei; | |
997 | Self-Supervised GANs with Label Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel self-supervised GAN that unifies the GAN task with the self-supervised task by augmenting the GAN labels (real or fake) via self-supervision of data transformation. |
Liang Hou; Huawei Shen; Qi Cao; Xueqi Cheng; | |
998 | Shape As Points: A Differentiable Poisson Solver Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) which allows for a GPU-accelerated fast solution of the indicator function given an oriented point cloud. |
Songyou Peng; Chiyu Jiang; Yiyi Liao; Michael Niemeyer; Marc Pollefeys; Andreas Geiger; | |
999 | Outcome-Driven Reinforcement Learning Via Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we view reinforcement learning as inferring policies that achieve desired outcomes, rather than as a problem of maximizing rewards. |
Tim G. J. Rudner; Vitchyr Pong; Rowan McAllister; Yarin Gal; Sergey Levine; | |
1000 | Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found Within Randomly Initialized Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: \textbf{Interestingly, we discover for the first time that there exist subnetworks with inborn robustness, matching or surpassing the robust accuracy of the adversarially trained networks with comparable model sizes, within randomly initialized networks without any model training}, indicating that adversarial training on model weights is not indispensable towards adversarial robustness. |
Yonggan Fu; Qixuan Yu; Yang Zhang; Shang Wu; Xu Ouyang; David Cox; Yingyan Lin; | |
1001 | Rectifying The Shortcut Learning of Background for Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. |
Xu Luo; Longhui Wei; Liangjian Wen; Jinrong Yang; Lingxi Xie; Zenglin Xu; Qi Tian; | |
1002 | SEAL: Self-supervised Embodied Active Learning Using Exploration and 3D Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how we can build upon the data and models of Internet images and use them to adapt to robot vision without requiring any extra labels. |
Devendra Singh Chaplot; Murtaza Dalal; Saurabh Gupta; Jitendra Malik; Russ R. Salakhutdinov; | |
1003 | Sifting Through The Noise: Universal First-order Methods for Stochastic Variational Inequalities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We examine a flexible algorithmic framework for solving monotone variational inequalities in the presence of randomness and uncertainty. |
Kimon Antonakopoulos; Thomas Pethick; Ali Kavis; Panayotis Mertikopoulos; Volkan Cevher; | |
1004 | Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we consider multi-objective reinforcement learning where the objectives are balanced using preferences. |
Jingfeng Wu; Vladimir braverman; Lin Yang; | |
1005 | Exact Privacy Guarantees for Markov Chain Implementations of The Exponential Mechanism with Artificial Atoms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we use tools from ergodic theory and perfect simulation to design exact finite runtime sampling algorithms for the exponential mechanism by introducing an intermediate modified target distribution using artificial atoms. |
Jeremy Seeman; Matthew Reimherr; Aleksandra Slavkovic; | |
1006 | The Emergence of Objectness: Learning Zero-shot Segmentation from Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this, we develop a zero-shot unsupervised approach for learning object segmentations. |
Runtao Liu; Zhirong Wu; Stella Yu; Stephen Lin; | |
1007 | Direct Multi-view Multi-person 3D Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. |
tao wang; Jianfeng Zhang; Yujun Cai; Shuicheng Yan; Jiashi Feng; | |
1008 | MST: Masked Self-Supervised Transformer for Visual Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel Masked Self-supervised Transformer approach named MST, which can explicitly capture the local context of an image while preserving the global semantic information. |
Zhaowen Li; Zhiyang Chen; Fan Yang; Wei Li; Yousong Zhu; Chaoyang Zhao; Rui Deng; Liwei Wu; Rui Zhao; Ming Tang; Jinqiao Wang; | |
1009 | Exploiting Opponents Under Utility Constraints in Sequential Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the problem of designing artificial agents that learn how to effectively exploit unknown human opponents while playing repeatedly against them in an online fashion. |
Martino Bernasconi-de-Luca; Federico Cacciamani; Simone Fioravanti; Nicola Gatti; Alberto Marchesi; Francesco Trov�; | |
1010 | A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show how complex inference scenarios for these models that commonly arise in machine learning—from computing the expectations of decision tree ensembles to information-theoretic divergences of sum-product networks—can be represented in terms of tractable modular operations over circuits. |
Antonio Vergari; YooJung Choi; Anji Liu; Stefano Teso; Guy Van den Broeck; | |
1011 | Demystifying and Generalizing BinaryConnect Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We attempt to close this gap in four different aspects: (a) we show that existing quantization algorithms, including post-training quantization, are surprisingly similar to each other; (b) we argue for proximal maps as a natural family of quantizers that is both easy to design and analyze; (c) we refine the observation that BC is a special case of dual averaging, which itself is a special case of the generalized conditional gradient algorithm; (d) consequently, we propose ProxConnect (PC) as a generalization of BC and we prove its convergence properties by exploiting the established connections. |
Tim Dockhorn; Yaoliang Yu; Eyy�b Sari; Mahdi Zolnouri; Vahid Partovi Nia; | |
1012 | CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose CARMS, an unbiased estimator for categorical random variables based on multiple mutually negatively correlated (jointly antithetic) samples. |
Alek Dimitriev; Mingyuan Zhou; | |
1013 | Learning to Learn Dense Gaussian Processes for Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to learn Gaussian processes with dense inducing variables by meta-learning for few-shot learning. |
Ze Wang; Zichen Miao; Xiantong Zhen; Qiang Qiu; | |
1014 | Stochastic Solutions for Linear Inverse Problems Using The Prior Implicit in A Denoiser Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Two recent lines of work – Denoising Score Matching and Plug-and-Play – propose methodologies for drawing samples from this implicit prior and using it to solve inverse problems, respectively. Here, we develop a parsimonious and robust generalization of these ideas. |
Zahra Kadkhodaie; Eero Simoncelli; | |
1015 | Towards Stable and Robust AdderNets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To enhance the stability and robustness of AdderNets, we first thoroughly analyze the variance estimation of weight parameters and output features of an arbitrary adder layer. Then, we develop a weight normalization scheme for adaptively optimizing the weight distribution of AdderNets during the training procedure, which can reduce the perturbation on running mean and variance in batch normalization layers. |
Minjing Dong; Yunhe Wang; Xinghao Chen; Chang Xu; | |
1016 | Representing Long-Range Context for Graph Neural Networks with Global Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the use of Transformer-based self-attention to learn long-range pairwise relationships, with a novel “readout” mechanism to obtain a global graph embedding. |
Paras Jain; Zhanghao Wu; Matthew Wright; Azalia Mirhoseini; Joseph E. Gonzalez; Ion Stoica; | code |
1017 | Beyond Bandit Feedback in Online Multiclass Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of online multiclass classification in a setting where the learner’s feedback is determined by an arbitrary directed graph. |
Dirk van der Hoeven; Federico Fusco; Nicol� Cesa-Bianchi; | |
1018 | Learning Student-Friendly Teacher Networks for Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. |
Dae Young Park; Moon-Hyun Cha; changwook jeong; Daesin Kim; Bohyung Han; | |
1019 | Implicit Transformer Network for Screen Content Image Continuous Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel Implicit Transformer Super-Resolution Network (ITSRN) for SCISR. |
Jingyu Yang; Sheng Shen; Huanjing Yue; Kun Li; | |
1020 | Channel Permutations for N:M Sparsity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce channel permutations as a method to maximize the accuracy of N:M sparse networks. |
Jeff Pool; Chong Yu; | code |
1021 | Curriculum Learning for Vision-and-Language Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we propose a novel curriculum- based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. |
Jiwen Zhang; zhongyu wei; Jianqing Fan; Jiajie Peng; | |
1022 | Better Algorithms for Individually Fair $k$-Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, our main contribution is to use Linear Programming (LP) techniques to obtain better algorithms for this problem, both in theory and in practice. |
Maryam Negahbani; Deeparnab Chakrabarty; | |
1023 | Video Instance Segmentation Using Inter-Frame Communication Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel end-to-end solution for video instance segmentation (VIS) based on transformers. |
Sukjun Hwang; Miran Heo; Seoung Wug Oh; Seon Joo Kim; | code |
1024 | Progressive Coordinate Transforms for Monocular 3D Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel and lightweight approach, dubbed {\em Progressive Coordinate Transforms} (PCT) to facilitate learning coordinate representations. |
Li Wang; Li Zhang; Yi Zhu; Zhi Zhang; Tong He; Mu Li; Xiangyang Xue; | |
1025 | Structured Reordering for Modeling Latent Alignments in Sequence Transduction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an efficient dynamic programming algorithm performing exact marginal inference of separable permutations, and, thus, enabling end-to-end differentiable training of our model. |
bailin wang; Mirella Lapata; Ivan Titov; | |
1026 | A Universal Probabilistic Spike Count Model Reveals Ongoing Modulation of Neural Variability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we present a universal probabilistic spike count model that eliminates these shortcomings. |
David Liu; Mate Lengyel; | |
1027 | Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper advances our understanding of this fundamental question by introducing a new complexity measure-Bellman Eluder (BE) dimension. |
Chi Jin; Qinghua Liu; Sobhan Miryoosefi; | |
1028 | Detecting Anomalous Event Sequences with Temporal Point Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we frame the problem of detecting anomalous continuous-time event sequences as out-of-distribution (OOD) detection for temporal point processes (TPPs). |
Oleksandr Shchur; Ali Caner Turkmen; Tim Januschowski; Jan Gasthaus; Stephan G�nnemann; | |
1029 | HNPE: Leveraging Global Parameters for Neural Posterior Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present hierarchical neural posterior estimation (HNPE), a novel method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters. |
Pedro Luiz Coelho Rodrigues; Thomas Moreau; Gilles Louppe; Alexandre Gramfort; | |
1030 | Alignment Attention By Matching Key and Query Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces alignment attention that explicitly encourages self-attention to match the distributions of the key and query within each head. |
Shujian Zhang; Xinjie Fan; Huangjie Zheng; Korawat Tanwisuth; Mingyuan Zhou; | |
1031 | Settling The Variance of Multi-Agent Policy Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we offer a rigorous analysis of MAPG methods by, firstly, quantifying the contributions of the number of agents and agents’ explorations to the variance of MAPG estimators. |
Jakub Kuba; Muning Wen; Linghui Meng; shangding gu; Haifeng Zhang; David Mguni; Jun Wang; Yaodong Yang; | |
1032 | For High-dimensional Hierarchical Models, Consider Exchangeability of Effects Across Covariates Instead of Across Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a hierarchical model expressing our alternative perspective. |
Brian Trippe; Hilary Finucane; Tamara Broderick; | |
1033 | Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present polynomial time and sample efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, under mild non-degeneracy assumptions. |
Pranjal Awasthi; Alex Tang; Aravindan Vijayaraghavan; | |
1034 | Controllable and Compositional Generation with Latent-Space Energy-Based Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use energy-based models (EBMs) to handle compositional generation over a set of attributes. |
Weili Nie; Arash Vahdat; Anima Anandkumar; | |
1035 | Reverse-Complement Equivariant Networks for DNA Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we close this gap by characterizing the set of all linear RC-equivariant layers, and show in particular that new architectures exist beyond the ones already explored. |
Vincent Mallet; Jean-Philippe Vert; | |
1036 | Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider two popular limited adaptivity models: the batch learning model and the rare policy switch model, and propose two efficient online RL algorithms for episodic linear Markov decision processes, where the transition probability and the reward function can be represented as a linear function of some known feature mapping. |
Tianhao Wang; Dongruo Zhou; Quanquan Gu; | |
1037 | Nonsmooth Implicit Differentiation for Machine-Learning and Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. |
J�r�me Bolte; Tam Le; Edouard Pauwels; Tony Silveti-Falls; | |
1038 | Heuristic-Guided Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a framework to accelerate reinforcement learning (RL) algorithms by heuristics that are constructed by domain knowledge or offline data. |
Ching-An Cheng; Andrey Kolobov; Adith Swaminathan; | |
1039 | Statistical Undecidability in Linear, Non-Gaussian Causal Models in The Presence of Latent Confounders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper refines these results: although it is possible to converge to the right orientation in the limit, causal orientation is no longer statistically decidable—it is not possible to converge to the correct orientation with finite-sample bounds on the probability of orientation errors, even if faithfulness is satisfied. |
Konstantin Genin; | |
1040 | A Novel Notion of Barycenter for Probability Distributions Based on Optimal Weak Mass Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce weak barycenters of a family of probability distributions, based on the recently developed notion of optimal weak transport of mass by Gozlan et al. (2017) and Backhoff-Veraguas et al. (2020). |
Elsa Cazelles; Felipe Tobar; Joaquin Fontbona; | |
1041 | Temporal-attentive Covariance Pooling Networks for Video Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, this paper proposes a Temporal-attentive Covariance Pooling (TCP), inserted at the end of deep architectures, to produce powerful video representations. |
Zilin Gao; Qilong Wang; Bingbing Zhang; Qinghua Hu; Peihua Li; | |
1042 | Revisiting Smoothed Online Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit the problem of smoothed online learning, in which the online learner suffers both a hitting cost and a switching cost, and target two performance metrics: competitive ratio and dynamic regret with switching cost. |
Lijun Zhang; Wei Jiang; Shiyin Lu; Tianbao Yang; | |
1043 | Marginalised Gaussian Processes with Nested Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes nested sampling as a means of marginalising kernel hyperparameters, because it is a technique that is well-suited to exploring complex, multi-modal distributions. |
Fergus Simpson; Vidhi Lalchand; Carl Edward Rasmussen; | |
1044 | Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a newoffline actor-critic algorithm that naturally incorporates the pessimism principle, leading to several key advantages compared to the state of the art. |
Andrea Zanette; Martin J. Wainwright; Emma Brunskill; | |
1045 | Bayesian Bellman Operators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we use BBO to provide a rigorous theoretical analysis of model-free Bayesian RL to better understand its relationship to established frequentist RL methodologies. |
Mattie Fellows; Kristian Hartikainen; Shimon Whiteson; | |
1046 | Uncertainty Calibration for Ensemble-Based Debiasing Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the bias-only model in these ensemble-based methods, which plays an important role but has not gained much attention in the existing literature. |
Ruibin Xiong; Yimeng Chen; Liang Pang; Xueqi Cheng; Zhi-Ming Ma; Yanyan Lan; | |
1047 | Provably Faster Algorithms for Bilevel Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose two new algorithms for bilevel optimization, where the first algorithm adopts momentum-based recursive iterations, and the second algorithm adopts recursive gradient estimations in nested loops to decrease the variance. |
Junjie Yang; Kaiyi Ji; Yingbin Liang; | |
1048 | Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for link prediction. |
Seongjun Yun; Seoyoon Kim; Junhyun Lee; Jaewoo Kang; Hyunwoo J. Kim; | |
1049 | Self-Supervised Multi-Object Tracking with Cross-input Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a self-supervised learning procedure for training a robust multi-object tracking (MOT) model given only unlabeled video. |
Favyen Bastani; Songtao He; Samuel Madden; | |
1050 | Tree in Tree: from Decision Trees to Decision Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces Tree in Tree decision graph (TnT), a framework that extends the conventional decision tree to a more generic and powerful directed acyclic graph. |
Bingzhao Zhu; Mahsa Shoaran; | |
1051 | Test-time Collective Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore a decentralized mechanism to make collective predictions at test time, that is inspired by the literature in social science on human consensus-making. |
Celestine Mendler-D�nner; Wenshuo Guo; Stephen Bates; Michael Jordan; | |
1052 | A Continuous Mapping For Augmentation Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using this mapping, we take a novel approach where 1) we pose the ADA as a continuous optimization problem over the parameters of the augmentation distribution; and 2) use Stochastic Gradient Langevin Dynamics to learn and sample augmentations. |
Keyu Tian; Chen Lin; Ser Nam Lim; Wanli Ouyang; Puneet Dokania; Philip Torr; | |
1053 | Neural Routing By Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proffers a simple yet effective idea of constructing parallel procedures and assigning similar intermediate features to the same specialized procedures in a divide-and-conquer fashion. |
Kaipeng Zhang; Zhenqiang Li; Zhifeng Li; Wei Liu; Yoichi Sato; | |
1054 | GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose GeoMol — an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate distributions of low-energy molecular 3D conformers. |
Octavian Ganea; Lagnajit Pattanaik; Connor Coley; Regina Barzilay; Klavs Jensen; William Green; Tommi Jaakkola; | |
1055 | CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to combine the benefits of communication compression and convergence acceleration, we propose a \emph{compressed and accelerated} gradient method based on ANITA [20] for distributed optimization, which we call CANITA. |
Zhize Li; Peter Richtarik; | |
1056 | Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the problem of sequence-to-sequence alignment for signals containing outliers. |
Nikita Dvornik; Isma Hadji; Konstantinos G. Derpanis; Animesh Garg; Allan Jepson; | |
1057 | Safe Reinforcement Learning with Natural Language Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose learning to interpret natural language constraints for safe RL. |
Tsung-Yen Yang; Michael Hu; Yinlam Chow; Peter J. Ramadge; Karthik Narasimhan; | |
1058 | Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel, domain-agnostic approach to tackling this problem, using compositions of physics-informed random features, derived from ordinary differential equations. |
Thomas McDonald; Mauricio Alvarez; | |
1059 | Implicit Semantic Response Alignment for Partial Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Implicit Semantic Response Alignment to explore the intrinsic relationships among different categories by applying a weighted schema on the feature level. |
Wenxiao Xiao; Zhengming Ding; Hongfu Liu; | |
1060 | ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an effective Task-oriented Alignment (ToAlign) for unsupervised domain adaptation (UDA). |
Guoqiang Wei; Cuiling Lan; Wenjun Zeng; Zhizheng Zhang; Zhibo Chen; | code |
1061 | Prior-independent Dynamic Auctions for A Value-maximizing Buyer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study prior-independent dynamic auction design with production costs for a value-maximizing buyer, a paradigm that is becoming prevalent recently following the development of automatic bidding algorithms in advertising platforms. |
Yuan Deng; Hanrui Zhang; | |
1062 | Safe Reinforcement Learning By Imagining The Near Future Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. |
Garrett Thomas; Yuping Luo; Tengyu Ma; | |
1063 | Contrastive Active Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a contrastive objective for active inference that strongly reduces the computational burden in learning the agent’s generative model and planning future actions. |
Pietro Mazzaglia; Tim Verbelen; Bart Dhoedt; | |
1064 | Overparameterization Improves Robustness to Covariate Shift in High Dimensions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine the exact high-dimensional asymptotics of random feature regression under covariate shift and present a precise characterization of the limiting test error, bias, and variance in this setting. |
Nilesh Tripuraneni; Ben Adlam; Jeffrey Pennington; | |
1065 | Logarithmic Regret in Feature-based Dynamic Pricing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit this problem and provide two algorithms (EMLP and ONSP) for stochastic and adversarial feature settings, respectively, and prove the optimal $O(d\log{T})$ regret bounds for both. |
Jianyu Xu; Yu-Xiang Wang; | |
1066 | Dimension-free Empirical Entropy Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We seek an entropy estimator for discrete distributions with fully empirical accuracy bounds. |
Doron Cohen; Aryeh Kontorovich; Aaron Koolyk; Geoffrey Wolfer; | |
1067 | Towards Biologically Plausible Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose instead to add lateral connectivity to a locally connected network, and allow learning via Hebbian plasticity. |
Roman Pogodin; Yash Mehta; Timothy Lillicrap; Peter Latham; | |
1068 | DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input. |
Yongming Rao; Wenliang Zhao; Benlin Liu; Jiwen Lu; Jie Zhou; Cho-Jui Hsieh; | code |
1069 | Learning Transferable Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we, therefore, investigate the transferability of generated perturbations when the conditions at inference time differ from the training ones in terms of the target architecture, target data, and target task. |
Krishna kanth Nakka; Mathieu Salzmann; | |
1070 | PortaSpeech: Portable and High-Quality Generative Text-to-Speech Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech model. |
Yi Ren; Jinglin Liu; Zhou Zhao; | |
1071 | Exponential Graph Is Provably Efficient for Decentralized Deep Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study so-called exponential graphs where every node is connected to $O(\log(n))$ neighbors and $n$ is the total number of nodes. This work proves such graphs can lead to both fast communication and effective averaging simultaneously. |
Bicheng Ying; Kun Yuan; Yiming Chen; Hanbin Hu; PAN PAN; Wotao Yin; | code |
1072 | CLIP-It! Language-Guided Video Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces CLIP-It, a single framework for addressing both generic and query-focused video summarization, typically approached separately in the literature. |
Medhini Narasimhan; Anna Rohrbach; Trevor Darrell; | |
1073 | Learning Treatment Effects in Panels with General Intervention Patterns Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper extends that framework to allow rate-optimal recovery of $\tau^*$ for general $Z$, thus broadly expanding its applicability. |
Vivek Farias; Andrew Li; Tianyi Peng; | |
1074 | Lossy Compression for Lossless Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we characterize the bit-rate required to ensure high performance on all predictive tasks that are invariant under a set of transformations, such as data augmentations. |
Yann Dubois; Benjamin Bloem-Reddy; Karen Ullrich; Chris J. Maddison; | |
1075 | From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study a generic \emph{Dirichlet Sampling} (DS) algorithm, based on pairwise comparisons of empirical indices computed with \textit{re-sampling} of the arms’ observations and a data-dependent \textit{exploration bonus}. |
Dorian Baudry; Patrick Saux; Odalric-Ambrym Maillard; | |
1076 | CCVS: Context-aware Controllable Video Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This presentation introduces a self-supervised learning approach to the synthesis of new videos clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual information for temporal continuity and ancillary information for fine control. |
Guillaume Le Moing; Jean Ponce; Cordelia Schmid; | |
1077 | An Online Riemannian PCA for Stochastic Canonical Correlation Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an efficient stochastic algorithm (RSG+) for canonical correlation analysis (CCA) using a reparametrization of the projection matrices. |
Zihang Meng; Rudrasis Chakraborty; Vikas Singh; | |
1078 | Predify: Augmenting Deep Neural Networks with Brain-inspired Predictive Coding Dynamics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks. |
Bhavin Choksi; Milad Mozafari; Callum Biggs O'May; B. ADOR; Andrea Alamia; Rufin VanRullen; | |
1079 | Deep Extrapolation for Attribute-Enhanced Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formulate a new task for extrapolation in sequence generation, focusing on natural language and proteins, and propose GENhance, a generative framework that enhances attributes through a learned latent space. |
Alvin Chan Guo Wei; Ali Madani; Ben Krause; Nikhil Naik; | |
1080 | Generalized DataWeighting Via Class-Level Gradient Manipulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, in this paper, we propose Generalized Data Weighting (GDW) to simultaneously mitigate label noise and class imbalance by manipulating gradients at the class level. |
Can Chen; Shuhao Zheng; Xi Chen; Erqun Dong; Xue (Steve) Liu; Hao Liu; Dejing Dou; | code |
1081 | Slow Learning and Fast Inference: Efficient Graph Similarity Computation Via Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For slow learning of graph similarity, this paper proposes a novel early-fusion approach by designing a co-attention-based feature fusion network on multilevel GNN features. |
Can Qin; Handong Zhao; Lichen Wang; Huan Wang; Yulun Zhang; Yun Fu; | |
1082 | Meta Learning Backpropagation And Improving It Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our Variable Shared Meta Learning (VSML) unifies the above and demonstrates that simple weight-sharing and sparsity in an NN is sufficient to express powerful learning algorithms (LAs) in a reusable fashion. |
Louis Kirsch; J�rgen Schmidhuber; | |
1083 | Posterior Meta-Replay for Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we describe an alternative Bayesian approach where task-conditioned parameter distributions are continually inferred from data. |
Christian Henning; Maria Cervera; Francesco D'Angelo; Johannes von Oswald; Regina Traber; Benjamin Ehret; Seijin Kobayashi; Benjamin F. Grewe; Jo�o Sacramento; | |
1084 | Optimizing Reusable Knowledge for Continual Learning Via Metalearning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose MetA Reusable Knowledge or MARK, a new method that fosters weight reusability instead of overwriting when learning a new task. |
Julio Hurtado; Alain Raymond; Alvaro Soto; | |
1085 | A Sampling-based Circuit for Optimal Decision Making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose a spiking network model that maps neural samples of a task-specific marginal distribution into an instantaneous representation of uncertainty via a procedure inspired by online kernel density estimation, so that its output can be readily used for decision making. |
Camille Rull�n Bux�; Cristina Savin; | |
1086 | Compressed Video Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, for the first time, the seemingly contradictory goals are simultaneously achieved by exploiting compressed videos and capturing mutual information between two input streams. |
Yuqi Huo; Mingyu Ding; Haoyu Lu; Nanyi Fei; Zhiwu Lu; Ji-Rong Wen; Ping Luo; | |
1087 | Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, in order to overcome the limitation of existing algorithms, we propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability. |
jiafan he; Dongruo Zhou; Quanquan Gu; | |
1088 | Attention Bottlenecks for Multimodal Fusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we introduce a novel transformer based architecture that uses ‘attention bottlenecks’ for modality fusion at multiple layers. |
Arsha Nagrani; Shan Yang; Anurag Arnab; Aren Jansen; Cordelia Schmid; Chen Sun; | |
1089 | Convergence of Adaptive Algorithms for Constrained Weakly Convex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze the adaptive first order algorithm AMSGrad, for solving a constrained stochastic optimization problem with a weakly convex objective. |
Ahmet Alacaoglu; Yura Malitsky; Volkan Cevher; | |
1090 | On The Convergence of Step Decay Step-Size for Stochastic Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide convergence results for step decay in the non-convex regime, ensuring that the gradient norm vanishes at an $\mathcal{O}(\ln T/\sqrt{T})$ rate. |
Xiaoyu Wang; Sindri Magn�sson; Mikael Johansson; | |
1091 | BernNet: Learning Arbitrary Graph Spectral Filters Via Bernstein Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these issues, we propose $\textit{BernNet}$, a novel graph neural network with theoretical support that provides a simple but effective scheme for designing and learning arbitrary graph spectral filters. |
Mingguo He; Zhewei Wei; zengfeng Huang; Hongteng Xu; | code |
1092 | Co-evolution Transformer for Protein Contact Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these issues, we propose an attention-based architecture, Co-evolution Transformer (CoT), for PCP. |
He Zhang; Fusong Ju; Jianwei Zhu; Liang He; Bin Shao; Nanning Zheng; Tie-Yan Liu; | |
1093 | Unsupervised Foreground Extraction Via Deep Region Competition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. |
Peiyu Yu; Sirui Xie; Xiaojian Ma; Yixin Zhu; Ying Nian Wu; Song-Chun Zhu; | |
1094 | Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of estimating at a central server the mean of a set of vectors distributed across several nodes (one vector per node). |
Divyansh Jhunjhunwala; Ankur Mallick; Advait Gadhikar; Swanand Kadhe; Gauri Joshi; | |
1095 | Last-iterate Convergence in Extensive-Form Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by recent advances on last-iterate convergence of optimistic algorithms in zero-sum normal-form games, we study this phenomenon in sequential games, and provide a comprehensive study of last-iterate convergence for zero-sum extensive-form games with perfect recall (EFGs), using various optimistic regret-minimization algorithms over treeplexes. |
Chung-Wei Lee; Christian Kroer; Haipeng Luo; | |
1096 | Class-Incremental Learning Via Dual Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we emphasize two dilemmas, representation bias and classifier bias in class-incremental learning, and present a simple and novel approach that employs explicit class augmentation (classAug) and implicit semantic augmentation (semanAug) to address the two biases, respectively. |
Fei Zhu; Zhen Cheng; Xu-yao Zhang; Cheng-lin Liu; | |
1097 | Robust and Fully-Dynamic Coreset for Continuous-and-Bounded Learning (With Outliers) Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel robust coreset method for the {\em continuous-and-bounded learning} problems (with outliers) which includes a broad range of popular optimization objectives in machine learning, {\em e.g.,} logistic regression and $ k $-means clustering. |
Zixiu Wang; Yiwen Guo; Hu Ding; | |
1098 | Rethinking and Reweighting The Univariate Losses for Multi-Label Ranking: Consistency and Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To take a step towards filling up this gap, this paper presents a systematic study from two complementary perspectives of consistency and generalization error bounds of learning algorithms. |
Guoqiang Wu; Chongxuan LI; Kun Xu; Jun Zhu; | |
1099 | Fair Clustering Under A Bounded Cost Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper we propose to treat an upper bound on the clustering objective as a constraint on the clustering problem, and to maximize equality of representation subject to it. |
Seyed Esmaeili; Brian Brubach; Aravind Srinivasan; John Dickerson; | |
1100 | Improving Calibration Through The Relationship with Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the connection between adversarial robustness and calibration and find that the inputs for which the model is sensitive to small perturbations (are easily attacked) are more likely to have poorly calibrated predictions. |
Yao Qin; Xuezhi Wang; Alex Beutel; Ed Chi; | |
1101 | Credal Self-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our approach, we therefore allow the learner to label instances in the form of credal sets, that is, sets of (candidate) probability distributions. |
Julian Lienen; Eyke H�llermeier; | |
1102 | Spot The Difference: Detection of Topological Changes Via Geometric Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a first step towards solving such alignment problems, we propose an unsupervised algorithm for the detection of changes in image topology. |
Per Steffen Czolbe; Aasa Feragen; Oswin Krause; | |
1103 | Rethinking The Variational Interpretation of Accelerated Optimization Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we revisit this idea and provide an in-depth analysis of the action relative to the Bregman Lagrangian from the point of view of calculus of variations. |
Peiyuan Zhang; Antonio Orvieto; Hadi Daneshmand; | |
1104 | Linear and Kernel Classification in The Streaming Model: Improved Bounds for Heavy Hitters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study linear and kernel classification in the streaming model. |
Arvind Mahankali; David Woodruff; | |
1105 | A PAC-Bayes Analysis of Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the first general PAC-Bayesian generalization bounds for adversarial robustness, that estimate, at test time, how much a model will be invariant to imperceptible perturbations in the input. |
Paul Viallard; Guillaume VIDOT; Amaury Habrard; Emilie Morvant; | |
1106 | SE(3)-equivariant Prediction of Molecular Wavefunctions and Electronic Densities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this issue, we introduce general SE(3)-equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data and apply them to reconstruct wavefunctions of atomistic systems with unprecedented accuracy. |
Oliver Unke; Mihail Bogojeski; Michael Gastegger; Mario Geiger; Tess Smidt; Klaus-Robert M�ller; | |
1107 | Modified Frank Wolfe in Probability Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Frank-Wolfe (FW) procedure for the optimization of infinite-dimensional functionals of probability measures – a task which arises naturally in a wide range of areas including statistical learning (e.g. variational inference) and artificial intelligence (e.g. generative adversarial networks). |
Carson Kent; Jiajin Li; Jose Blanchet; Peter W. Glynn; | |
1108 | Bayesian Optimization of Function Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider Bayesian optimization of the output of a network of functions, where each function takes as input the output of its parent nodes, and where the network takes significant time to evaluate. |
Raul Astudillo; Peter Frazier; | |
1109 | Look at What I’m Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the task of spatially localizing narrated interactions in videos. |
Reuben Tan; Bryan Plummer; Kate Saenko; Hailin Jin; Bryan Russell; | |
1110 | RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose RETRIEVE, a coreset selection framework for efficient and robust semi-supervised learning. |
Krishnateja Killamsetty; Xujiang Zhao; Feng Chen; Rishabh Iyer; | code |
1111 | Collaborating with Humans Without Human Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we study the problem of how to train agents that collaborate well with human partners without using human data. |
DJ Strouse; Kevin McKee; Matt Botvinick; Edward Hughes; Richard Everett; | |
1112 | Training Feedback Spiking Neural Networks By Implicit Differentiation on The Equilibrium State Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider feedback spiking neural networks, which are more brain-like, and propose a novel training method that does not rely on the exact reverse of the forward computation. |
Mingqing Xiao; Qingyan Meng; Zongpeng Zhang; Yisen Wang; Zhouchen Lin; | code |
1113 | Online Selective Classification with Limited Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by applications to resource-limited and safety-critical domains, we study selective classification in the online learning model, wherein a predictor may abstain from classifying an instance. |
Aditya Gangrade; Anil Kag; Ashok Cutkosky; Venkatesh Saligrama; | |
1114 | Controlled Text Generation As Continuous Optimization with Multiple Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As an alternative, we propose \textsc{MuCoCO}—a flexible and modular algorithm for controllable inference from pretrained models. |
Sachin Kumar; Eric Malmi; Aliaksei Severyn; Yulia Tsvetkov; | |
1115 | S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose S$^3$ re-parameterization, a novel technique for training low-bit shift networks. |
Xinlin Li; Bang Liu; Yaoliang Yu; Wulong Liu; Chunjing XU; Vahid Partovi Nia; | |
1116 | Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components. |
Mathias Niepert; Pasquale Minervini; Luca Franceschi; | |
1117 | Scaling Up Continuous-Time Markov Chains Helps Resolve Underspecification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To put our theoretical insight into practice, we develop an approximate likelihood maximization method for learning continuous-time Markov chains, which can scale to hundreds of items and is orders of magnitude faster than previous methods. |
Alkis Gotovos; Rebekka Burkholz; John Quackenbush; Stefanie Jegelka; | |
1118 | Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this issue for quadratic-cost transport—specifically, computation of the Wasserstein-2 distance, a commonly-used formulation of optimal transport in machine learning. |
Alexander Korotin; Lingxiao Li; Aude Genevay; Justin M. Solomon; Alexander Filippov; Evgeny Burnaev; | |
1119 | Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a general algorithmic framework called FedLin to tackle some of the key challenges intrinsic to FL, namely objective heterogeneity, systems heterogeneity, and infrequent and imprecise communication. |
Aritra Mitra; Rayana Jaafar; George Pappas; Hamed Hassani; | |
1120 | On The Convergence of Prior-Guided Zeroth-Order Optimization Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper makes an attempt to fill up this gap by analyzing the convergence of prior-guided ZO algorithms under a greedy descent framework with various gradient estimators. |
Shuyu Cheng; Guoqiang Wu; Jun Zhu; | |
1121 | Revisit Multimodal Meta-Learning Through The Lens of Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: First, we propose a method to quantify knowledge transfer between tasks of different modes at a micro-level. Our quantitative, task-level analysis is inspired by the recent transference idea from multi-task learning. Second, inspired by hard parameter sharing in multi-task learning and a new interpretation of related work, we propose a new multimodal meta-learner that outperforms existing work by considerable margins. |
Milad Abdollahzadeh; Touba Malekzadeh; Ngai-Man (Man) Cheung; | code |
1122 | Dynamic Sasvi: Strong Safe Screening for Norm-Regularized Least Squares Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we first propose a flexible framework for safe screening based on the Fenchel–Rockafellar duality and then derive a strong safe screening rule for norm-regularized least squares using the proposed framework. |
Hiroaki Yamada; Makoto Yamada; | |
1123 | What Matters for Adversarial Imitation Learning? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we implement more than 50 of these choices in a generic adversarial imitation learning frameworkand investigate their impacts in a large-scale study (>500k trained agents) with both synthetic and human-generated demonstrations. |
Manu Orsini; Anton Raichuk; Leonard Hussenot; Damien Vincent; Robert Dadashi; Sertan Girgin; Matthieu Geist; Olivier Bachem; Olivier Pietquin; Marcin Andrychowicz; | |
1124 | Sequential Causal Imitation Learning with Unobserved Confounders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper investigates the problem of causal imitation learning in sequential settings, where the imitator must make multiple decisions per episode. |
Daniel Kumor; Junzhe Zhang; Elias Bareinboim; | |
1125 | Topic Modeling Revisited: A Document Graph-based Neural Network Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, in this paper, we revisit the task of topic modeling by transforming each document into a directed graph with word dependency as edges between word nodes, and develop a novel approach, namely Graph Neural Topic Model (GNTM). |
Dazhong Shen; Chuan Qin; Chao Wang; Zheng Dong; Hengshu Zhu; Hui Xiong; | |
1126 | Hard-Attention for Scalable Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down fashion, visiting only the most informative image regions along the way. |
Athanasios Papadopoulos; Pawel Korus; Nasir Memon; | |
1127 | Fast Routing Under Uncertainty: Adaptive Learning in Congestion Games Via Exponential Weights Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we propose a novel, adaptive exponential weights method—dubbed AdaWeight—that seamlessly interpolates between the $\mathcal{O}(1/T^{2})$ and $\mathcal{O}(1/\sqrt{T})$ rates in the static and stochastic regimes respectively. |
Dong Quan Vu; Kimon Antonakopoulos; Panayotis Mertikopoulos; | |
1128 | Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel gradient-based algorithm for profiling Pareto front by using Stein variational gradient descent (SVGD). |
Xingchao Liu; Xin Tong; Qiang Liu; | |
1129 | MAP Propagation Algorithm: Faster Learning with A Team of Reinforcement Learning Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore propose a novel algorithm called MAP propagation to reduce this variance significantly while retaining the local property of the learning rule. |
Stephen Chung; | |
1130 | TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to conduct the first pilot study in building a GAN \textit{completely free of convolutions}, using only pure transformer-based architectures. |
Yifan Jiang; Shiyu Chang; Zhangyang Wang; | code |
1131 | A Central Limit Theorem for Differentially Private Query Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The central question is, therefore, to understand which noise distribution optimizes the privacy-accuracy trade-off, especially when the dimension of the answer vector is high. Accordingly, an extensive literature has been dedicated to the question and the upper and lower bounds have been successfully matched up to constant factors (Bun et al.,2018; Steinke & Ullman, 2017). In this paper, we take a novel approach to address this important optimality question. |
Jinshuo Dong; Weijie Su; Linjun Zhang; | |
1132 | Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study this problem for noisy gradient descent algorithms, and model the \emph{dynamics} of R\’enyi differential privacy loss throughout the training process. |
Rishav Chourasia; Jiayuan Ye; Reza Shokri; | |
1133 | Data Driven Semi-supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present a novel data driven approach for learning the graph and provide strong formal guarantees in both the distributional and online learning formalizations. |
Maria-Florina F. Balcan; Dravyansh Sharma; | |
1134 | Meta-Learning Via Learning with Distributed Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We demonstrate that efficient meta-learning can be achieved via end-to-end training of deep neural networks with memory distributed across layers. |
Sudarshan Babu; Pedro Savarese; Michael Maire; | |
1135 | Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on the integration of incomplete physics models into deep generative models. |
Naoya Takeishi; Alexandros Kalousis; | |
1136 | Characterizing The Risk of Fairwashing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness trade-offs. |
Ulrich A�vodji; Hiromi Arai; S�bastien Gambs; Satoshi Hara; | |
1137 | Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples. |
Kanghyun Choi; Deokki Hong; Noseong Park; Youngsok Kim; Jinho Lee; | code |
1138 | Embedding Principle of Loss Landscape of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we prove an embedding principle that the loss landscape of a DNN "contains" all the critical points of all the narrower DNNs. |
Yaoyu Zhang; Zhongwang Zhang; Tao Luo; Zhiqin Xu; | |
1139 | Adversarial Reweighting for Partial Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the challenge of negative domain transfer, we propose a novel Adversarial Reweighting (AR) approach that adversarially learns the weights of source domain data to align the source and target domain distributions, and the transferable deep recognition network is learned on the reweighted source domain data. |
Xiang Gu; Xi Yu; yan yang; Jian Sun; Zongben Xu; | |
1140 | M-FAC: Efficient Matrix-Free Approximations of Second-Order Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate matrix-free approaches for estimating Inverse-Hessian Vector Products (IHVPs) for the case when the Hessian can be approximated as a sum of rank-one matrices, as in the classic approximation of the Hessian by the empirical Fisher matrix. |
Elias Frantar; Eldar Kurtic; Dan Alistarh; | |
1141 | Graph Adversarial Self-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by adversarial training, we propose an adversarial self-supervised learning (\texttt{GASSL}) framework for learning unsupervised representations of graph data without any handcrafted views. |
Longqi Yang; Liangliang Zhang; Wenjing Yang; | |
1142 | Anti-Backdoor Learning: Training Clean Models on Poisoned Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the concept of \emph{anti-backdoor learning}, aiming to train \emph{clean} models given backdoor-poisoned data. |
Yige Li; Xixiang Lyu; Nodens Koren; Lingjuan Lyu; Bo Li; Xingjun Ma; | code |
1143 | Locally Most Powerful Bayesian Test for Out-of-Distribution Detection Using Deep Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new OOD score based on a Bayesian hypothesis test called the locally most powerful Bayesian test (LMPBT). |
keunseo kim; JunCheol Shin; Heeyoung Kim; | |
1144 | Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a neural ODE with Lyapunov-stable equilibrium points for defending against adversarial attacks (SODEF). |
Qiyu Kang; Yang Song; Qinxu Ding; Wee Peng Tay; | |
1145 | Robust Compressed Sensing MRI with Deep Generative Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In thispaper, we present the first successful application of the CSGMframework on clinical MRI data. |
Ajil Jalal; Marius Arvinte; Giannis Daras; Eric Price; Alexandros G. Dimakis; Jonathan Tamir; | code |
1146 | H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present neural radiance fields for rendering and temporal (4D) reconstruction of humans in motion (H-NeRF), as captured by a sparse set of cameras or even from a monocular video. |
Hongyi Xu; Thiemo Alldieck; Cristian Sminchisescu; | |
1147 | DOBF: A Deobfuscation Pre-Training Objective for Programming Languages Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new pre-training objective, DOBF, that leverages the structural aspect of programming languages and pre-trains a model to recover the original version of obfuscated source code. |
Marie-Anne Lachaux; Baptiste Roziere; Marc Szafraniec; Guillaume Lample; | |
1148 | Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a principled and practically effective framework that simultaneously addresses the two tasks. |
Jiefeng Chen; Frederick Liu; Besim Avci; Xi Wu; Yingyu Liang; Somesh Jha; | |
1149 | Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To measure the difference between two probability distributions, referred to as the source and target, respectively, we exploit both the chain rule and Bayes’ theorem to construct conditional transport (CT), which is constituted by both a forward component and a backward one. |
Huangjie Zheng; Mingyuan Zhou; | |
1150 | Actively Identifying Causal Effects with Latent Variables Given Only Response Variable Observable Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we attempt to identify such effects by a few active interventions where only the response variable is observable. |
Tian-Zuo Wang; Zhi-Hua Zhou; | |
1151 | Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a step towards tractable causal models, we consider the problem of learning interventional distributions using sum-product networks (SPNs) that are over-parameterized by gate functions, e.g., neural networks. |
Matej Zecevic; Devendra Dhami; Athresh Karanam; Sriraam Natarajan; Kristian Kersting; | |
1152 | PettingZoo: Gym for Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle (AEC) games model. |
Justin Terry; Benjamin Black; Nathaniel Grammel; Mario Jayakumar; Ananth Hari; Ryan Sullivan; Luis Santos; Clemens Dieffendahl; Caroline Horsch; Rodrigo Perez-Vicente; Niall Williams; Yashas Lokesh; Praveen Ravi ; | |
1153 | Parametric Complexity Bounds for Approximating PDEs with Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the representational power of neural networks for approximating solutions to linear elliptic PDEs with Dirichlet boundary conditions. |
Tanya Marwah; Zachary Lipton; Andrej Risteski; | |
1154 | Learning-to-learn Non-convex Piecewise-Lipschitz Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze the meta-learning of the initialization and step-size of learning algorithms for piecewise-Lipschitz functions, a non-convex setting with applications to both machine learning and algorithms. |
Maria-Florina F. Balcan; Mikhail Khodak; Dravyansh Sharma; Ameet Talwalkar; | |
1155 | Uncertain Decisions Facilitate Better Preference Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To better understand preference learning in these cases, we study the setting of inverse decision theory (IDT), a previously proposed framework where a human is observed making non-sequential binary decisions under uncertainty. |
Cassidy Laidlaw; Stuart Russell; | |
1156 | Decision Transformer: Reinforcement Learning Via Sequence Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. |
Lili Chen; Kevin Lu; Aravind Rajeswaran; Kimin Lee; Aditya Grover; Misha Laskin; Pieter Abbeel; Aravind Srinivas; Igor Mordatch; | |
1157 | Probability Paths and The Structure of Predictions Over Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given a collection of such probability paths, we introduce a Bayesian framework — which we call the Gaussian latent information martingale, or GLIM — for modeling the structure of dynamic predictions over time. |
Zhiyuan Jerry Lin; Hao Sheng; Sharad Goel; | |
1158 | Deep Extended Hazard Models for Survival Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Rather than estimating the survival function targeted by most existing methods, we introduce a Deep Extended Hazard (DeepEH) model to provide a flexible and general framework for deep survival analysis. |
Qixian Zhong; Jonas W. Mueller; Jane-Ling Wang; | |
1159 | TNASP: A Transformer-based NAS Predictor with A Self-evolution Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we propose a Transformer-based NAS performance predictor, associated with a Laplacian matrix based positional encoding strategy, which better represents topology information and achieves better performance than previous state-of-the-art methods on NAS-Bench-101, NAS-Bench-201, and DARTS search space. |
Shun Lu; Jixiang Li; Jianchao Tan; Sen Yang; Ji Liu; | |
1160 | Automorphic Equivalence-aware Graph Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make GNN aware of automorphic equivalence, we first introduce a localized variant of this concept — ego-centered automorphic equivalence (Ego-AE). Then, we design a novel variant of GNN, i.e., GRAPE, that uses learnable AE-aware aggregators to explicitly differentiate the Ego-AE of each node’s neighbors with the aids of various subgraph templates. |
Fengli Xu; Quanming Yao; Pan Hui; Yong Li; | code |
1161 | Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Perhaps surprisingly, we prove that when the condition number is taken into account, without-replacement SGD \emph{does not} significantly improve on with-replacement SGD in terms of worst-case bounds, unless the number of epochs (passes over the data) is larger than the condition number. |
Itay Safran; Ohad Shamir; | |
1162 | Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the optimization problem associated with fitting two-layer ReLU neural networks with respect to the squared loss, where labels are generated by a target network. |
Yossi Arjevani; Michael Field; | |
1163 | CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. |
Sakshi Varshney; Vinay Kumar Verma; P. K. Srijith; Lawrence Carin; Piyush Rai; | |
1164 | Structured Dropout Variational Inference for Bayesian Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We tackle this challenge by introducing a novel variational structured approximation inspired by the Bayesian interpretation of Dropout regularization. |
Son Nguyen; Duong Nguyen; Khai Nguyen; Khoat Than; Hung Bui; Nhat Ho; | |
1165 | Neural Relightable Participating Media Rendering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to learn neural representations for participating media with a complete simulation of global illumination. |
Quan Zheng; Gurprit Singh; Hans-peter Seidel; | |
1166 | Efficient Neural Network Training Via Forward and Backward Propagation Sparsification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper solves this problem by proposing an efficient sparse training method with completely sparse forward and backward passes. |
Xiao Zhou; Weizhong Zhang; Zonghao Chen; SHIZHE DIAO; Tong Zhang; | |
1167 | Learning to Ground Multi-Agent Communication with Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We demonstrate a simple way to ground language in learned representations, which facilitates decentralized multi-agent communication and coordination. |
Toru Lin; Jacob Huh; Christopher Stauffer; Ser Nam Lim; Phillip Isola; | |
1168 | Large-Scale Wasserstein Gradient Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a scalable method to approximate Wasserstein gradient flows, targeted to machine learning applications. |
Petr Mokrov; Alexander Korotin; Lingxiao Li; Aude Genevay; Justin M. Solomon; Evgeny Burnaev; | |
1169 | Who Leads and Who Follows in Strategic Classification? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we argue that the order of play in strategic classification is fundamentally determined by the relative frequencies at which the decision-maker and the agents adapt to each other’s actions. |
Tijana Zrnic; Eric Mazumdar; Shankar Sastry; Michael Jordan; | |
1170 | Unadversarial Examples: Designing Objects for Robust Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a framework that leverages this capability—and deep networks’ unusual sensitivity to input perturbations—to design “robust objects,” i.e., objects that are explicitly optimized to be confidently classified. |
Hadi Salman; Andrew Ilyas; Logan Engstrom; Sai Vemprala; Aleksander Madry; Ashish Kapoor; | |
1171 | Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle continuous treatments, we develop a novel estimation method for OPE using deep jump learning. |
Hengrui Cai; Chengchun Shi; Rui Song; Wenbin Lu; | |
1172 | Attention Approximates Sparse Distributed Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we show that Transformer Attention can be closely related under certain data conditions to Kanerva’s Sparse Distributed Memory (SDM), a biologically plausible associative memory model. |
Trenton Bricken; Cengiz Pehlevan; | |
1173 | Augmented Shortcuts for Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we theoretically analyze the feature collapse phenomenon and study the relationship between shortcuts and feature diversity in these transformer models. |
Yehui Tang; Kai Han; Chang Xu; An Xiao; Yiping Deng; Chao Xu; Yunhe Wang; | |
1174 | Finding Regions of Heterogeneity in Decision-Making Via Expected Conditional Covariance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With these examples in mind, we present an algorithm for identifying types of contexts (e.g., types of cases or patients) with high inter-decision-maker disagreement. |
Justin Lim; Christina Ji; Michael Oberst; Saul Blecker; Leora Horwitz; David Sontag; | |
1175 | Identifying and Benchmarking Natural Out-of-Context Prediction Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a framework unifying the literature on OOC performance measurement, and demonstrate how rich auxiliary information can be leveraged to identify candidate sets of OOC examples in existing datasets. |
David Madras; Richard Zemel; | |
1176 | Label Disentanglement in Partition-based Extreme Multilabel Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that the label assignment problem in partition-based XMC can be formulated as an optimization problem, with the objective of maximizing precision rates. |
Xuanqing Liu; Wei-Cheng Chang; Hsiang-Fu Yu; Cho-Jui Hsieh; Inderjit Dhillon; | |
1177 | Leveraging SE(3) Equivariance for Self-supervised Category-Level Object Pose Estimation from Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reduce the huge amount of pose annotations needed for category-level learning, we propose for the first time a self-supervised learning framework to estimate category-level 6D object pose from single 3D point clouds. |
Xiaolong Li; Yijia Weng; Li Yi; Leonidas J. Guibas; A. Abbott; Shuran Song; He Wang; | |
1178 | A Theoretical Analysis of Fine-tuning with Linear Teachers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For deep linear regression, we propose a novel result regarding the inductive bias of gradient-based training when the network is initialized with pretrained weights. |
Gal Shachaf; Alon Brutzkus; Amir Globerson; | |
1179 | Overinterpretation Reveals Image Classification Model Pathologies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Batched Gradient SIS, a new method for discovering sufficient input subsets for complex datasets, and use this method to show the sufficiency of border pixels in ImageNet for training and testing. |
Brandon Carter; Siddhartha Jain; Jonas W. Mueller; David Gifford; | |
1180 | Neural Circuit Synthesis from Specification Patterns Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider a method to generate large amounts of additional training data, i.e., pairs of speci?cations and circuits implementing them. |
Frederik Schmitt; Christopher Hahn; Markus Rabe; Bernd Finkbeiner; | |
1181 | Directional Message Passing on Molecular Graphs Via Synthetic Coordinates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose synthetic coordinates that enable the use of advanced GNNs without requiring the true molecular configuration. |
Johannes Klicpera; Chandan Yeshwanth; Stephan G�nnemann; | |
1182 | Federated Multi-Task Learning Under A Mixture of Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to study federated MTL under the flexible assumption that each local data distribution is a mixture of unknown underlying distributions. |
Othmane MARFOQ; Giovanni Neglia; Aur�lien Bellet; Laetitia Kameni; Richard Vidal; | |
1183 | Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection. |
Jing Zhang; Jianwen Xie; Nick Barnes; Ping Li; | |
1184 | Regularization in ResNet with Stochastic Depth Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides a hybrid analysis combining perturbation analysis and signal propagation to shed light on different regularization effects of SD. |
Soufiane Hayou; Fadhel Ayed; | |
1185 | ResT: An Efficient Transformer for Visual Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. |
Qinglong Zhang; Yu-Bin Yang; | code |
1186 | Adversarial Examples for K-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an algorithm for evaluating the adversarial robustness of $k$-nearest neighbor classification, i.e., finding a minimum-norm adversarial example. |
Chawin Sitawarin; Evgenios Kornaropoulos; Dawn Song; David Wagner; | |
1187 | Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we systematically study the impact of various self-supervised learning proxy tasks on different architectures and threat models for 3D point clouds with adversarial training. |
Jiachen Sun; Yulong Cao; Christopher B. Choy; Zhiding Yu; Anima Anandkumar; Zhuoqing Morley Mao; Chaowei Xiao; | |
1188 | Tuning Mixed Input Hyperparameters on The Fly for Efficient Population Based AutoRL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce a new (provably) efficient hierarchical approach for optimizing \emph{both continuous and categorical} variables, using a new time-varying bandit algorithm specifically designed for the population based training regime. |
Jack Parker-Holder; Vu Nguyen; Shaan Desai; Stephen J. Roberts; | |
1189 | Neural Algorithmic Reasoners Are Implicit Planners Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose eXecuted Latent Value Iteration Networks (XLVINs), which alleviate the above limitations. |
Andreea-Ioana Deac; Petar Velickovic; Ognjen Milinkovic; Pierre-Luc Bacon; Jian Tang; Mladen Nikolic; | |
1190 | Self-Supervised Learning with Kernel Dependence Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC). |
Yazhe Li; Roman Pogodin; Danica J. Sutherland; Arthur Gretton; | |
1191 | CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a supervised contrastive learning framework, CROCS, where representations of cardiac signals associated with a set of patient-specific attributes (e.g., disease class, sex, age) are attracted to learnable embeddings entitled clinical prototypes. |
Dani Kiyasseh; Tingting Zhu; David Clifton; | |
1192 | Representing Hyperbolic Space Accurately Using Multi-Component Floats Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple, feasible-on-GPUs, and easy-to-understand solution for numerically accurate learning on hyperbolic space. |
Tao Yu; Christopher M. De Sa; | |
1193 | Dimensionality Reduction for Wasserstein Barycenter Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to cope with this “curse of dimensionality,” we study dimensionality reduction techniques for the Wasserstein barycenter problem. |
Zachary Izzo; Sandeep Silwal; Samson Zhou; | |
1194 | Neural Population Geometry Reveals The Role of Stochasticity in Robust Perception Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, using recently developed geometrical techniques from computational neuroscience, we investigate how adversarial perturbations influence the internal representations of standard, adversarially trained, and biologically-inspired stochastic networks. |
Joel Dapello; Jenelle Feather; Hang Le; Tiago Marques; David Cox; Josh McDermott; James J. DiCarlo; Sueyeon Chung; | |
1195 | Unsupervised Learning of Energy Compositions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose COMET, which discovers and represents concepts as separate energy functions, enabling us to represent both global concepts as well as objects under a unified framework. |
Yilun Du; Shuang Li; Yash Sharma; Josh Tenenbaum; Igor Mordatch; | code |
1196 | Nearly Horizon-Free Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision Processes (MDP). |
Tongzheng Ren; Jialian Li; Bo Dai; Simon S. Du; Sujay Sanghavi; | |
1197 | Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a. panoptic segmentation) consisting of a convolutional neural network and an asymmetric multiway cut problem solver. |
Ahmed Abbas; Paul Swoboda; | |
1198 | Reinforcement Learning with State Observation Costs in Action-Contingent Noiselessly Observable Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For continuous-state, continuous-action ACNO-MDPs, we propose a novel method of incorporating observation information that, when coupled with modern RL algorithms, yields significantly faster learning compared to other POMDP-RL algorithms in several simulated environments. |
HyunJi Nam; Scott Fleming; Emma Brunskill; | |
1199 | Iterative Amortized Policy Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given this perspective, we consider the more flexible class of iterative amortized optimizers. |
Joseph Marino; Alexandre Piche; Alessandro Davide Ialongo; Yisong Yue; | |
1200 | Revisiting The Calibration of Modern Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We systematically relate model calibration and accuracy, and find that the most recent models, notably those not using convolutions, are among the best calibrated. |
Matthias Minderer; Josip Djolonga; Rob Romijnders; Frances Hubis; Xiaohua Zhai; Neil Houlsby; Dustin Tran; Mario Lucic; | |
1201 | The Decomposition of The Higher-order Homology Embedding Constructed from The $k$-Laplacian Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the geometry of the $k$-th homology embedding and focus on cases reminiscent of spectral clustering. |
Yu-Chia Chen; Marina Meila; | |
1202 | Breaking The Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We make the first attempt to actively handle such super heavy-tailed noise in bandit learning problems: We propose a novel robust statistical estimator, mean of medians, which estimates a random variable by computing the empirical mean of a sequence of empirical medians. |
Han Zhong; Jiayi Huang; Lin Yang; Liwei Wang; | |
1203 | A Nonparametric Method for Gradual Change Problems with Statistical Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general method for detecting and localizing gradual changes that does not require any specific data generating model, any particular data type, or any prior knowledge about which features of the distribution are subject to change. |
Lizhen Nie; Dan Nicolae; | |
1204 | Nested Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, rooted subtrees are of limited expressiveness to represent a non-tree graph. To address it, we propose Nested Graph Neural Networks (NGNNs). |
Muhan Zhang; Pan Li; | |
1205 | Multimodal and Multilingual Embeddings for Large-Scale Speech Mining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach to encode a speech signal into a fixed-size representation which minimizes the cosine loss with the existing massively multilingual LASER text embedding space. |
Paul-Ambroise Duquenne; Hongyu Gong; Holger Schwenk; | |
1206 | Necessary and Sufficient Graphical Conditions for Optimal Adjustment Sets in Causal Graphical Models with Hidden Variables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The problem of selecting optimal backdoor adjustment sets to estimate causal effects in graphical models with hidden and conditioned variables is addressed. |
Jakob Runge; | |
1207 | On Blame Attribution for Accountable Multi-Agent Sequential Decision Making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study blame attribution in the context of cooperative multi-agent sequential decision making. |
Stelios Triantafyllou; Adish Singla; Goran Radanovic; | |
1208 | FLEX: Unifying Evaluation for Few-Shot NLP Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we formulate the FLEX Principles, a set of requirements and best practices for unified, rigorous, valid, and cost-sensitive few-shot NLP evaluation. |
Jonathan Bragg; Arman Cohan; Kyle Lo; Iz Beltagy; | |
1209 | A Flow-based Latent State Generative Model of Neural Population Responses to Natural Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a joint deep neural system identification model for two major sources of neural variability: stimulus-driven and stimulus-conditioned fluctuations. |
Mohammad Bashiri; Edgar Walker; Konstantin-Klemens Lurz; Akshay Jagadish; Taliah Muhammad; Zhiwei Ding; Zhuokun Ding; Andreas Tolias; Fabian Sinz; | |
1210 | Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel positional encoding method based on learnable Fourier features. |
Yang Li; Si Si; Gang Li; Cho-Jui Hsieh; Samy Bengio; | |
1211 | Doubly Robust Thompson Sampling with Linear Payoffs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The dependence of the arm choice on the past context and reward pairs compounds the complexity of regret analysis.We propose a novel multi-armed contextual bandit algorithm called Doubly Robust Thompson Sampling (DRTS) employing the doubly-robust estimator used in missing data literature to Thompson Sampling with contexts (\texttt{LinTS}). |
Wonyoung Kim; Gi-Soo Kim; Myunghee Cho Paik; | |
1212 | A Computationally Efficient Method for Learning Exponential Family Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a computationally efficient estimator that is consistent as well as asymptotically normal under mild conditions. |
Abhin Shah; Devavrat Shah; Gregory Wornell; | |
1213 | Rethinking Neural Operations for Diverse Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a search space of operations called XD-Operations that mimic the inductive bias of standard multi-channel convolutions while being much more expressive: we prove that it includes many named operations across multiple application areas. |
Nicholas Roberts; Mikhail Khodak; Tri Dao; Liam Li; Christopher R�; Ameet Talwalkar; | |
1214 | Motif-based Graph Self-Supervised Learning for Molecular Property Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge this gap, we propose Motif-based Graph Self-supervised Learning (MGSSL) by introducing a novel self-supervised motif generation framework for GNNs. |
ZAIXI ZHANG; Qi Liu; Hao Wang; Chengqiang Lu; Chee-Kong Lee; | |
1215 | On Inductive Biases for Heterogeneous Treatment Effect Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate and compare three end-to-end learning strategies to overcome this problem — based on regularization, reparametrization and a flexible multi-task architecture — each encoding inductive bias favoring shared behavior across POs. |
Alicia Curth; Mihaela van der Schaar; | |
1216 | DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new SSL method called DP-SSL that adopts an innovative data programming (DP) scheme to generate probabilistic labels for unlabeled data. |
Yi Xu; Jiandong Ding; Lu Zhang; Shuigeng Zhou; | |
1217 | Transformer in Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we point out that the attention inside these local patches are also essential for building visual transformers with high performance and we explore a new architecture, namely, Transformer iN Transformer (TNT). |
Kai Han; An Xiao; Enhua Wu; Jianyuan Guo; Chunjing XU; Yunhe Wang; | code |
1218 | Adversarial Graph Augmentation to Improve Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a novel principle, termed adversarial-GCL (\textit{AD-GCL}), which enables GNNs to avoid capturing redundant information during the training by optimizing adversarial graph augmentation strategies used in GCL. |
Susheel Suresh; Pan Li; Cong Hao; Jennifer Neville; | |
1219 | Online Control of Unknown Time-Varying Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We sketch extensions to Disturbance Action policies and partial observation, and propose an inefficient algorithm for regret against linear state feedback policies. |
Edgar Minasyan; Paula Gradu; Max Simchowitz; Elad Hazan; | |
1220 | Contrastive Reinforcement Learning of Symbolic Reasoning Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we instead consider symbolic domains as simple environments where states and actions are given as unstructured text, and binary rewards indicate whether a problem is solved. |
Gabriel Poesia; WenXin Dong; Noah Goodman; | |
1221 | Spatial Ensemble: A Novel Model Smoothing Mechanism for Student-Teacher Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ”Spatial Ensemble”, a novel model smoothing mechanism in parallel with TMA. |
Tengteng Huang; Yifan Sun; Xun Wang; Haotian Yao; Chi Zhang; | code |
1222 | Probabilistic Tensor Decomposition of Neural Population Spiking Activity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we extend the Pólya-Gamma (PG) augmentation, previously used in sampling-based Bayesianinference, to implement scalable variational inference in non-conjugate spike-count models. |
Hugo Soulat; Sepiedeh Keshavarzi; Troy Margrie; Maneesh Sahani; | |
1223 | Recurrent Bayesian Classifier Chains for Exact Multi-Label Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we propose Recurrent Bayesian Classifier Chains (RBCCs), which learn a Bayesian network of class dependencies and leverage this network in order to condition the prediction of child nodes only on their parents. |
Walter Gerych; Tom Hartvigsen; Luke Buquicchio; Emmanuel Agu; Elke Rundensteiner; | |
1224 | Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a mean-field perspective on the evolution and convergence of feature-based neural AC. |
Yufeng Zhang; Siyu Chen; Zhuoran Yang; Michael Jordan; Zhaoran Wang; | |
1225 | Assessing Fairness in The Presence of Missing Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this significant gap, we study the problem of estimating fairness in the complete data domain for an arbitrary model evaluated merely using complete cases. |
Yiliang Zhang; Qi Long; | |
1226 | Adversarial Attack Generation Empowered By Min-Max Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show how a general notion of min-max optimization over multiple domains can be leveraged to the design of different types of adversarial attacks. |
Jingkang Wang; Tianyun Zhang; Sijia Liu; Pin-Yu Chen; Jiacen Xu; Makan Fardad; Bo Li; | |
1227 | Safe Pontryagin Differentiable Programming Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic framework to solve a broad class of safety-critical learning and control tasks—problems that require the guarantee of safety constraint satisfaction at any stage of the learning and control progress. |
Wanxin Jin; Shaoshuai Mou; George Pappas; | |
1228 | Class-Disentanglement and Applications in Adversarial Detection and Defense Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ”class-disentanglement” that trains a variational autoencoder $G(\cdot)$ to extract this class-dependent information as $x – G(x)$ via a trade-off between reconstructing $x$ by $G(x)$ and classifying $x$ by $D(x-G(x))$, where the former competes with the latter in decomposing $x$ so the latter retains only necessary information for classification in $x-G(x)$. |
Kaiwen Yang; Tianyi Zhou; yonggang zhang; Xinmei Tian; Dacheng Tao; | |
1229 | Active 3D Shape Reconstruction from Vision and Touch Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on this problem and introduce a system composed of: 1) a haptic simulator leveraging high spatial resolution vision-based tactile sensors for active touching of 3D objects; 2) a mesh-based 3D shape reconstruction model that relies on tactile or visuotactile signals; and 3) a set of data-driven solutions with either tactile or visuotactile priors to guide the shape exploration. |
Edward Smith; David Meger; Luis Pineda; Roberto Calandra; Jitendra Malik; Adriana Romero; Michal Drozdzal; | |
1230 | CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an augmentation-based approach (CAPE) for absolute positional embeddings, which keeps the advantages of both absolute (simplicity and speed) and relative positional embeddings (better generalization). |
Tatiana Likhomanenko; Qiantong Xu; Gabriel Synnaeve; Ronan Collobert; Alex Rogozhnikov; | |
1231 | Multi-armed Bandit Requiring Monotone Arm Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the continuum-armed bandit problem when the arm sequence is required to be monotone. |
Ningyuan Chen; | |
1232 | Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we adopt federated learning as a gradient-based formalization of collaborative machine learning, propose a novel cosine gradient Shapley value to evaluate the agents’ uploaded model parameter updates/gradients, and design theoretically guaranteed fair rewards in the form of better model performance. |
Xinyi Xu; Lingjuan Lyu; Xingjun Ma; Chenglin Miao; Chuan Sheng Foo; Bryan Kian Hsiang Low; | |
1233 | Generalizable Imitation Learning from Observation Via Inferring Goal Proximity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: From this intuition, we propose a simple yet effective imitation learning from observation method for a goal-directed task using a learned goal proximity function as a task progress estimator, for better generalization to unseen states and goals. |
Youngwoon Lee; Andrew Szot; Shao-Hua Sun; Joseph J. Lim; | |
1234 | DualNet: Continual Learning, Fast and Slow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this theory, we propose a novel continual learning framework named “DualNet", which comprises a fast learning system for supervised learning of pattern-separated representation from specific tasks and a slow learning system for unsupervised representation learning of task-agnostic general representation via a Self-Supervised Learning (SSL) technique. |
Quang Pham; Chenghao Liu; Steven Hoi; | code |
1235 | Deformable Butterfly: A Highly Structured and Sparse Linear Transform Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new kind of linear transform named Deformable Butterfly (DeBut) that generalizes the conventional butterfly matrices and can be adapted to various input-output dimensions. |
Rui Lin; Jie Ran; King Hung Chiu; Graziano Chesi; Ngai Wong; | code |
1236 | Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an analysis framework that links the pretraining and downstream tasks with an underlying latent variable generative model of text — the downstream classifier must recover a function of the posterior distribution over the latent variables. |
Colin Wei; Sang Michael Xie; Tengyu Ma; | |
1237 | Learning Diverse Policies in MOBA Games Via Macro-Goals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Macro-Goals Guided framework, called MGG, to learn diverse policies in MOBA games. |
Yiming Gao; Bei Shi; Xueying Du; Liang Wang; Guangwei Chen; Zhenjie Lian; Fuhao Qiu; GUOAN HAN; Weixuan Wang; Deheng Ye; Qiang Fu; Wei Yang; Lanxiao Huang; | |
1238 | Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we perform a single-blind evaluation of teams of humans and AI agents in the cooperative card game Hanabi, with both rule-based and learning-based agents. |
Ho Chit Siu; Jaime Pe�a; Edenna Chen; Yutai Zhou; Victor Lopez; Kyle Palko; Kimberlee Chang; Ross Allen; | |
1239 | Counterfactual Invariance to Spurious Correlations in Text Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study stress testing using the tools of causal inference. |
Victor Veitch; Alexander D'Amour; Steve Yadlowsky; Jacob Eisenstein; | |
1240 | Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By formalizing this malicious attack as finding the worst-case training data within a specific $\infty$-Wasserstein ball, we show that minimizing adversarial risk on the perturbed data is equivalent to optimizing an upper bound of natural risk on the original data. |
Lue Tao; Lei Feng; Jinfeng Yi; Sheng-Jun Huang; Songcan Chen; | |
1241 | Determinantal Point Processes Based on Orthogonal Polynomials for Sampling Minibatches in SGD Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we contribute an orthogonal polynomial-based determinantal point process paradigm for performing minibatch sampling in SGD. |
R�mi Bardenet; Subhroshekhar Ghosh; Meixia LIN; | |
1242 | Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. |
Wouter Van Gansbeke; Simon Vandenhende; Stamatios Georgoulis; Luc V. Gool; | |
1243 | Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a neural analysis and synthesis (NANSY) framework that can manipulate the voice, pitch, and speed of an arbitrary speech signal. |
Hyeong-Seok Choi; Juheon Lee; Wansoo Kim; Jie Lee; Hoon Heo; Kyogu Lee; | |
1244 | Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To relax the dependency on paired data, we propose an unsupervised model Knowledge Graph Auto-Encoder (KGAE) which accepts independent sets of images and reports in training. |
Fenglin Liu; Chenyu You; Xian Wu; Shen Ge; Sheng wang; Xu Sun; | |
1245 | Diffusion Normalizing Flow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel generative modeling method called diffusion normalizing flow based on stochastic differential equations (SDEs). |
Qinsheng Zhang; Yongxin Chen; | |
1246 | Introspective Distillation for Robust Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel debiasing method called Introspective Distillation (IntroD) to make the best of both worlds for QA. |
Yulei Niu; Hanwang Zhang; | |
1247 | Rethinking The Pruning Criteria for Convolutional Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the above blind spots on different types of pruning criteria with layer-wise pruning or global pruning. |
Zhongzhan Huang; Wenqi Shao; Xinjiang Wang; Liang Lin; Ping Luo; | |
1248 | Adaptive Machine Unlearning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we give a general reduction from deletion guarantees against adaptive sequences to deletion guarantees against non-adaptive sequences, using differential privacy and its connection to max information. |
Varun Gupta; Christopher Jung; Seth Neel; Aaron Roth; Saeed Sharifi-Malvajerdi; Chris Waites; | |
1249 | EditGAN: High-Precision Semantic Image Editing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose EditGAN, a novel method for high-quality, high-precision semantic image editing, allowing users to edit images by modifying their highly detailed part segmentation masks, e.g., drawing a new mask for the headlight of a car. |
Huan Ling; Karsten Kreis; Daiqing Li; Seung Wook Kim; Antonio Torralba; Sanja Fidler; | |
1250 | Deep Molecular Representation Learning Via Fusing Physical and Chemical Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To push the boundaries of molecular representation learning, we present PhysChem, a novel neural architecture that learns molecular representations via fusing physical and chemical information of molecules. |
Shuwen Yang; Ziyao Li; Guojie Song; Lingsheng Cai; | |
1251 | Neural Optimal Feedback Control with Local Learning Rules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these shortcomings, we introduce a novel online algorithm which combines adaptive Kalman filtering with a model free control approach (i.e., policy gradient algorithm). |
Johannes Friedrich; Siavash Golkar; Shiva Farashahi; Alexander Genkin; Anirvan Sengupta; Dmitri Chklovskii; | |
1252 | Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. |
Matteo Papini; Andrea Tirinzoni; Aldo Pacchiano; Marcello Restelli; Alessandro Lazaric; Matteo Pirotta; | |
1253 | Noether Networks: Meta-learning Useful Conserved Quantities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on sequential prediction problems and take inspiration from Noether’s theorem to reduce the problem of finding inductive biases to meta-learning useful conserved quantities. |
Ferran Alet; Dylan Doblar; Allan Zhou; Josh Tenenbaum; Kenji Kawaguchi; Chelsea Finn; | |
1254 | Uncertainty-Driven Loss for Single Image Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new adaptive weighted loss for SISR to train deep networks focusing on challenging situations such as textured and edge pixels with high uncertainty. |
Qian Ning; Weisheng Dong; Xin Li; Jinjian Wu; GUANGMING Shi; | |
1255 | GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents GradInit, an automated and architecture agnostic method for initializing neural networks. |
Chen Zhu; Renkun Ni; Zheng Xu; Kezhi Kong; W. Ronny Huang; Tom Goldstein; | code |
1256 | Capacity and Bias of Learned Geometric Embeddings for Directed Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a novel variant of box embeddings that uses a learned smoothing parameter to achieve better representational capacity than vector models in low dimensions, while also avoiding performance saturation common to other geometric models in high dimensions. |
Michael Boratko; Dongxu Zhang; Nicholas Monath; Luke Vilnis; Kenneth Clarkson; Andrew McCallum; | |
1257 | Online Learning Of Neural Computations From Sparse Temporal Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we include the parameters that determine the intrinsic properties, e.g., time constants and reset potential, into the learning paradigm. |
Lukas Braun; Tim Vogels; | |
1258 | Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formulate the augmentation process as a latent variable model by postulating a partition of the latent representation into a content component, which is assumed invariant to augmentation, and a style component, which is allowed to change. |
Julius von K�gelgen; Yash Sharma; Luigi Gresele; Wieland Brendel; Bernhard Sch�lkopf; Michel Besserve; Francesco Locatello; | |
1259 | Instance-Conditional Knowledge Distillation for Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a conditional distillation framework to find the desired knowledge. |
Zijian Kang; Peizhen Zhang; Xiangyu Zhang; Jian Sun; Nanning Zheng; | |
1260 | Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose to use SSL to learn neural representations of the weights of populations of NNs. |
Konstantin Sch�rholt; Dimche Kostadinov; Damian Borth; | |
1261 | Multimodal Virtual Point 3D Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present an approach to seamlessly fuse RGB sensors into Lidar-based 3D recognition. |
Tianwei Yin; Xingyi Zhou; Philipp Kr�henb�hl; | code |
1262 | On Joint Learning for Solving Placement and Routing in Chip Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To achieve end-to-end placement learning, we first propose a joint learning method for the placement of macros and standard cells, by the integration of reinforcement learning with a gradient based optimization scheme. To further bridge the placement with the subsequent routing task, we also develop a joint learning approach via reinforcement learning. |
Ruoyu Cheng; Junchi Yan; | |
1263 | Learning with Algorithmic Supervision Via Continuous Relaxations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we build on those ideas to propose an approach that allows to integrate algorithms into end-to-end trainable neural network architectures based on a general approximation of discrete conditions. |
Felix Petersen; Christian Borgelt; Hilde Kuehne; Oliver Deussen; | |
1264 | Differentiable Multiple Shooting Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop the algorithmic framework of MSLs, analyzing the different choices of solution methods from a theoretical and computational perspective. |
Stefano Massaroli; Michael Poli; Sho Sonoda; Taiji Suzuki; Jinkyoo Park; Atsushi Yamashita; Hajime Asama; | |
1265 | Global-aware Beam Search for Neural Abstractive Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study develops a calibrated beam-based algorithm with awareness of the global attention distribution for neural abstractive summarization, aiming to improve the local optimality problem of the original beam search in a rigorous way. |
Ye Ma; Zixun Lan; Lu Zong; Kaizhu Huang; | |
1266 | DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce DROID-SLAM, a new deep learning based SLAM system. |
Zachary Teed; Jia Deng; | code |
1267 | Few-Shot Object Detection Via Association and DIscrimination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these obstacles, we propose a two-step fine-tuning framework, Few-shot object detection via Association and DIscrimination (FADI), which builds up a discriminative feature space for each novel class with two integral steps. |
Yuhang Cao; Jiaqi Wang; Ying Jin; Tong Wu; Kai Chen; Ziwei Liu; Dahua Lin; | |
1268 | Neural Dubber: Dubbing for Videos According to Scripts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Neural Dubber, the first neural network model to solve a novel automatic video dubbing (AVD) task: synthesizing human speech synchronized with the given video from the text. |
Chenxu Hu; Qiao Tian; Tingle Li; Wang Yuping; Yuxuan Wang; Hang Zhao; | |
1269 | Neural Bootstrapper Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this computational bottleneck, we propose a novel approach called Neural Bootstrapper (NeuBoots), which learns to generate bootstrapped neural networks through single model training. |
Minsuk Shin; Hyungjoo Cho; Hyun-seok Min; Sungbin Lim; | |
1270 | An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address an inherent difficulty in welfare-theoretic fair ML, by proposing an equivalently-axiomatically justified alternative setting, and studying the resulting computational and statistical learning questions. |
Cyrus Cousins; | |
1271 | HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this and advance ZSL, we propose a novel hierarchical semantic-visual adaptation (HSVA) framework. |
Shiming Chen; Guosen Xie; Yang Liu; Qinmu Peng; Baigui Sun; Hao Li; Xinge You; Ling Shao; | code |
1272 | Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By conditioning the process on its filtration, we introduce a family of higher order kernel mean embeddings (KMEs) that generalizes the notion of KME to capture additional information related to the filtration. |
Cristopher Salvi; Maud Lemercier; Chong Liu; Blanka Horvath; Theodoros Damoulas; Terry Lyons; | |
1273 | Low-Rank Subspaces in GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By contrast, this work introduces low-rank subspaces that enable more precise control of GAN generation. |
Jiapeng Zhu; Ruili Feng; Yujun Shen; Deli Zhao; Zheng-Jun Zha; Jingren Zhou; Qifeng Chen; | |
1274 | Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a model that learns the symplectic form from data using neural networks, thereby providing a method for learning Hamiltonian equations from data represented in general coordinate systems, which are not limited to the generalized coordinates and the generalized momenta. |
Yuhan Chen; Takashi Matsubara; Takaharu Yaguchi; | |
1275 | Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We make progress towards understanding this linear $Q^{\star}$ problem by investigating a new sampling protocol, which draws samples in an online/exploratory fashion but allows one to backtrack and revisit previous states. |
Gen Li; Yuxin Chen; Yuejie Chi; Yuantao Gu; Yuting Wei; | |
1276 | Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the task of medical image segmentation and adapt contrastive learning with meta-label annotations to scenarios where no additional unlabeled data is available. |
Jizong Peng; Ping Wang; Christian Desrosiers; Marco Pedersoli; | |
1277 | Reverse Engineering Recurrent Neural Networks with Jacobian Switching Linear Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new model that overcomes these limitations by co-training an RNN with a novel switching linear dynamical system (SLDS) formulation. |
Jimmy Smith; Scott Linderman; David Sussillo; | |
1278 | Learning-Augmented Dynamic Power Management with Multiple States Via New Ski Rental Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the online problem of minimizing power consumption in systems with multiple power-saving states. |
Antonios Antoniadis; Christian Coester; Marek Elias; Adam Polak; Bertrand Simon; | |
1279 | Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By utilizing our equivariant SVGD for training equivariant EBMs, we propose new ways of improving and scaling up training of energy based models. |
Priyank Jaini; Lars Holdijk; Max Welling; | |
1280 | Information Directed Sampling for Sparse Linear Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we explore the use of information-directed sampling (IDS), which naturally balances the information-regret trade-off. |
Botao Hao; Tor Lattimore; Wei Deng; | |
1281 | Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present non-asymptotic optimization guarantees of gradient descent methods for estimating structured transition matrices in high-dimensional vector autoregressive (VAR) models. |
Xiao Lv; Wei Cui; Yulong Liu; | |
1282 | Large-Scale Unsupervised Object Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel formulation of UOD as a ranking problem, amenable to the arsenal of distributed methods available for eigenvalue problems and link analysis. |
Van Huy Vo; Elena Sizikova; Cordelia Schmid; Patrick P�rez; Jean Ponce; | |
1283 | Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance. |
Jiehong Lin; Hongyang Li; Ke Chen; Jiangbo Lu; Kui Jia; | code |
1284 | Noisy Adaptation Generates L�vy Flights in Attractor Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we investigate how Lévy flights can be achieved in attractor neural networks. |
Xingsi Dong; Tianhao Chu; Tiejun Huang; Zilong Ji; Si Wu; | |
1285 | On Linear Stability of SGD and Input-Smoothness of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Together with the multiplicative structure, we identify the Sobolev regularization effect of SGD, i.e. SGD regularizes the Sobolev seminorms of the model function with respect to the input data. |
Chao Ma; Lexing Ying; | |
1286 | Joint Inference and Input Optimization in Equilibrium Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that there is a natural synergy between these two settings. |
Swaminathan Gurumurthy; Shaojie Bai; Zachary Manchester; J. Zico Kolter; | |
1287 | A Unified Framework for Bandit Multiple Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a unified, modular framework for bandit FDR control that emphasizes the decoupling of exploration and summarization of evidence. |
Ziyu Xu; Ruodu Wang; Aaditya Ramdas; | |
1288 | Recovering Latent Causal Factor for Generalization to Distributional Shifts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a Variational-Bayesian-based method to learn this invariance for prediction. |
Xinwei Sun; Botong Wu; Xiangyu Zheng; Chang Liu; Wei Chen; Tao Qin; Tie-Yan Liu; | code |
1289 | Graph Differentiable Architecture Search with Structure Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on our findings, we propose a Graph differentiable Architecture Search model with Structure Optimization (GASSO), which allows differentiable search of the architecture with gradient descent and is able to discover graph neural architectures with better performance through employing graph structure learning as a denoising process in the search procedure. |
Yijian Qin; Xin Wang; Zeyang Zhang; Wenwu Zhu; | |
1290 | Designing Counterfactual Generators Using Deep Model Inversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the case where we have access only to the trained deep classifier and not the actual training data. |
Jayaraman Thiagarajan; Vivek Sivaraman Narayanaswamy; Deepta Rajan; Jia Liang; Akshay Chaudhari; Andreas Spanias; | |
1291 | A Faster Maximum Cardinality Matching Algorithm with Applications in Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simplification of a recent algorithm (Lahn and Raghvendra, JoCG 2021) for the maximum cardinality matching problem and describe how a maximum cardinality matching in a $\delta$-disc graph can be computed asymptotically faster than $O(n^{3/2})$ time for any moderately dense point set. |
Nathaniel Lahn; Sharath Raghvendra; Jiacheng Ye; | |
1292 | Dynamic Population-based Meta-learning for Multi-agent Communication with Natural Language Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, our goal is to train agents that can coordinate with seen, unseen as well as human partners in a multi-agent communication environment involving natural language. |
Abhinav Gupta; Marc Lanctot; Angeliki Lazaridou; | |
1293 | Adversarial Neuron Pruning Purifies Backdoored Deep Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these observations, we propose a novel model repairing method, termed Adversarial Neuron Pruning (ANP), which prunes some sensitive neurons to purify the injected backdoor. |
Dongxian Wu; Yisen Wang; | |
1294 | Towards Robust and Reliable Algorithmic Recourse Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To the best of our knowledge, this work proposes the first ever solution to this critical problem. |
Sohini Upadhyay; Shalmali Joshi; Himabindu Lakkaraju; | |
1295 | Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel module named Neural Rule-Execution Tracking Machine (NRETM) that can be equipped into various transformer-based generators to leverage multiple rules simultaneously to guide the neural generation model for superior generation performance in an unified and scalable way. |
Yufei Wang; Can Xu; Huang Hu; Chongyang Tao; Stephen Wan; Mark Dras; Mark Johnson; Daxin Jiang; | |
1296 | Scalable Online Planning Via Reinforcement Learning Fine-Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. |
Arnaud Fickinger; Hengyuan Hu; Brandon Amos; Stuart Russell; Noam Brown; | |
1297 | Adversarial Regression with Doubly Non-negative Weighting Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel and coherent scheme for kernel-reweighted regression by reparametrizing the sample weights using a doubly non-negative matrix. |
Tam Le; Truyen Nguyen; Makoto Yamada; Jose Blanchet; Viet Anh Nguyen; | |
1298 | Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a scalable and learnable non-convex approach for high-dimensional RPCA problems, which we call Learned Robust PCA (LRPCA). |
HanQin Cai; Jialin Liu; Wotao Yin; | |
1299 | Proxy-Normalizing Activations to Match Batch Normalization While Removing Batch Dependence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate failure mode (i) without aggravating failure mode (ii), we introduce the technique "Proxy Normalization" that normalizes post-activations using a proxy distribution. |
Antoine Labatie; Dominic Masters; Zach Eaton-Rosen; Carlo Luschi; | |
1300 | Dynamic Bottleneck for Robust Self-Supervised Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle. |
Chenjia Bai; Lingxiao Wang; Lei Han; Animesh Garg; Jianye Hao; Peng Liu; Zhaoran Wang; | |
1301 | ProTo: Program-Guided Transformer for Program-Guided Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards learning general program executors to unify perception, reasoning, and decision making, we formulate program-guided tasks which require learning to execute a given program on the observed task specification. |
Zelin Zhao; Karan Samel; Binghong Chen; lee song; | |
1302 | An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. |
Tianpei Yang; Weixun Wang; Hongyao Tang; Jianye Hao; Zhaopeng Meng; Hangyu Mao; Dong Li; Wulong Liu; Yingfeng Chen; Yujing Hu; Changjie Fan; Chengwei Zhang; | |
1303 | Learning to Time-Decode in Spiking Neural Networks Through The Information Bottleneck Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, this work introduces a hybrid variational autoencoder architecture, consisting of an encoding SNN and a decoding Artificial Neural Network (ANN). |
Nicolas Skatchkovsky; Osvaldo Simeone; Hyeryung Jang; | |
1304 | NEO: Non Equilibrium Sampling on The Orbits of A Deterministic Transform Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel family of importance samplers (IS) and Markov chain Monte Carlo (MCMC) samplers is derived. |
Achille Thin; Yazid Janati El Idrissi; Sylvain Le Corff; Charles Ollion; Eric Moulines; Arnaud Doucet; Alain Durmus; Christian Robert; | |
1305 | Relaxing Local Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce two relaxed safety properties for classifiers that address this observation: (1) relaxed top-k robustness, which serves as the analogue of top-k accuracy; and (2) affinity robustness, which specifies which sets of labels must be separated by a robustness margin, and which can be $\epsilon$-close in $\ell_p$ space. |
Klas Leino; Matt Fredrikson; | |
1306 | Tuning Large Neural Networks Via Zero-Shot Hyperparameter Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This leads to a new HP tuning paradigm we call *$\mu$Transfer*: parametrize the target model in $\mu$P, tune the HP indirectly on a smaller model, and *zero-shot transfer* them to the full-sized model, i.e., without directly tuning the latter at all.We verify $\mu$Transfer on Transformer and ResNet. |
Ge Yang; Edward Hu; Igor Babuschkin; Szymon Sidor; Xiaodong Liu; David Farhi; Nick Ryder; Jakub Pachocki; Weizhu Chen; Jianfeng Gao; | |
1307 | Statistical Regeneration Guarantees of The Wasserstein Autoencoder with Latent Space Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To close this gap, in this paper, we investigate the statistical properties of WAE. |
Anish Chakrabarty; Swagatam Das; | |
1308 | Leveraging The Inductive Bias of Large Language Models for Abstract Textual Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP tasks, but also in the nontraditional task of training a symbolic reasoning engine. |
Christopher Rytting; David Wingate; | |
1309 | Differentiable Simulation of Soft Multi-body Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a method for differentiable simulation of soft articulated bodies. |
Yiling Qiao; Junbang Liang; Vladlen Koltun; Ming Lin; | |
1310 | Good Classification Measures and How to Find Them Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Can we say that some of them are better than others, or, ideally, choose one measure that is best in all situations? To answer this question, we conduct a systematic analysis of classification performance measures: we formally define a list of desirable properties and theoretically analyze which measures satisfy which properties. |
Martijn G�sgens; Anton Zhiyanov; Aleksey Tikhonov; Liudmila Prokhorenkova; | |
1311 | Distilling Robust and Non-Robust Features in Adversarial Examples By Information Bottleneck Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a way of explicitly distilling feature representation into the robust and non-robust features, using Information Bottleneck. |
Junho Kim; Byung-Kwan Lee; Yong Man Ro; | |
1312 | Vector-valued Gaussian Processes on Riemannian Manifolds Via Gauge Independent Projected Kernels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose techniques that generalize this class to model vector fields on Riemannian manifolds, which are important in a number of application areas in the physical sciences. |
Michael Hutchinson; Alexander Terenin; Viacheslav Borovitskiy; So Takao; Yee Teh; Marc Deisenroth; | |
1313 | On The Representation Power of Set Pooling Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study the expressive power of such networks and prove new cardinality-agnostic universality results for point clouds as well as extensions of these models beyond point clouds. |
Christian Bueno; Alan Hylton; | |
1314 | Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the issue of safety in reinforcement learning. |
Tao Liu; Ruida Zhou; Dileep Kalathil; Panganamala Kumar; Chao Tian; | |
1315 | A Prototype-Oriented Framework for Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. |
Korawat Tanwisuth; Xinjie Fan; Huangjie Zheng; Shujian Zhang; Hao Zhang; Bo Chen; Mingyuan Zhou; | |
1316 | Mining The Benefits of Two-stage and One-stage HOI Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to explore the essential pros and cons of two-stage and one-stage methods. |
Aixi Zhang; Yue Liao; Si Liu; Miao Lu; Yongliang Wang; Chen Gao; XIAOBO LI; | |
1317 | Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN). |
Ying Sun; Hengshu Zhu; Chuan Qin; Fuzhen Zhuang; Qing He; Hui Xiong; | |
1318 | Risk-averse Heteroscedastic Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we propose a novel risk-averse heteroscedastic Bayesian optimization algorithm (RAHBO) that aims to identify a solution with high return and low noise variance, while learning the noise distribution on the fly. |
Anastasia Makarova; Ilnura Usmanova; Ilija Bogunovic; Andreas Krause; | |
1319 | Invertible DenseNets with Concatenated LipSwish Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient extension of Residual Flows. |
Yura Perugachi-Diaz; Jakub Tomczak; Sandjai Bhulai; | |
1320 | Topological Detection of Trojaned Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Guided by basic neuroscientific principles, we discover subtle — yet critical — structural deviation characterizing Trojaned models. |
Songzhu Zheng; Yikai Zhang; Hubert Wagner; Mayank Goswami; Chao Chen; | |
1321 | Provably Strict Generalisation Benefit for Invariance in Kernel Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we build on the function space perspective of Elesedy and Zaidi [8] to derive a strictly non-zero generalisation benefit of incorporating invariance in kernel ridge regression when the target is invariant to the action of a compact group. |
Bryn Elesedy; | |
1322 | Formalizing The Generalization-Forgetting Trade-off in Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formulate the continual learning (CL) problem via dynamic programming and model the trade-off between catastrophic forgetting and generalization as a two-player sequential game. |
Krishnan Raghavan; Prasanna Balaprakash; | |
1323 | Risk-Aware Transfer in Reinforcement Learning Using Successor Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the problem of transferring policies between tasks in a common domain that differ only in their reward functions, in which risk is measured by the variance of reward streams. |
Michael Gimelfarb; Andre Barreto; Scott Sanner; Chi-Guhn Lee; | |
1324 | Causal Inference for Event Pairs in Multivariate Point Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a formalization for causal inference between pairs of event variables in multivariate recurrent event streams by extending Rubin’s framework for the average treatment effect (ATE) and propensity scores to multivariate point processes. |
Tian Gao; Dharmashankar Subramanian; Debarun Bhattacharjya; Xiao Shou; Nicholas Mattei; Kristin Bennett; | |
1325 | Evaluating Model Performance Under Worst-case Subpopulations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards assessing distributional robustness, we study the worst-case performance of a model over all subpopulations of a given size, defined with respect to core attributes $Z$. |
Mike Li; Hongseok Namkoong; Shangzhou Xia; | |
1326 | Privately Publishable Per-instance Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the per-instance privacy loss of releasing a private empirical risk minimizer learned via objective perturbation, and propose a group of methods to privately and accurately publish the pDP losses at little to no additional privacy cost. |
Rachel Redberg; Yu-Xiang Wang; | |
1327 | Understanding The Limits of Unsupervised Domain Adaptation Via Data Poisoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we prove a simple lower bound on the target domain error that complements the existing upper bound. |
Akshay Mehra; Bhavya Kailkhura; Pin-Yu Chen; Jihun Hamm; | |
1328 | Coresets for Clustering with Missing Values Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide the first coreset for clustering points in $\mathbb{R}^d$ that have multiple missing values (coordinates). |
Vladimir braverman; Shaofeng Jiang; Robert Krauthgamer; Xuan Wu; | |
1329 | Boosting with Multiple Sources Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce and analyze a new boosting algorithm, MULTIBOOST, for this scenario and show that it benefits from favorable theoretical guarantees. |
Corinna Cortes; Mehryar Mohri; Dmitry Storcheus; Ananda Theertha Suresh; | |
1330 | Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As each location on the encoder’s output corresponds to a local patch of the semantic labels, in this work, we represent these local patches of labels with compact neural networks. |
Bowen Zhang; Yifan liu; Zhi Tian; Chunhua Shen; | |
1331 | Dense Keypoints Via Multiview Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new end-to-end semi-supervised framework to learn a dense keypoint detector using unlabeled multiview images. |
Zhixuan Yu; Haozheng Yu; Long Sha; Sujoy Ganguly; Hyun Park; | |
1332 | Scatterbrain: Unifying Sparse and Low-rank Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the classical robust-PCA algorithm for sparse and low-rank decomposition, we propose Scatterbrain, a novel way to unify sparse (via locality sensitive hashing) and low-rank (via kernel feature map) attention for accurate and efficient approximation. |
Beidi Chen; Tri Dao; Eric Winsor; Zhao Song; Atri Rudra; Christopher R�; | |
1333 | PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, to better serve for part-based conceptual, relational and physical reasoning, we introduce a new large-scale diagnostic visual reasoning dataset named PTR. |
Yining Hong; Li Yi; Josh Tenenbaum; Antonio Torralba; Chuang Gan; | |
1334 | Property-Aware Relation Networks for Few-Shot Molecular Property Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Property-Aware Relation networks (PAR) to handle this problem. |
Yaqing Wang; ABULIKEMU ABUDUWEILI; Quanming Yao; Dejing Dou; | |
1335 | Differentially Private Learning with Adaptive Clipping Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method wherein instead of a fixed clipping norm, one clips to a value at a specified quantile of the update norm distribution, where the value at the quantile is itself estimated online, with differential privacy. |
Galen Andrew; Om Thakkar; Swaroop Ramaswamy; Brendan McMahan; | |
1336 | Can Less Be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we answer the question of when inserting label noise (less informative labels) can instead return us more accurate and fair models. |
Yang Liu; Jialu Wang; | |
1337 | Projected GANs Converge Faster Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. |
Axel Sauer; Kashyap Chitta; Jens M�ller; Andreas Geiger; | |
1338 | Generating High-Quality Explanations for Navigation in Partially-Revealed Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach for generating natural language explanations of high-level behavior of autonomous agents navigating in partially-revealed environments. |
Gregory Stein; | |
1339 | De-randomizing MCMC Dynamics with The Diffusion Stein Operator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose de-randomized kernel-based particle samplers to all diffusion-based samplers known as MCMC dynamics. |
Zheyang Shen; Markus Heinonen; Samuel Kaski; | |
1340 | Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, we propose Gated $L_0$ Regularized Dynamics (GateL0RD), a novel recurrent architecture that incorporates the inductive bias to maintain stable, sparsely changing latent states. |
Christian Gumbsch; Martin V. Butz; Georg Martius; | |
1341 | PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose PreferenceNet, an extension of existing neural-network-based auction mechanisms to encode constraints using (potentially human-provided) exemplars of desirable allocations. |
Neehar Peri; Michael Curry; Samuel Dooley; John Dickerson; | |
1342 | Large-Scale Learning with Fourier Features and Tensor Decompositions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our approach we overcome said curse of dimensionality by exploiting the tensor product structure of deterministic Fourier features, which enables us to represent the model parameters as a low-rank tensor decomposition. |
Frederiek Wesel; Kim Batselier; | |
1343 | Hash Layers For Large Sparse Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the training of sparse layers that use different parameters for different inputs based on hashing in large Transformer models. |
Stephen Roller; Sainbayar Sukhbaatar; arthur szlam; Jason Weston; | |
1344 | Sliced Mutual Information: A Scalable Measure of Statistical Dependence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by statistical scalability to high dimensions, this paper proposes sliced MI (SMI) as a surrogate measure of dependence. |
Ziv Goldfeld; Kristjan Greenewald; | |
1345 | Emergent Communication Under Varying Sizes and Connectivities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This research provides an analytical study of the shared emergent language within the group communication settings of different sizes and connectivities. |
Jooyeon Kim; Alice Oh; | |
1346 | Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce Sample Average Uncertainty (SAU), a simple and efficient uncertainty measure for contextual bandits. |
Rong Zhu; Mattia Rigotti; | code |
1347 | Regret Minimization Experience Replay in Off-Policy Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we start from the regret minimization objective, and obtain an optimal prioritization strategy for Bellman update that can directly maximize the return of the policy. |
Xu-Hui Liu; Zhenghai Xue; Jingcheng Pang; Shengyi Jiang; Feng Xu; Yang Yu; | |
1348 | Relative Uncertainty Learning for Facial Expression Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To quantify these uncertainties and achieve good performance under noisy data, we regard uncertainty as a relative concept and propose an innovative uncertainty learning method called Relative Uncertainty Learning (RUL). |
Yuhang Zhang; Chengrui Wang; Weihong Deng; | code |
1349 | An Information-theoretic Approach to Distribution Shifts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we describe the problem of data shift from an information-theoretic perspective by (i) identifying and describing the different sources of error, (ii) comparing some of the most promising objectives explored in the recent domain generalization and fair classification literature. |
Marco Federici; Ryota Tomioka; Patrick Forr�; | |
1350 | TRS: Transferability Reduced Ensemble Via Promoting Gradient Diversity and Model Smoothness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by our theoretical analysis, we propose an effective Transferability Reduced Smooth (TRS) ensemble training strategy to train a robust ensemble with low transferability by enforcing both gradient orthogonality and model smoothness between base models. |
Zhuolin Yang; Linyi Li; Xiaojun Xu; Shiliang Zuo; Qian Chen; Pan Zhou; Benjamin Rubinstein; Ce Zhang; Bo Li; | |
1351 | Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, motivated by recent advances in deep generative models, we provide recovery guarantees with near-optimal sample complexity for phase retrieval with generative priors. |
Zhaoqiang Liu; Subhroshekhar Ghosh; Jonathan Scarlett; | |
1352 | Moser Flow: Divergence-based Generative Modeling on Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Moser Flow (MF), a new class of generative models within the family of continuous normalizing flows (CNF). |
Noam Rozen; Aditya Grover; Maximilian Nickel; Yaron Lipman; | |
1353 | Structure-Aware Random Fourier Kernel for Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel structure-aware random Fourier (SRF) kernel for GPs that brings several benefits when modeling graph-structured data. |
Jinyuan Fang; Qiang Zhang; Zaiqiao Meng; Shangsong Liang; | |
1354 | Diffusion Schr�dinger Bridge with Applications to Score-Based Generative Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Diffusion SB (DSB), an original approximation of the Iterative Proportional Fitting (IPF) procedure to solve the SB problem, and provide theoretical analysis along with generative modeling experiments. |
Valentin De Bortoli; James Thornton; Jeremy Heng; Arnaud Doucet; | |
1355 | Improving Transferability of Representations Via Augmentation-Aware Self-Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our intuition is that AugSelf encourages to preserve augmentation-aware information in learned representations, which could be beneficial for their transferability. |
Hankook Lee; Kibok Lee; Kimin Lee; Honglak Lee; Jinwoo Shin; | code |
1356 | Long-Short Transformer: Efficient Transformers for Language and Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. |
Chen Zhu; Wei Ping; Chaowei Xiao; Mohammad Shoeybi; Tom Goldstein; Anima Anandkumar; Bryan Catanzaro; | code |
1357 | Post-Training Sparsity-Aware Quantization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a sparsity-aware quantization (SPARQ) method, in which the unstructured and dynamic activation sparsity is leveraged in different representation granularities. |
Gil Shomron; Freddy Gabbay; Samer Kurzum; Uri Weiser; | |
1358 | The Implicit Bias of Minima Stability: A View from Function Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study the effect that this mechanism has on the function implemented by the trained model. |
Rotem Mulayoff; Tomer Michaeli; Daniel Soudry; | |
1359 | Breaking The Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome such a large sample size barrier to efficient RL, we design a novel model-free algorithm, with space complexity $O(SAH)$, that achieves near-optimal regret as soon as the sample size exceeds the order of $SA\,\mathrm{poly}(H)$. |
Gen Li; Laixi Shi; Yuxin Chen; Yuantao Gu; Yuejie Chi; | |
1360 | Robust Auction Design in The Auto-bidding World Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on value maximizing bidders with return on spend constraints—a paradigm that has drawn considerable attention recently as more advertisers adopt auto-bidding algorithms in advertising platforms—and show that the introduction of reserve prices has a novel impact on the market. |
Santiago Balseiro; Yuan Deng; Jieming Mao; Vahab Mirrokni; Song Zuo; | |
1361 | Weighted Model Estimation for Offline Model-based Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the artificial weight, this paper defines a loss function for offline MBRL and presents an algorithm to optimize it. |
Toru Hishinuma; Kei Senda; | |
1362 | Practical, Provably-Correct Interactive Learning in The Realizable Setting: The Power of True Believers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider interactive learning in the realizable setting and develop a general framework to handle problems ranging from best arm identification to active classification. |
Julian Katz-Samuels; Blake Mason; Kevin G. Jamieson; Rob Nowak; | |
1363 | Deconditional Downscaling with Gaussian Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Bayesian formulation of deconditioning which naturally recovers the initial reproducing kernel Hilbert space formulation from Hsu and Ramos (2019). |
Siu Lun Chau; Shahine Bouabid; Dino Sejdinovic; | |
1364 | Image Generation Using Continuous Filter Atoms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we model the subspace of convolutional filters with a neural ordinary differential equation (ODE) to enable gradual changes in generated images. |
Ze Wang; Seunghyun Hwang; Zichen Miao; Qiang Qiu; | |
1365 | Latent Equilibrium: Arbitrarily Fast Computation with Arbitrarily Slow Neurons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Latent Equilibrium, a new framework for inference and learning in networks of slow components which avoids these issues by harnessing the ability of biological neurons to phase-advance their output with respect to their membrane potential. |
Paul Haider; Benjamin Ellenberger; Laura Kriener; Jakob Jordan; Walter Senn; Mihai Petrovici; | |
1366 | Learning Fast-Inference Bayesian Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose new methods for learning Bayesian networks (BNs) that reliably support fast inference. |
Vaidyanathan Peruvemba Ramaswamy; Stefan Szeider; | |
1367 | Per-Pixel Classification Is Not All You Need for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. |
Bowen Cheng; Alex Schwing; Alexander Kirillov; | |
1368 | Deep Markov Factor Analysis: Towards Concurrent Temporal and Spatial Analysis of FMRI Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present deep Markov factor analysis (DMFA), a generative model that employs Markov property in a chain of low dimensional temporal embeddings together with spatial inductive assumptions, all related through neural networks, to capture temporal dynamics in functional magnetic resonance imaging (fMRI) data, and tackle their high spatial dimensionality, respectively. |
Amirreza Farnoosh; Sarah Ostadabbas; | |
1369 | BooVAE: Boosting Approach for Continual Learning of VAE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the learnable prior, we introduce an end-to-end approach for continual learning of VAEs and provide empirical studies on commonly used benchmarks (MNIST, Fashion MNIST, NotMNIST) and CelebA datasets. |
Evgenii Egorov; Anna Kuzina; Evgeny Burnaev; | |
1370 | Handling Long-tailed Feature Distribution in AdderNets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To locate the potential problem of ANNs, we focus on the property difference due to similarity measurement. |
Minjing Dong; Yunhe Wang; Xinghao Chen; Chang Xu; | |
1371 | Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge such a gap, we propose a SAFARI (peSsimistic meAn-Field vAlue iteRatIon) algorithm for off-line MF-MARL, which only requires a handful of pre-collected experience data. |
Minshuo Chen; Yan Li; Ethan Wang; Zhuoran Yang; Zhaoran Wang; Tuo Zhao; | |
1372 | A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we derive a novel law of iterated logarithm for a family of distributed nonlinear stochastic approximation schemes that is useful in MARL. |
Gugan Chandrashekhar Thoppe; Bhumesh Kumar; | |
1373 | MOMA: Multi-Object Multi-Actor Activity Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces Activity Parsing as the overarching task of temporal segmentation and classification of activities, sub-activities, atomic actions, along with an instance-level understanding of actors, objects, and their relationships in videos. |
Zelun Luo; Wanze Xie; Siddharth Kapoor; Yiyun Liang; Michael Cooper; Juan Carlos Niebles; Ehsan Adeli; Fei-Fei Li; | |
1374 | The Pareto Frontier of Model Selection for General Contextual Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: It asks whether it is possible to obtain simultaneously the optimal single algorithm guarantees over all policies in a nested sequence of policy classes, or if otherwise this is possible for a trade-off $\alpha\in[\frac{1}{2},1)$ between complexity term and time: $\ln(|\Pi_m|)^{1-\alpha}T^\alpha$. We give a disappointing answer to this question. |
Teodor Vanislavov Marinov; Julian Zimmert; | |
1375 | Teaching An Active Learner with Contrastive Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we view this information in the form of an additional contrastive example ($\{x^c, y^c\}$) where $x^c$ is picked from a set constrained by $x^q$ (e.g., dissimilar instances with the same label). |
Chaoqi Wang; Adish Singla; Yuxin Chen; | |
1376 | Structured Denoising Diffusion Models in Discrete State-Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce Discrete Denoising Diffusion Probabilistic Models (D3PMs), diffusion-like generative models for discrete data that generalize the multinomial diffusion model of Hoogeboom et al. [2021], by going beyond corruption processes with uniform transition probabilities. |
Jacob Austin; Daniel Johnson; Rianne van den Berg; Jonathan Ho; Daniel Tarlow; | |
1377 | Emergent Communication of Generalizations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote such skills, we propose games that require communicating generalizations over sets of objects representing abstract visual concepts, optionally with separate contexts for each agent. |
Jesse Mu; Noah Goodman; | |
1378 | Distributed Machine Learning with Sparse Heterogeneous Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method based on Basis Pursuit Denoising with a total variation penalty, and provide finite sample guarantees for sub-Gaussian design matrices. |
Dominic Richards; Sahand Negahban; Patrick Rebeschini; | |
1379 | Manipulating SGD with Data Ordering Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a novel class of training-time attacks that require no changes to the underlying dataset or model architecture, but instead only change the order in which data are supplied to the model. |
I Shumailov; Zakhar Shumaylov; Dmitry Kazhdan; Yiren Zhao; Nicolas Papernot; Murat A. Erdogdu; Ross Anderson; | |
1380 | Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. |
Maximilian Stadler; Bertrand Charpentier; Simon Geisler; Daniel Z�gner; Stephan G�nnemann; | |
1381 | Locality Sensitive Teaching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel teaching framework, Locality Sensitive Teaching (LST), based on locality sensitive sampling, to overcome these challenges. |
Zhaozhuo Xu; Beidi Chen; Chaojian Li; Weiyang Liu; Le Song; Yingyan Lin; Anshumali Shrivastava; | |
1382 | No-Press Diplomacy from Scratch Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe an algorithm for action exploration and equilibrium approximation in games with combinatorial action spaces. |
Anton Bakhtin; David Wu; Adam Lerer; Noam Brown; | |
1383 | Remember What You Want to Forget: Algorithms for Machine Unlearning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of unlearning datapoints from a learnt model. |
Ayush Sekhari; Jayadev Acharya; Gautam Kamath; Ananda Theertha Suresh; | |
1384 | Learning Latent Causal Graphs Via Mixture Oracles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of reconstructing a causal graphical model from data in the presence of latent variables. |
Bohdan Kivva; Goutham Rajendran; Pradeep Ravikumar; Bryon Aragam; | |
1385 | ErrorCompensatedX: Error Compensation for Variance Reduced Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: So, we propose ErrorCompensateX, which uses the compression error from the previous two steps. |
Hanlin Tang; Yao Li; Ji Liu; Ming Yan; | |
1386 | Deep Contextual Video Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a deep contextual video compression framework to enable a paradigm shift from predictive coding to conditional coding. |
Jiahao Li; Bin Li; Yan Lu; | |
1387 | On The Frequency Bias of Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We take a sober look at those explanations and provide insights on what makes proposed measures against high-frequency artifacts effective. |
Katja Schwarz; Yiyi Liao; Andreas Geiger; | |
1388 | Learning Curves of Generic Features Maps for Realistic Datasets with A Teacher-student Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a Gaussian covariate generalisation of the model where the teacher and student can act on different spaces, generated with fixed, but generic feature maps. |
Bruno Loureiro; Cedric Gerbelot; Hugo Cui; Sebastian Goldt; Florent Krzakala; Marc Mezard; Lenka Zdeborov�; | |
1389 | It Has Potential: Gradient-Driven Denoisers for Convergent Solutions to Inverse Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce image denoisers derived as the gradients of smooth scalar-valued deep neural networks, acting as potentials. |
Regev Cohen; Yochai Blau; Daniel Freedman; Ehud Rivlin; | |
1390 | Training Over-parameterized Models with Non-decomposable Objectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a remedy, we propose new cost- sensitive losses that extend the classical idea of logit adjustment to handle more general cost matrices. |
Harikrishna Narasimhan; Aditya K. Menon; | |
1391 | Reinforcement Learning for Optimization of Variational Quantum Circuit Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a reinforcement learning algorithm that autonomously explores the space of possible ansatzes, identifying economic circuits which still yield accurate ground energy estimates. |
Mateusz Ostaszewski; Lea Trenkwalder; Wojciech Masarczyk; Eleanor Scerri; Vedran Dunjko; | |
1392 | Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we lift that restriction by proposing Moshpit All-Reduce – an iterative averaging protocol that exponentially converges to the global average. |
Max Ryabinin; Eduard Gorbunov; Vsevolod Plokhotnyuk; Gennady Pekhimenko; | |
1393 | IRM—when It Works and When It Doesn't: A Test Case of Natural Language Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the applicability of IRM to bias mitigation-a special case of o.o.d generalization-in increasingly naturalistic settings and deep models. |
Yana Dranker; He He; Yonatan Belinkov; | |
1394 | Self-Supervised Learning Disentangled Group Representation As Feature Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To break the limitation, we propose an iterative SSL algorithm: Iterative Partition-based Invariant Risk Minimization (IP-IRM), which successfully grounds the abstract semantics and the group acting on them into concrete contrastive learning. |
Tan Wang; Zhongqi Yue; Jianqiang Huang; Qianru Sun; Hanwang Zhang; | code |
1395 | SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper explores how saliency explanations can be used to improve KG-augmented models’ performance. |
Aaron Chan; Jiashu Xu; Boyuan Long; Soumya Sanyal; Tanishq Gupta; Xiang Ren; | |
1396 | Supervising The Transfer of Reasoning Patterns in VQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method for knowledge transfer based on a regularization term in our loss function, supervising the sequence of required reasoning operations. |
Corentin Kervadec; Christian Wolf; Grigory Antipov; Moez Baccouche; Madiha Nadri; | |
1397 | Conformal Bayesian Computation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop scalable methods for producing conformal Bayesian predictive intervals with finite sample calibration guarantees. |
Edwin Fong; Chris C. Holmes; | |
1398 | A Unified Approach to Fair Online Learning Via Blackwell Approachability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a setting and a general approach to fair online learning with stochastic sensitive and non-sensitive contexts.The setting is a repeated game between the Player and Nature, where at each stage both pick actions based on the contexts. |
Evgenii Chzhen; Christophe Giraud; Gilles Stoltz; | |
1399 | Training Neural Networks Is ER-complete Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We determine the algorithmic complexity of this fundamental problem precisely, by showing that it is $\exists\mathbb R$-complete. |
Mikkel Abrahamsen; Linda Kleist; Tillmann Miltzow; | |
1400 | Understanding The Under-Coverage Bias in Uncertainty Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a rigorous theoretical study on the coverage of uncertainty estimation algorithms in learning quantiles. |
Yu Bai; Song Mei; Huan Wang; Caiming Xiong; | |
1401 | Decentralized Q-learning in Zero-sum Markov Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a radically uncoupled Q-learning dynamics that is both rational and convergent: the learning dynamics converges to the best response to the opponent’s strategy when the opponent follows an asymptotically stationary strategy; when both agents adopt the learning dynamics, they converge to the Nash equilibrium of the game. |
Muhammed Sayin; Kaiqing Zhang; David Leslie; Tamer Basar; Asuman Ozdaglar; | |
1402 | Fast Certified Robust Training with Short Warmup Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we identify two important issues in existing methods, namely exploded bounds at initialization, and the imbalance in ReLU activation states and improve IBP training. |
Zhouxing Shi; Yihan Wang; Huan Zhang; Jinfeng Yi; Cho-Jui Hsieh; | code |
1403 | Vector-valued Distance and Gyrocalculus on The Space of Symmetric Positive Definite Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the use of the vector-valued distance to compute distances and extract geometric information from the manifold of symmetric positive definite matrices (SPD), and develop gyrovector calculus, constructing analogs of vector space operations in this curved space. |
Federico Lopez; Beatrice Pozzetti; Steve Trettel; Michael Strube; Anna Wienhard; | |
1404 | Improved Transformer for High-Resolution GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce two key ingredients to Transformer to address this challenge. |
Long Zhao; Zizhao Zhang; Ting Chen; Dimitris Metaxas; Han Zhang; | |
1405 | Learning High-Precision Bounding Box for Rotated Object Detection Via Kullback-Leibler Divergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection. |
Xue Yang; Xiaojiang Yang; Jirui Yang; Qi Ming; Wentao Wang; Qi Tian; Junchi Yan; | code |
1406 | On Locality of Local Explanation Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence we consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values. |
Sahra Ghalebikesabi; Lucile Ter-Minassian; Karla DiazOrdaz; Chris C. Holmes; | |
1407 | FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Curriculum Pseudo Labeling (CPL), a curriculum learning approach to leverage unlabeled data according to the model’s learning status. |
Bowen Zhang; Yidong Wang; Wenxin Hou; HAO WU; Jindong Wang; Manabu Okumura; Takahiro Shinozaki; | code |
1408 | Relative Flatness and Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the connection between flatness and generalization by relating it to the interpolation from representative data, deriving notions of representativeness, and feature robustness. |
Henning Petzka; Michael Kamp; Linara Adilova; Cristian Sminchisescu; Mario Boley; | |
1409 | The Image Local Autoregressive Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we propose a novel model — image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis. |
Chenjie Cao; Yuxin Hong; Xiang Li; Chengrong Wang; Chengming Xu; Yanwei Fu; Xiangyang Xue; | |
1410 | Towards Multi-Grained Explainability for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we exploit the pre-training and ?ne-tuning idea to develop our explainer and generate multi-grained explanations. |
Xiang Wang; Yingxin Wu; An Zhang; Xiangnan He; Tat-Seng Chua; | code |
1411 | Behavior From The Void: Unsupervised Active Pre-Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new unsupervised pre-training method for reinforcement learning called APT, which stands for Active Pre-Training. |
Hao Liu; Pieter Abbeel; | |
1412 | Autonomous Reinforcement Learning Via Subgoal Curricula Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Value-accelerated Persistent Reinforcement Learning (VaPRL), which generates a curriculum of initial states such that the agent can bootstrap on the success of easier tasks to efficiently learn harder tasks. |
Archit Sharma; Abhishek Gupta; Sergey Levine; Karol Hausman; Chelsea Finn; | |
1413 | Statistically and Computationally Efficient Linear Meta-representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand and explain the success of popular meta-representation learning approaches such as ANIL, MetaOptNet, R2D2, and OML, we study a alternating gradient-descent minimization (AltMinGD) method (and its variant alternating minimization (AltMin)) which underlies the aforementioned methods. |
Kiran K. Thekumparampil; Prateek Jain; Praneeth Netrapalli; Sewoong Oh; | |
1414 | Decentralized Learning in Online Queuing Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore consider cooperative queues and propose the first learning decentralized algorithm guaranteeing stability of the system as long as the ratio of rates is larger than $1$, thus reaching performances comparable to centralized strategies. |
Flore Sentenac; Etienne Boursier; Vianney Perchet; | |
1415 | Explainable Semantic Space By Grounding Language to Vision with Cross-Modal Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this notion and recent work in vision-language learning, we design a two-stream model for grounding language learning in vision. |
Yizhen Zhang; Minkyu Choi; Kuan Han; Zhongming Liu; | |
1416 | BulletTrain: Accelerating Robust Neural Network Training Via Boundary Example Mining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To combat this inefficiency, we propose BulletTrain, a boundary example mining technique to drastically reduce the computational cost of robust training. |
Weizhe Hua; Yichi Zhang; Chuan Guo; Zhiru Zhang; G. Edward Suh; | |
1417 | Neural Distance Embeddings for Biological Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Neural Distance Embeddings (NeuroSEED), a general framework to embed sequences in geometric vector spaces, and illustrate the effectiveness of the hyperbolic space that captures the hierarchical structure and provides an average 38% reduction in embedding RMSE against the best competing geometry. |
Gabriele Corso; Zhitao Ying; Michal P�ndy; Petar Velickovic; Jure Leskovec; Pietro Li�; | |
1418 | Fitting Summary Statistics of Neural Data with A Differentiable Spiking Network Simulator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To correct for this, we suggest to augment the log-likelihood with terms that measure the dissimilarity between simulated and recorded activity. This dissimilarity is defined via summary statistics commonly used in neuroscience and the optimization is efficient because it relies on back-propagation through the stochastically simulated spike trains. |
Guillaume Bellec; Shuqi Wang; Alireza Modirshanechi; Johanni Brea; Wulfram Gerstner; | |
1419 | PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents Via Personalized Simulators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose PerSim, a model-based offline RL approach which first learns a personalized simulator for each agent by collectively using the historical trajectories across all agents, prior to learning a policy. |
Anish Agarwal; Abdullah Alomar; Varkey Alumootil; Devavrat Shah; Dennis Shen; Zhi Xu; Cindy Yang; | |
1420 | Online Sign Identification: Minimization of The Number of Errors in Thresholding Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a large family of algorithms (containing most existing relevant ones), inspired by the Frank-Wolfe algorithm, and provide a thorough yet generic analysis of their performance. |
reda ouhamma; R�my Degenne; Vianney Perchet; Pierre Gaillard; | |
1421 | All Tokens Matter: Token Labeling for Training Better Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present token labeling—a new training objective for training high-performance vision transformers (ViTs). |
Zi-Hang Jiang; Qibin Hou; Li Yuan; Daquan Zhou; Yujun Shi; Xiaojie Jin; Anran Wang; Jiashi Feng; | |
1422 | Partition and Code: Learning How to Compress Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims to establish the necessary principles a lossless graph compression method should follow to approach the entropy storage lower bound. |
Georgios Bouritsas; Andreas Loukas; Nikolaos Karalias; Michael Bronstein; | |
1423 | Knowledge-inspired 3D Scene Graph Prediction in Point Cloud Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike conventional methods that learn knowledge embedding and regular patterns from encoded visual information, we propose to suppress the misunderstandings caused by appearance similarities and other perceptual confusion. |
Shoulong Zhang; shuai li; Aimin Hao; Hong Qin; | |
1424 | Online Variational Filtering and Parameter Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a variational method for online state estimation and parameter learning in state-space models (SSMs), a ubiquitous class of latent variable models for sequential data. |
Andrew Campbell; Yuyang Shi; Thomas Rainforth; Arnaud Doucet; | |
1425 | Heavy Ball Neural Ordinary Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the continuous limit of the classical momentum accelerated gradient descent, to improve neural ODEs (NODEs) training and inference. |
Hedi Xia; Vai Suliafu; Hangjie Ji; Tan Nguyen; Andrea Bertozzi; Stanley Osher; Bao Wang; | code |
1426 | Structure Learning in Polynomial Time: Greedy Algorithms, Bregman Information, and Exponential Families Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide new insight into this phenomenon by studying a general greedy score-based algorithm for learning DAGs. |
Goutham Rajendran; Bohdan Kivva; Ming Gao; Bryon Aragam; | |
1427 | On The Sample Complexity of Learning Under Geometric Stability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the sample complexity of learning problems where the target function presents such invariance and stability properties, by considering spherical harmonic decompositions of such functions on the sphere. |
Alberto Bietti; Luca Venturi; Joan Bruna; | |
1428 | SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose SIMILAR (Submodular Information Measures based actIve LeARning), a unified active learning framework using recently proposed submodular information measures (SIM) as acquisition functions. |
Suraj Kothawade; Nathan Beck; Krishnateja Killamsetty; Rishabh Iyer; | |
1429 | Monte Carlo Tree Search With Iteratively Refining State Abstractions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a method, called abstraction refining, for extending MCTS to stochastic environments which, unlike progressive widening, leverages the geometry of the state space. |
Samuel Sokota; Caleb Ho; Zaheen Ahmad; J. Zico Kolter; | |
1430 | Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the relationship between the weight loss landscape and sensitivity-stability in the continual learning scenario, based on which, we propose a novel method, Flattening Sharpness for Dynamic Gradient Projection Memory (FS-DGPM). |
Danruo DENG; Guangyong Chen; Jianye Hao; Qiong Wang; Pheng-Ann Heng; | |
1431 | Taxonomizing Local Versus Global Structure in Neural Network Loss Landscapes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we perform a detailed empirical analysis of the loss landscape structure of thousands of neural network models, systematically varying learning tasks, model architectures, and/or quantity/quality of data. |
Yaoqing Yang; Liam Hodgkinson; Ryan Theisen; Joe Zou; Joseph E. Gonzalez; Kannan Ramchandran; Michael W. Mahoney; | |
1432 | Learning Models for Actionable Recourse Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel algorithm that leverages adversarial training and PAC confidence sets to learn models that theoretically guarantee recourse to affected individuals with high probability without sacrificing accuracy. |
Alexis Ross; Himabindu Lakkaraju; Osbert Bastani; | |
1433 | Efficient and Accurate Gradients for Neural SDEs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, this has previously suffered from severe speed and accuracy issues, due to high computational complexity, numerical errors in the SDE solve, and the cost of reconstructing Brownian motion. Here, we make several technical innovations to overcome these issues. |
Patrick Kidger; James Foster; Xuechen (Chen) Li; Terry Lyons; | |
1434 | EIGNN: Efficient Infinite-Depth Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN), to efficiently capture very long-range dependencies. |
Juncheng Liu; Kenji Kawaguchi; Bryan Hooi; Yiwei Wang; Xiaokui Xiao; | |
1435 | Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we approach this problem from a dynamical systems theory perspective and represent stochastic optimization algorithms as \emph{random iterated function systems} (IFS). |
Alexander Camuto; George Deligiannidis; Murat A. Erdogdu; Mert Gurbuzbalaban; Umut Simsekli; Lingjiong Zhu; | |
1436 | An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend finite ReLU BNNs with infinite ReLU features via the GP and show that the resulting model is asymptotically maximally uncertain far away from the data while the BNNs’ predictive power is unaffected near the data. |
Agustinus Kristiadi; Matthias Hein; Philipp Hennig; | |
1437 | Bandit Phase Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a bandit version of phase retrieval where the learner chooses actions $(A_t)_{t=1}^n$ in the $d$-dimensional unit ball and the expected reward is $\langle{A_t, \theta_\star \rangle^2$ with $\theta_\star \in \mathbb R^d$ an unknown parameter vector. |
Tor Lattimore; Botao Hao; | |
1438 | Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give lower bounds on the performance of two of the most popular sampling methods in practice, the Metropolis-adjusted Langevin algorithm (MALA) and multi-step Hamiltonian Monte Carlo (HMC) with a leapfrog integrator, when applied to well-conditioned distributions. |
Yin Tat Lee; Ruoqi Shen; Kevin Tian; | |
1439 | Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on decentralized MARL policy evaluation with nonlinear function approximation, which is often seen in deep MARL. |
Xin Zhang; Zhuqing Liu; Jia Liu; Zhengyuan Zhu; Songtao Lu; | |
1440 | Federated Graph Classification Over Non-IID Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle this, we propose a graph clustered federated learning (GCFL) framework that dynamically finds clusters of local systems based on the gradients of GNNs, and theoretically justify that such clusters can reduce the structure and feature heterogeneity among graphs owned by the local systems. |
Han Xie; Jing Ma; Li Xiong; Carl Yang; | |
1441 | SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new framework, Subsetting features of Tabular data (SubTab), that turns the task of learning from tabular data into a multi-view representation learning problem by dividing the input features to multiple subsets. |
Talip Ucar; Ehsan Hajiramezanali; Lindsay Edwards; | |
1442 | Convergence Rates of Stochastic Gradient Descent Under Infinite Noise Variance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide convergence guarantees for SGD under a state-dependent and heavy-tailed noise with a potentially infinite variance, for a class of strongly convex objectives. |
Hongjian Wang; Mert Gurbuzbalaban; Lingjiong Zhu; Umut Simsekli; Murat A. Erdogdu; | |
1443 | Conflict-Averse Gradient Descent for Multi-task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: But most of them lack convergence guarantee and/or could converge to any Pareto-stationary point.In this paper, we introduce Conflict-Averse Gradient descent (CAGrad) which minimizes the average loss function, while leveraging the worst local improvement of individual tasks to regularize the algorithm trajectory. |
Bo Liu; Xingchao Liu; Xiaojie Jin; Peter Stone; Qiang Liu; | |
1444 | Amortized Synthesis of Constrained Configurations Using A Differentiable Surrogate Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We first learn the decoder: a differentiable surrogate that approximates the many-to-one physical realization process. We then learn the encoder, which maps from goal to design, while using the fixed decoder to evaluate the quality of the realization. |
Xingyuan Sun; Tianju Xue; Szymon Rusinkiewicz; Ryan P. Adams; | |
1445 | Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give a resolution to this question by providing an optimal and efficient reduction from contextual bandits to online regression with the logarithmic (or, cross-entropy) loss. |
Dylan J. Foster; Akshay Krishnamurthy; | |
1446 | Distributed Estimation with Multiple Samples Per User: Sharp Rates and Phase Transition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We obtain tight minimax rates for the problem of distributed estimation of discrete distributions under communication constraints, where $n$ users observing $m $ samples each can broadcast only $\ell$ bits. |
Jayadev Acharya; Clement Canonne; Yuhan Liu; Ziteng Sun; Himanshu Tyagi; | |
1447 | Revisiting Deep Learning Models for Tabular Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform an overview of the main families of DL architectures for tabular data and raise the bar of baselines in tabular DL by identifying two simple and powerful deep architectures. |
Yury Gorishniy; Ivan Rubachev; Valentin Khrulkov; Artem Babenko; | code |
1448 | Backdoor Attack with Imperceptible Input and Latent Modification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formulate such an objective as a non-convex and constrained optimization problem and solve the problem with an efficient stochastic alternating optimization procedure. |
Khoa Doan; Yingjie Lao; Ping Li; | |
1449 | SOPE: Spectrum of Off-Policy Estimators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new perspective on this bias-variance trade-off and show the existence of a spectrum of estimators whose endpoints are SIS and IS. |
Christina Yuan; Yash Chandak; Stephen Giguere; Philip S. Thomas; Scott Niekum; | |
1450 | Label-Imbalanced and Group-Sensitive Classification Under Overparameterization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to previous heuristics, we follow a principled analysis explaining how different loss adjustments affect margins. |
Ganesh Ramachandra Kini; Orestis Paraskevas; Samet Oymak; Christos Thrampoulidis; | |
1451 | Neural Program Generation Modulo Static Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to address this deficiency using weak supervision from a static program analyzer. |
Rohan Mukherjee; Yeming Wen; Dipak Chaudhari; Thomas Reps; Swarat Chaudhuri; Christopher Jermaine; | |
1452 | Unfolding Taylor's Approximations for Image Restoration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the above problems, inspired by Taylor’s Approximations, we unfold Taylor’s Formula to construct a novel framework for image restoration. |
man zhou; Xueyang Fu; Zeyu Xiao; Gang Yang; Aiping Liu; Zhiwei Xiong; | |
1453 | Metropolis-Hastings Data Augmentation for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning. |
Hyeonjin Park; Seunghun Lee; Sihyeon Kim; Jinyoung Park; Jisu Jeong; Kyung-Min Kim; Jung-Woo Ha; Hyunwoo J. Kim; | |
1454 | Strategic Behavior Is Bliss: Iterative Voting Improves Social Welfare Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we differentiate agents’ utility from their manipulation mechanism and determine iterative plurality’s ADPoA in the worst- and average-cases. |
Joshua Kavner; Lirong Xia; | |
1455 | Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the more realistic setting of agnostic RL with rich observation spaces and a fixed class of policies $\Pi$ that may not contain any near-optimal policy. |
Ayush Sekhari; Christoph Dann; Mehryar Mohri; Yishay Mansour; Karthik Sridharan; | |
1456 | Functional Regularization for Reinforcement Learning Via Learned Fourier Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. |
Alexander Li; Deepak Pathak; | |
1457 | Adaptive First-Order Methods Revisited: Convex Minimization Without Lipschitz Requirements Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new family of adaptive first-order methods for a class of convex minimization problems that may fail to be Lipschitz continuous or smooth in the standard sense. |
Kimon Antonakopoulos; Panayotis Mertikopoulos; | |
1458 | Adapting to Function Difficulty and Growth Conditions in Private Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop algorithms for private stochastic convex optimization that adapt to the hardness of the specific function we wish to optimize. |
Hilal Asi; Daniel Levy; John C. Duchi; | |
1459 | Support Recovery of Sparse Signals from A Mixture of Linear Measurements Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the number of measurements sufficient for recovering the supports of all the component vectors in a mixture in both these models. |
Soumyabrata Pal; Arya Mazumdar; Venkata Gandikota; | |
1460 | Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis Under Expected Co-coercivity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO under this condition for solving a class of stochastic variational inequality problems that are potentially non-monotone. |
Nicolas Loizou; Hugo Berard; Gauthier Gidel; Ioannis Mitliagkas; Simon Lacoste-Julien; | |
1461 | Tighter Expected Generalization Error Bounds Via Wasserstein Distance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents several expected generalization error bounds based on the Wasserstein distance. |
Borja Rodr�guez G�lvez; German Bassi; Ragnar Thobaben; Mikael Skoglund; | |
1462 | Unifying Width-Reduced Methods for Quasi-Self-Concordant Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide several algorithms for constrained optimization of a large class of convex problems, including softmax, $\ell_p$ regression, and logistic regression. |
Deeksha Adil; Brian Bullins; Sushant Sachdeva; | |
1463 | Bridging The Imitation Gap By Adaptive Insubordination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To better address these tasks and alleviate the imitation gap we propose ‘Adaptive Insubordination’ (ADVISOR). |
Luca Weihs; Unnat Jain; Iou-Jen Liu; Jordi Salvador; Svetlana Lazebnik; Aniruddha Kembhavi; Alex Schwing; | |
1464 | Adversarial Robustness with Non-uniform Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose using characteristics of the empirical data distribution, both on correlations between the features and the importance of the features themselves. |
Ecenaz Erdemir; Jeffrey Bickford; Luca Melis; Sergul Aydore; | |
1465 | Container: Context Aggregation Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the \model (CONText AggregatIon NEtwoRk), a general-purpose building block for multi-head context aggregation that can exploit long-range interactions \emph{a la} Transformers while still exploiting the inductive bias of the local convolution operation leading to faster convergence speeds, often seen in CNNs. |
peng gao; Jiasen Lu; hongsheng Li; Roozbeh Mottaghi; Aniruddha Kembhavi; | code |
1466 | ConE: Cone Embeddings for Multi-Hop Reasoning Over Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a novel query embedding model, namely \textbf{Con}e \textbf{E}mbeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation. |
Zhanqiu Zhang; Jie Wang; Jiajun Chen; Shuiwang Ji; Feng Wu; | |
1467 | Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the problem of federated hyperparameter tuning. |
Mikhail Khodak; Renbo Tu; Tian Li; Liam Li; Maria-Florina F. Balcan; Virginia Smith; Ameet Talwalkar; | |
1468 | Training for The Future: A Simple Gradient Interpolation Loss to Generalize Along Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Responding to the above limitations, we propose a simple method that starts with a model with time-sensitive parameters but regularizes its temporal complexity using a Gradient Interpolation (GI) loss. |
Anshul Nasery; Soumyadeep Thakur; Vihari Piratla; Abir De; Sunita Sarawagi; | |
1469 | Agent Modelling Under Partial Observability for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from the local information of the controlled agent using encoder-decoder architectures. |
Georgios Papoudakis; Filippos Christianos; Stefano Albrecht; | |
1470 | Leveraging Distribution Alignment Via Stein Path for Cross-Domain Cold-Start Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the Cross-Domain Cold-Start Recommendation (CDCSR) problem. |
Weiming Liu; Jiajie Su; Chaochao Chen; Xiaolin Zheng; | |
1471 | Conservative Offline Distributional Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove that CODAC learns a conservative return distribution—in particular, for finite MDPs, CODAC converges to an uniform lower bound on the quantiles of the return distribution; our proof relies on a novel analysis of the distributional Bellman operator. |
Yecheng Ma; Dinesh Jayaraman; Osbert Bastani; | |
1472 | Separation Results Between Fixed-Kernel and Feature-Learning Probability Metrics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide separation results between probability metrics with fixed-kernel and feature-learning discriminators using the function classes $\mathcal{F}_2$ and $\mathcal{F}_1$ respectively, which were developed to study overparametrized two-layer neural networks. |
Carles Domingo i Enrich; Youssef Mroueh; | |
1473 | Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a generic importance sampling weighted ERM algorithm for using adaptively collected data to minimize the average of a loss function over a hypothesis class and provide first-of-their-kind generalization guarantees and fast convergence rates. |
Aurelien Bibaut; Nathan Kallus; Maria Dimakopoulou; Antoine Chambaz; Mark van der Laan; | |
1474 | Bayesian Optimization with High-Dimensional Outputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We devise an efficient technique for exact multi-task GP sampling that combines exploiting Kronecker structure in the covariance matrices with Matheron’s identity, allowing us to perform Bayesian optimization using exact multi-task GP models with tens of thousands of correlated outputs. |
Wesley J. Maddox; Maximilian Balandat; Andrew G. Wilson; Eytan Bakshy; | |
1475 | Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel geometric-based approach called Tangent Attack (TA), which identifies an optimal tangent point of a virtual hemisphere located on the decision boundary to reduce the distortion of the attack. |
Chen Ma; Xiangyu Guo; Li Chen; Jun-Hai Yong; Yisen Wang; | |
1476 | Scalable Diverse Model Selection for Accessible Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize this setting as "Scalable Diverse Model Selection" and propose several benchmarks for evaluating on this task. |
Daniel Bolya; Rohit Mittapalli; Judy Hoffman; | |
1477 | Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel neural scene representation, Light Field Networks or LFNs, which represent both geometry and appearance of the underlying 3D scene in a 360-degree, four-dimensional light field parameterized via a neural implicit representation. |
Vincent Sitzmann; Semon Rezchikov; Bill Freeman; Josh Tenenbaum; Fredo Durand; | |
1478 | ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce ViSER, a method for recovering articulated 3D shapes and dense3D trajectories from monocular videos. |
Gengshan Yang; Deqing Sun; Varun Jampani; Daniel Vlasic; Forrester Cole; Ce Liu; Deva Ramanan; | |
1479 | Understanding The Effect of Stochasticity in Policy Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the effect of stochasticity in on-policy policy optimization, and make the following four contributions. \emph{First}, we show that the preferability of optimization methods depends critically on whether stochastic versus exact gradients are used. |
Jincheng Mei; Bo Dai; Chenjun Xiao; Csaba Szepesvari; Dale Schuurmans; | |
1480 | Fine-Grained Zero-Shot Learning with DNA As Side Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As manually annotated visual attributes are extremely costly and often impractical to obtain for a large number of classes, in this study we use DNA as a side information for the first time for fine-grained zero-shot classification of species. |
Sarkhan Badirli; Zeynep Akata; George Mohler; Christine Picard; Mehmet Dundar; | |
1481 | Optimal Underdamped Langevin MCMC Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the paper, we study the underdamped Langevin diffusion (ULD) with strongly-convex potential consisting of finite summation of $N$ smooth components, and propose an efficient discretization method, which requires $O(N+d^\frac{1}{3}N^\frac{2}{3}/\varepsilon^\frac{2}{3})$ gradient evaluations to achieve $\varepsilon$-error (in $\sqrt{\mathbb{E}{\lVert{\cdot}\rVert_2^2}}$ distance) for approximating $d$-dimensional ULD. |
Zhengmian Hu; Feihu Huang; Heng Huang; | |
1482 | Scheduling Jobs with Stochastic Holding Costs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a learning and scheduling algorithm to minimize the expected cumulative holding cost incurred by jobs, where statistical parameters defining their individual holding costs are unknown a priori. |
Dabeen Lee; Milan Vojnovic; | |
1483 | REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People Under Weak Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce \textbf{REMIPS}, a model for 3D \underline{Re}construction of \underline{M}ultiple \underline{I}nteracting \underline{P}eople under Weak \underline{S}upervision. |
Mihai Fieraru; Mihai Zanfir; Teodor Szente; Eduard Bazavan; Vlad Olaru; Cristian Sminchisescu; | |
1484 | Differentiable Annealed Importance Sampling and The Perils of Gradient Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose Differentiable AIS (DAIS), a variant of AIS which ensures differentiability by abandoning the Metropolis-Hastings corrections. |
Guodong Zhang; Kyle Hsu; Jianing Li; Chelsea Finn; Roger B. Grosse; | |
1485 | PSD Representations for Effective Probability Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that a recently proposed class of positive semi-definite (PSD) models for non-negative functions is particularly suited to this end. |
Alessandro Rudi; Carlo Ciliberto; | |
1486 | Exploiting A Zoo of Checkpoints for Unseen Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper attempts to address this question by capturing relationships among checkpoints published on the web. |
Jiaji Huang; Qiang Qiu; Kenneth Church; | |
1487 | Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new learning paradigm with graph representation and learning. |
Qitian Wu; Chenxiao Yang; Junchi Yan; | |
1488 | Adversarial Teacher-Student Representation Learning for Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To extract and leverage the information which exhibits sufficient generalization ability, we propose a simple yet effective approach of Adversarial Teacher-Student Representation Learning, with the goal of deriving the domain generalizable representations via generating and exploring out-of-source data distributions. |
Fu-En Yang; Yuan-Chia Cheng; Zu-Yun Shiau; Yu-Chiang Frank Wang; | |
1489 | Stochastic Bandits with Groups of Similar Arms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a lower-bound inspired strategy involving a computationally efficient relaxation that is based on a sorting mechanism. |
Fabien Pesquerel; Hassan SABER; Odalric-Ambrym Maillard; | |
1490 | Tracking Without Re-recognition in Humans and Machines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this, we introduce PathTracker, a synthetic visual challenge that asks human observers and machines to track a target object in the midst of identical-looking "distractor" objects. |
Drew Linsley; Girik Malik; Junkyung Kim; Lakshmi Narasimhan Govindarajan; Ennio Mingolla; Thomas Serre; | |
1491 | Rethinking Conditional GAN Training: An Approach Using Geometrically Structured Latent Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we tackle this problem from a geometrical perspective and propose a novel training mechanism that increases both the diversity and the visual quality of a vanilla cGAN, by systematically encouraging a bi-lipschitz mapping between the latent and the output manifolds. |
Sameera Ramasinghe; Moshiur Farazi; Salman H. Khan; Nick Barnes; Stephen Gould; | |
1492 | How to Transfer Algorithmic Reasoning Knowledge to Learn New Algorithms? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we investigate how we can use algorithms for which we have access to the execution trace to learn to solve similar tasks for which we do not. |
Louis-Pascal Xhonneux; Andreea-Ioana Deac; Petar Velickovic; Jian Tang; | |
1493 | Fast Axiomatic Attribution for Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we break this trade-off by considering a special class of efficiently axiomatically attributable DNNs for which an axiomatic feature attribution can be computed with only a single forward/backward pass. |
Robin Hesse; Simone Schaub-Meyer; Stefan Roth; | |
1494 | OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To eliminate the requirement of saving separate models for different target datasets, we propose a novel setting that starts from a pretrained deep generative model and compresses the data batches while adapting the model with a dynamical system for only one epoch. |
Chen Zhang; Shifeng Zhang; Fabio Maria Carlucci; Zhenguo Li; | |
1495 | Compressive Visual Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we hypothesize that adding explicit information compression to these algorithms yields better and more robust representations. |
Kuang-Huei Lee; Anurag Arnab; Sergio Guadarrama; John Canny; Ian Fischer; | |
1496 | Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the problem from the perspective of two standard objectives: 1) regret minimization, and 2) best-arm identification. |
Arnab Maiti; Vishakha Patil; Arindam Khan; | |
1497 | Grounding Inductive Biases in Natural Images: Invariance Stems from Variations in Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we study the relative importance of several types of inductive biases towards such predictable behavior: the choice of data, their augmentations, and model architectures. |
Diane Bouchacourt; Mark Ibrahim; Ari Morcos; | |
1498 | Directed Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design a directed graph data augmentation method called Laplacian perturbation and theoretically analyze how it provides contrastive information without changing the directed graph structure. |
Zekun Tong; Yuxuan Liang; Henghui Ding; Yongxing Dai; Xinke Li; Changhu Wang; | |
1499 | Space-time Mixing Attention for Video Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Video Transformer model the complexity of which scales linearly with the number of frames in the video sequence and hence induces no overhead compared to an image-based Transformer model. |
Adrian Bulat; Juan Manuel Perez Rua; Swathikiran Sudhakaran; Brais Martinez; Georgios Tzimiropoulos; | |
1500 | Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the particle dual averaging (PDA) method, which generalizes the dual averaging method in convex optimization to the optimization over probability distributions with quantitative runtime guarantee. |
Atsushi Nitanda; Denny Wu; Taiji Suzuki; | |
1501 | Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a Represent And Mimic (RAMi) framework for training 1) an identifiable latent representation to capture the independent factors of variation for the objects and 2) a mimic tree that extracts the causal impact of the latent features on DRL action values. |
Guiliang Liu; Xiangyu Sun; Oliver Schulte; Pascal Poupart; | |
1502 | Only Train Once: A One-Shot Neural Network Training And Pruning Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we propose a framework that compresses DNNs into slimmer architectures with competitive performances and significant FLOPs reductions by Only-Train-Once (OTO). |
Tianyi Chen; Bo Ji; Tianyu Ding; Biyi Fang; Guanyi Wang; Zhihui Zhu; Luming Liang; Yixin Shi; Sheng Yi; Xiao Tu; | code |
1503 | Referring Transformer: A One-step Approach to Multi-task Visual Grounding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple one-stage multi-task framework for visual grounding tasks. |
Muchen Li; Leonid Sigal; | |
1504 | Decoupling The Depth and Scope of Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a design principle to decouple the depth and scope of GNNs – to generate representation of a target entity (i.e., a node or an edge), we first extract a localized subgraph as the bounded-size scope, and then apply a GNN of arbitrary depth on top of the subgraph. |
Hanqing Zeng; Muhan Zhang; Yinglong Xia; Ajitesh Srivastava; Andrey Malevich; Rajgopal Kannan; Viktor Prasanna; Long Jin; Ren Chen; | |
1505 | Fast and Memory Efficient Differentially Private-SGD Via JL Projections Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new framework to design differentially private optimizers called DP-SGD-JL and DP-Adam-JL. |
Zhiqi Bu; Sivakanth Gopi; Janardhan Kulkarni; Yin Tat Lee; Hanwen Shen; Uthaipon Tantipongpipat; | |
1506 | Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the first integral study and analysis for feed-forward neural networks in terms of the robustness in pairwise class margin and its generalization behavior under weight perturbation. |
Yu-Lin Tsai; Chia-Yi Hsu; Chia-Mu Yu; Pin-Yu Chen; | |
1507 | Pipeline Combinators for Gradual AutoML Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a small set of orthogonal combinators for composing machine-learning operators into pipelines. |
Guillaume Baudart; Martin Hirzel; Kiran Kate; Parikshit Ram; Avraham Shinnar; Jason Tsay; | |
1508 | Boost Neural Networks By Checkpoints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel method to ensemble the checkpoints, where a boosting scheme is utilized to accelerate model convergence and maximize the checkpoint diversity. |
Feng Wang; Guoyizhe Wei; Qiao Liu; Jinxiang Ou; xian wei; Hairong Lv; | |
1509 | Model Selection for Bayesian Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the common practice of type-II maximum likelihood optimization and its equivalence to Kullback-Leibler divergence minimization, we propose to optimize the distributional sliced-Wasserstein distance (DSWD) between the output of the autoencoder and the empirical data distribution. |
Ba-Hien Tran; Simone Rossi; Dimitrios Milios; Pietro Michiardi; Edwin V. Bonilla; Maurizio Filippone; | |
1510 | Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by these concerns, we analyze three potentially valuable extensions of TOS. |
Alp Yurtsever; Alex Gu; Suvrit Sra; | |
1511 | Knowledge-Adaptation Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Knowledge-adaptation priors (K-priors) to reduce the cost of retraining by enabling quick and accurate adaptation for a wide-variety of tasks and models. |
Mohammad Emtiyaz E. Khan; Siddharth Swaroop; | |
1512 | Provably Efficient Multi-task Reinforcement Learning with Model Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design and analyze a model-based algorithm, and provide gap-dependent and gap-independent regret upper and lower bounds that characterize the intrinsic complexity of the problem. |
Chicheng Zhang; Zhi Wang; | |
1513 | Predicting Molecular Conformation Via Dynamic Graph Score Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new approach called Dynamic Graph Score Matching (DGSM) for molecular conformation prediction, which models both the local and long-range interactions by dynamically constructing graph structures between atoms according to their spatial proximity during both training and inference. |
Shitong Luo; Chence Shi; Minkai Xu; Jian Tang; | |
1514 | When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to use neural functional processes to fill this gap. |
Harshavardhan Kamarthi; Lingkai Kong; Alexander Rodriguez; Chao Zhang; B. Aditya Prakash; | |
1515 | Bounds All Around: Training Energy-based Models with Bidirectional Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a bidirectional bound on the EBM log-likelihood, such that we maximize a lower bound and minimize an upper bound when solving the minimax game. |
Cong Geng; Jia Wang; Zhiyong Gao; Jes Frellsen; S�ren Hauberg; | |
1516 | CogView: Mastering Text-to-Image Generation Via Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. |
Ming Ding; Zhuoyi Yang; Wenyi Hong; Wendi Zheng; Chang Zhou; Da Yin; Junyang Lin; Xu Zou; Zhou Shao; Hongxia Yang; Jie Tang; | |
1517 | Time-independent Generalization Bounds for SGLD in Non-convex Settings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We establish generalization error bounds for stochastic gradient Langevin dynamics (SGLD) with constant learning rate under the assumptions of dissipativity and smoothness, a setting that has received increased attention in the sampling/optimization literature. |
Tyler Farghly; Patrick Rebeschini; | |
1518 | Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further improve the estimation efficiency over the IPW method, we propose a likelihood-based estimator by correcting log odds for the sampled data and prove that the improved estimator has the smallest asymptotic variance among a large class of estimators. |
HaiYing Wang; Aonan Zhang; Chong Wang; | |
1519 | Algorithmic Stability and Generalization of An Unsupervised Feature Selection Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an innovative unsupervised feature selection algorithm attaining this stability with provable guarantees. |
xinxing wu; Qiang Cheng; | |
1520 | On Learning Sparse Vectors from Mixture of Responses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As the main contribution of the paper, we prove the existence of learning algorithms for the first problem which work without any assumptions. |
Nikita Polyanskii; | |
1521 | Convergence and Alignment of Gradient Descent with Random Backpropagation Weights Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study the mathematical properties of the feedback alignment procedure by analyzing convergence and alignment for two-layer networks under squared error loss. |
Ganlin Song; Ruitu Xu; John Lafferty; | |
1522 | Adder Attention for Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present to reduce the energy consumptions using adder neural network (AdderNet). |
Han Shu; Jiahao Wang; Hanting Chen; Lin Li; Yujiu Yang; Yunhe Wang; | |
1523 | Reverse Engineering Learned Optimizers Reveals Known and Novel Mechanisms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address these questions by careful analysis and visualization of learned optimizers. |
Niru Maheswaranathan; David Sussillo; Luke Metz; Ruoxi Sun; Jascha Sohl-Dickstein; | |
1524 | Matching A Desired Causal State Via Shift Interventions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of identifying a shift intervention that matches the desired mean of a system through active learning. |
Vicky Zhang; Chandler Squires; Caroline Uhler; | |
1525 | Unsupervised Noise Adaptive Speech Enhancement By Discriminator-Constrained Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. |
Hsin-Yi Lin; Huan-Hsin Tseng; Xugang Lu; Yu Tsao; | |
1526 | Optimality of Variational Inference for Stochasticblock Model with Missing Links Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work, we consider the case of networks with missing links that is important in application and show that the variational approximation to the maximum likelihood estimator converges at the minimax rate. |
Solenne Gaucher; Olga Klopp; | |
1527 | Policy Learning Using Weak Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We aim for a unified framework that leverages the available cheap weak supervisions to perform policy learning efficiently. |
Jingkang Wang; Hongyi Guo; Zhaowei Zhu; Yang Liu; | |
1528 | Chasing Sparsity in Vision Transformers: An End-to-End Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, this paper aims to trim down both the training memory overhead and the inference complexity, without sacrificing the achievable accuracy. |
Tianlong Chen; Yu Cheng; Zhe Gan; Lu Yuan; Lei Zhang; Zhangyang Wang; | code |
1529 | Graphical Models in Heavy-Tailed Markets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present graph learning estimators based on the Markov random field framework that assume a Student-$t$ data generating process. |
Jose Vinicius de Miranda Cardoso; Jiaxi Ying; Daniel Palomar; | |
1530 | A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this ambiguity by proposing a novel shading-guided generative implicit model that is able to learn a starkly improved shape representation. |
Xingang Pan; Xudong XU; Chen Change Loy; Christian Theobalt; Bo Dai; | code |
1531 | XCiT: Cross-Covariance Image Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a “transposed” version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. |
Alaaeldin Ali; Hugo Touvron; Mathilde Caron; Piotr Bojanowski; Matthijs Douze; Armand Joulin; Ivan Laptev; Natalia Neverova; Gabriel Synnaeve; Jakob Verbeek; Herve Jegou; | |
1532 | Row-clustering of A Point Process-valued Matrix Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To cluster repeatedly observed marked point processes, we propose a novel mixture model of multi-level marked point processes for identifying potential heterogeneity in the observed data. |
Lihao Yin; Ganggang Xu; Huiyan Sang; Yongtao Guan; | |
1533 | Fine-Grained Neural Network Explanation By Identifying Input Features with Predictive Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to identify features with predictive information in the input domain. |
Yang Zhang; Ashkan Khakzar; Yawei Li; Azade Farshad; Seong Tae Kim; Nassir Navab; | |
1534 | Fast Minimum-norm Adversarial Attacks Through Adaptive Norm Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we overcome these limitations by proposing a fast minimum-norm (FMN) attack that works with different $\ell_p$-norm perturbation models ($p=0, 1, 2, \infty$), is robust to hyperparameter choices, does not require adversarial starting points, and converges within few lightweight steps. |
Maura Pintor; Fabio Roli; Wieland Brendel; Battista Biggio; | code |
1535 | Uncertainty Quantification and Deep Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This text examines the interplay between three of the most simple and commonly used approaches to leverage deep learning when data is scarce: data-augmentation, ensembling, and post-processing calibration methods. We demonstrate that, although standard ensembling techniques certainly help to boost accuracy, the calibration of deep ensembles relies on subtle trade-offs. |
Rahul Rahaman; alexandre thiery; | |
1536 | Directed Probabilistic Watershed Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the "Directed Probabilistic Watershed", an extension of the Probabilistic Watershed algorithm to directed graphs. |
Enrique Fita Sanmartin; Sebastian Damrich; Fred A. Hamprecht; | |
1537 | Laplace Redux – Effortless Bayesian Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we show that these are misconceptions: we (i) review the range of variants of the LA including versions with minimal cost overhead; (ii) introduce "laplace", an easy-to-use software library for PyTorch offering user-friendly access to all major flavors of the LA; and (iii) demonstrate through extensive experiments that the LA is competitive with more popular alternatives in terms of performance, while excelling in terms of computational cost. |
Erik Daxberger; Agustinus Kristiadi; Alexander Immer; Runa Eschenhagen; Matthias Bauer; Philipp Hennig; | |
1538 | Hessian Eigenspectra of More Realistic Nonlinear Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we exploit tools from random matrix theory to make a precise characterization of the Hessian eigenspectra for a broad family of nonlinear models that extends the classical generalized linear models, without relying on strong simplifying assumptions used previously. |
Zhenyu Liao; Michael W. Mahoney; | |
1539 | Explicable Reward Design for Reinforcement Learning Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the problem from the perspective of discrete optimization and introduce a novel framework, ExpRD, to design explicable reward functions. |
Rati Devidze; Goran Radanovic; Parameswaran Kamalaruban; Adish Singla; | |
1540 | A Minimalist Approach to Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we aim to make a deep RL algorithm work while making minimal changes. |
Scott Fujimoto; Shixiang (Shane) Gu; | |
1541 | SIMONe: View-Invariant, Temporally-Abstracted Object Representations Via Unsupervised Video Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This problem is especially difficult when scene structure needs to be inferred while also estimating the agent’s location/viewpoint, as the two variables jointly give rise to the agent’s observations. We present an unsupervised variational approach to this problem. |
Rishabh Kabra; Daniel Zoran; Goker Erdogan; Loic Matthey; Antonia Creswell; Matt Botvinick; Alexander Lerchner; Chris Burgess; | |
1542 | Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose simple stochastic and online gradient descent methods for pairwise learning. |
ZHENHUAN YANG; Yunwen Lei; Puyu Wang; Tianbao Yang; Yiming Ying; | |
1543 | User-Level Differentially Private Learning Via Correlated Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the setting where each user holds $m$ samples and the privacy protection is enforced at the level of each user’s data. |
Badih Ghazi; Ravi Kumar; Pasin Manurangsi; | |
1544 | Asynchronous Decentralized Online Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we study decentralized online learning in the asynchronous setting, which allows different learners to work at their own pace. |
Jiyan Jiang; Wenpeng Zhang; Jinjie GU; Wenwu Zhu; | |
1545 | Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the shortcomings of existing approaches, we propose the budgeted multi-step expected improvement, a non-myopic acquisition function that generalizes classical expected improvement to the setting of heterogeneous and unknown evaluation costs. |
Raul Astudillo; Daniel Jiang; Maximilian Balandat; Eytan Bakshy; Peter Frazier; | |
1546 | Model-Based Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this theoretical motivation, we propose a novel domain generalization algorithm with convergence guarantees. |
Alexander Robey; George Pappas; Hamed Hassani; | |
1547 | $\alpha$-IoU: A Family of Power Intersection Over Union Losses for Bounding Box Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter $\alpha$. |
JIABO HE; Sarah Erfani; Xingjun Ma; James Bailey; Ying Chi; Xian-Sheng Hua; | |
1548 | Practical Large-Scale Linear Programming Using Primal-Dual Hybrid Gradient Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present PDLP, a practical first-order method for linear programming (LP) that can solve to the high levels of accuracy that are expected in traditional LP applications. |
David Applegate; Mateo Diaz; Oliver Hinder; Haihao Lu; Miles Lubin; Brendan O'Donoghue; Warren Schudy; | |
1549 | On The Provable Generalization of Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the training and generalization for RNNs with random initialization, and provide the following improvements over recent works:(1) For a RNN with input sequence $x=(X_1,X_2,…,X_L)$, previous works study to learn functions that are summation of $f(\beta^T_lX_l)$ and require normalized conditions that $||X_l||\leq\epsilon$ with some very small $\epsilon$ depending on the complexity of $f$. |
Lifu Wang; Bo Shen; Bo Hu; Xing Cao; | |
1550 | Differentiable Spline Approximations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal in this paper is to use a new, principled approach to extend gradient-based optimization to functions well modeled by splines, which encompass a large family of piecewise polynomial models. |
Minsu Cho; Aditya Balu; Ameya Joshi; Anjana Deva Prasad; Biswajit Khara; Soumik Sarkar; Baskar Ganapathysubramanian; Adarsh Krishnamurthy; Chinmay Hegde; | code |
1551 | Rate-Optimal Subspace Estimation on Random Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the theory of random bipartite graph whose adjacency matrix is generated according to a connectivity matrix $M$. |
Zhixin Zhou; Fan Zhou; Ping Li; Cun-Hui Zhang; | |
1552 | Estimating The Unique Information of Continuous Variables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present a method for estimating the unique information in continuous distributions, for the case of one versus two variables. |
Ari Pakman; Amin Nejatbakhsh; Dar Gilboa; Abdullah Makkeh; Luca Mazzucato; Michael Wibral; Elad Schneidman; | |
1553 | Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce several strategies to improve the scalability of exact score-based methods in the linear Gaussian setting. |
Ignavier Ng; Yujia Zheng; Jiji Zhang; Kun Zhang; | |
1554 | Node Dependent Local Smoothing for Scalable Graph Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel algorithm called node-dependent local smoothing (NDLS), which aims to control the smoothness of every node by setting a node-specific smoothing iteration. |
Wentao Zhang; Mingyu Yang; Zeang Sheng; Yang Li; Wen Ouyang; Yangyu Tao; Zhi Yang; Bin CUI; | |
1555 | Parallel and Efficient Hierarchical K-Median Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce a new parallel algorithm for the Euclidean hierarchical $k$-median problem that, when using machines with memory $s$ (for $s\in \Omega(\log^2 (n+\Delta+d))$), outputs a hierarchical clustering such that for every fixed value of $k$ the cost of the solution is at most an $O(\min\{d, \log n\} \log \Delta)$ factor larger in expectation than that of an optimal solution. |
Vincent Cohen-Addad; Silvio Lattanzi; Ashkan Norouzi-Fard; Christian Sohler; Ola Svensson; | |
1556 | Human-Adversarial Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to stress test VQA models, we benchmark them against human-adversarial examples. |
Sasha Sheng; Amanpreet Singh; Vedanuj Goswami; Jose Magana; Tristan Thrush; Wojciech Galuba; Devi Parikh; Douwe Kiela; | |
1557 | Across-animal Odor Decoding By Probabilistic Manifold Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a novel probabilistic approach for aligning stimulus-evoked responses from multiple animals in a common low dimensional manifold and use hierarchical inference to identify which stimulus drives neural activity in any given trial. |
Pedro Herrero-Vidal; Dmitry Rinberg; Cristina Savin; | |
1558 | Excess Capacity and Backdoor Poisoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To gain a better foundational understanding of backdoor data poisoning attacks, we present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems. |
Naren Manoj; Avrim Blum; | |
1559 | A Convergence Analysis of Gradient Descent on Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study the convergence properties of the gradient descent algorithm when used to train GNNs. |
Pranjal Awasthi; Abhimanyu Das; Sreenivas Gollapudi; | |
1560 | Differentiable Rendering with Perturbed Optimizers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take a more general approach and study differentiable renderers through the prism of randomized optimization and the related notion of perturbed optimizers. |
Quentin Le Lidec; Ivan Laptev; Cordelia Schmid; Justin Carpentier; | |
1561 | BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle with above problems, we propose a budget constrained offline reinforcement learning and evaluation with $\lambda$-generalization (BCORLE($\lambda$)) framework. |
Yang Zhang; Bo Tang; Qingyu Yang; Dou An; Hongyin Tang; Chenyang Xi; Xueying LI; Feiyu Xiong; | |
1562 | Nested Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each level of nesting. |
Heiko Zimmermann; Hao Wu; Babak Esmaeili; Jan-Willem van de Meent; | |
1563 | Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study risk-sensitive reinforcement learning (RL) based on the entropic risk measure. |
Yingjie Fei; Zhuoran Yang; Yudong Chen; Zhaoran Wang; | |
1564 | On Sensitivity of Meta-learning to Support Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite their success, we show that modern meta-learning algorithms are extremely sensitive to the data used for adaptation, i.e. support data. |
Mayank Agarwal; Mikhail Yurochkin; Yuekai Sun; | |
1565 | On Large-Cohort Training for Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore how the number of clients sampled at each round (the cohort size) impacts the quality of the learned model and the training dynamics of federated learning algorithms. |
Zachary Charles; Zachary Garrett; Zhouyuan Huo; Sergei Shmulyian; Virginia Smith; | |
1566 | Generic Neural Architecture Search Via Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we attempt to answer two fundamental questions related to NAS. |
Yuhong Li; Cong Hao; Pan Li; Jinjun Xiong; Deming Chen; | |
1567 | The Best of Both Worlds: Stochastic and Adversarial Episodic MDPs with Unknown Transition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we resolve this open problem by using the same Follow-the-Regularized-Leader (FTRL) framework together with a set of new techniques. |
Tiancheng Jin; Longbo Huang; Haipeng Luo; | |
1568 | Private Learning Implies Quantum Stability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we prove a sequence of (information-theoretic) implications from differentially-private PAC learning to online learning and then to quantum stability. |
Yihui Quek; Srinivasan Arunachalam; John Smolin; | |
1569 | Interesting Object, Curious Agent: Learning Task-Agnostic Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a paradigm change in the formulation and evaluation of task-agnostic exploration. |
Simone Parisi; Victoria Dean; Deepak Pathak; Abhinav Gupta; | code |
1570 | SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training Using Gradient Similarity Measurement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a fully automated and lightweight adaptive batching methodology to enable fine-grained batch size adaption (e.g., at a mini-batch level) that can achieve state-of-the-art performance with record breaking batch sizes. |
Heyang Qin; Samyam Rajbhandari; Olatunji Ruwase; Feng Yan; Lei Yang; Yuxiong He; | |
1571 | Variational Inference for Continuous-Time Switching Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Since many areas, such as biology or discrete-event systems, are naturally described in continuous time, we present a model based on a Markov jump process modulating a subordinated diffusion process. |
Lukas K�hs; Bastian Alt; Heinz Koeppl; | |
1572 | Implicit Regularization in Matrix Sensing Via Mirror Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study discrete-time mirror descent applied to the unregularized empirical risk in matrix sensing. |
Fan Wu; Patrick Rebeschini; | |
1573 | STORM+: Fully Adaptive SGD with Recursive Momentum for Nonconvex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we investigate stochastic non-convex optimization problems where the objective is an expectation over smooth loss functions, and the goal is to find an approximate stationary point. |
Kfir Levy; Ali Kavis; Volkan Cevher; | |
1574 | Skipping The Frame-Level: Event-Based Piano Transcription With Neural Semi-CRFs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel formulation of piano transcription, which is optimized to directly predict note events. |
Yujia Yan; Frank Cwitkowitz; Zhiyao Duan; | |
1575 | Deep Learning on A Data Diet: Finding Important Examples Early in Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we make the striking observation that, in standard vision datasets, simple scores averaged over several weight initializations can be used to identify important examples very early in training. |
Mansheej Paul; Surya Ganguli; Gintare Karolina Dziugaite; | |
1576 | BNS: Building Network Structures Dynamically for Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The novelty of BNS is that it dynamically builds a network to learn each new task to overcome CF and to transfer knowledge across tasks at the same time. |
Qi Qin; Wenpeng Hu; Han Peng; Dongyan Zhao; Bing Liu; | |
1577 | Auditing Black-Box Prediction Models for Data Minimization Compliance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on auditing black-box prediction models for compliance with the GDPR’s data minimization principle. |
Bashir Rastegarpanah; Krishna Gummadi; Mark Crovella; | |
1578 | Dueling Bandits with Team Comparisons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the dueling teams problem, a new online-learning setting in which the learner observes noisy comparisons of disjoint pairs of $k$-sized teams from a universe of $n$ players. |
Lee Cohen; Ulrike Schmidt-Kraepelin; Yishay Mansour; | |
1579 | Meta Internal Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these issues, we propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. |
Raphael Bensadoun; Shir Gur; Tomer Galanti; Lior Wolf; | |
1580 | Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interpolators in an arbitrary hypothesis class in terms of the class’s Gaussian width. |
Frederic Koehler; Lijia Zhou; Danica J. Sutherland; Nathan Srebro; | |
1581 | Adaptive Wavelet Distillation from Neural Networks Through Interpretations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose adaptive wavelet distillation (AWD), a method which aims to distill information from a trained neural network into a wavelet transform. |
Wooseok Ha; Chandan Singh; Francois Lanusse; Srigokul Upadhyayula; Bin Yu; | |
1582 | Generative Occupancy Fields for 3D Surface-Aware Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Generative Occupancy Fields (GOF), a novel model based on generative radiance fields that can learn compact object surfaces without impeding its training convergence. |
Xudong XU; Xingang Pan; Dahua Lin; Bo Dai; | code |
1583 | Relaxed Marginal Consistency for Differentially Private Query Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We overcome the main scalability limitation of PRIVATE-PGMthrough a principled approach that relaxes consistency constraints in the estimationobjective. |
Ryan McKenna; Siddhant Pradhan; Daniel R. Sheldon; Gerome Miklau; | |
1584 | Local Policy Search with Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop an algorithm utilizing a probabilistic model of the objective function and its gradient. Based on the model, the algorithm decides where to query a noisy zeroth-order oracle to improve the gradient estimates. |
Sarah M�ller; Alexander von Rohr; Sebastian Trimpe; | |
1585 | DominoSearch: Find Layer-wise Fine-grained N:M Sparse Schemes from Dense Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we present a novel technique — \textbf{\textit{DominoSearch}} to find mixed N:M sparsity schemes from pre-trained dense deep neural networks to achieve higher accuracy than the uniform-sparsity scheme with equivalent complexity constraints (e.g. model size or FLOPs). |
Wei Sun; Aojun Zhou; Sander Stuijk; Rob Wijnhoven; Andrew Oakleigh Nelson; hongsheng Li; Henk Corporaal; | code |
1586 | Techniques for Symbol Grounding with SATNet Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a self-supervised pre-training pipeline that enables SATNet to overcome this limitation, thus broadening the class of problems that SATNet architectures can solve to include datasets where no intermediary labels are available at all. |
Sever Topan; David Rolnick; Xujie Si; | |
1587 | Object DGCNN: 3D Object Detection Using Dynamic Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by recent non-maximum suppression-free 2D object detection models, we propose a 3D object detection architecture on point clouds. |
Yue Wang; Justin M. Solomon; | |
1588 | Safe Policy Optimization with Local Generalized Linear Function Approximations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel algorithm, SPO-LF, that optimizes an agent’s policy while learning the relation between a locally available feature obtained by sensors and environmental reward/safety using generalized linear function approximations. |
Akifumi Wachi; Yunyue Wei; Yanan Sui; | |
1589 | Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study proposes the symplectic adjoint method, which is an adjoint method solved by a symplectic integrator. |
Takashi Matsubara; Yuto Miyatake; Takaharu Yaguchi; | |
1590 | Exponential Separation Between Two Learning Models and Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove an exponential separation for the sample/query complexity between the standard PAC-learning model and a version of the Equivalence-Query-learning model. |
Grzegorz Gluch; Ruediger Urbanke; | |
1591 | The Balancing Principle for Parameter Choice in Distance-regularized Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the unsolved algorithm design problem of choosing a justified regularization parameter in unsupervised domain adaptation. |
Werner Zellinger; Natalia Shepeleva; Marius-Constantin Dinu; Hamid Eghbalzadeh; Hoan Nguyen; Bernhard Nessler; Sergei Pereverzyev; Bernhard A. Moser; | |
1592 | Gaussian Kernel Mixture Network for Single Image Defocus Deblurring Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an end-to-end deep learning approach for removing defocus blur from a single image, so as to have an all-in-focus image for consequent vision tasks. |
Yuhui Quan; Zicong Wu; Hui Ji; | |
1593 | Cockpit: A Practical Debugging Tool for The Training of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we present Cockpit, a collection of instruments that enable a closer look into the inner workings of a learning machine, and a more informative and meaningful status report for practitioners. |
Frank Schneider; Felix Dangel; Philipp Hennig; | |
1594 | MEST: Accurate and Fast Memory-Economic Sparse Training Framework on The Edge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for accurate and fast execution on edge devices. |
Geng Yuan; Xiaolong Ma; Wei Niu; Zhengang Li; Zhenglun Kong; Ning Liu; Yifan Gong; Zheng Zhan; Chaoyang He; Qing Jin; Siyue Wang; Minghai Qin; Bin Ren; Yanzhi Wang; Sijia Liu; Xue Lin; | code |
1595 | Precise Characterization of The Prior Predictive Distribution of Deep ReLU Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Similar in spirit to the kind of analysis that has been developed to devise better initialization schemes for neural networks (cf. He- or Xavier initialization), we derive a precise characterization of the prior predictive distribution of finite-width ReLU networks with Gaussian weights. |
Lorenzo Noci; Gregor Bachmann; Kevin Roth; Sebastian Nowozin; Thomas Hofmann; | |
1596 | RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present RED, a data-free, unified approach to tackle structured pruning. |
Edouard YVINEC; Arnaud Dapogny; Matthieu Cord; Kevin Bailly; | |
1597 | TestRank: Bringing Order Into Unlabeled Test Instances for Deep Learning Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given the ubiquitous unlabeled test data and high labeling cost, in this paper, we propose a novel test prioritization technique, namely TestRank, which aims at revealing more model failures with less labeling effort. |
YU LI; Min LI; Qiuxia LAI; Yannan Liu; Qiang Xu; | |
1598 | Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these concerns, we introduce LINKX — a strong simple method that admits straightforward minibatch training and inference. |
Derek Lim; Felix Hohne; Xiuyu Li; Sijia Linda Huang; Vaishnavi Gupta; Omkar Bhalerao; Ser Nam Lim; | code |
1599 | Reinforcement Learning Based Disease Progression Model for Alzheimer’s Disease Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We model Alzheimer’s disease (AD) progression by combining differential equations (DEs) and reinforcement learning (RL) with domain knowledge. |
Krishnakant Saboo; Anirudh Choudhary; Yurui Cao; Gregory Worrell; David Jones; Ravishankar Iyer; | |
1600 | Catch-A-Waveform: Learning to Generate Audio from A Single Short Example Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we present a GAN-based generative model that can be trained on one short audio signal from any domain (e.g. speech, music, etc.) and does not require pre-training or any other form of external supervision. |
Gal Greshler; Tamar Shaham; Tomer Michaeli; | |
1601 | Explanation-based Data Augmentation for Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a framework that utilizes concept-based explanations to automatically augment the dataset with new images that can cover these under-represented regions to improve the model performance. |
Sandareka Wickramanayake; Wynne Hsu; Mong Li Lee; | |
1602 | Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Treating this as an inductive prior, we suggest a brand-new angle towards data-efficient GAN training: by first identifying the lottery ticket from the original GAN using the small training set of real images; and then focusing on training that sparse subnetwork by re-using the same set. |
Tianlong Chen; Yu Cheng; Zhe Gan; Jingjing Liu; Zhangyang Wang; | code |
1603 | When Are Solutions Connected in Deep Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we improve both conditions by exploiting the quality of the features at every intermediate layer together with a milder over-parameterization requirement. |
Quynh N. Nguyen; Pierre Br�chet; Marco Mondelli; | |
1604 | TOHAN: A One-step Approach Towards Few-shot Hypothesis Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to prevent privacy leakage in SD, we consider a very challenging problem setting, where the classifier for the TD has to be trained using few labeled target data and a well-trained SD classifier, named few-shot hypothesis adaptation (FHA). |
Haoang Chi; Feng Liu; Wenjing Yang; Long Lan; Tongliang Liu; Bo Han; William Cheung; James Kwok; | |
1605 | Learning Graph Cellular Automata Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we focus on a generalised version of typical CA, called graph cellular automata (GCA), in which the lattice structure is replaced by an arbitrary graph. |
Daniele Grattarola; Lorenzo Livi; Cesare Alippi; | |
1606 | Efficient Online Estimation of Causal Effects By Deciding What to Observe Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the problem of deciding, at each time, which data source to sample from. |
Shantanu Gupta; Zachary Lipton; David Childers; | |
1607 | Perturbation Theory for The Information Bottleneck Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we derive a perturbation theory for the IB method and report the first complete characterization of the learning onset, the limit of maximum relevant information per bit extracted from data. |
Vudtiwat Ngampruetikorn; David J. Schwab; | |
1608 | Deconvolutional Networks on Graph Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider an inverse problem in graph learning domain — "given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?" |
Jia Li; Jiajin Li; Yang Liu; Jianwei Yu; Yueting Li; Hong Cheng; | |
1609 | Variational Multi-Task Learning with Gumbel-Softmax Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we propose variational multi-task learning (VMTL), a general probabilistic inference framework for learning multiple related tasks. |
Jiayi Shen; Xiantong Zhen; Marcel Worring; Ling Shao; | |
1610 | Accelerating Quadratic Optimization with Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these, we explore how Reinforcement Learning (RL) can learn a policy to tune parameters to accelerate convergence. |
Jeffrey Ichnowski; Paras Jain; Bartolomeo Stellato; Goran Banjac; Michael Luo; Francesco Borrelli; Joseph E. Gonzalez; Ion Stoica; Ken Goldberg; | code |
1611 | Deep Residual Learning in Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the spike-element-wise (SEW) ResNet to realize residual learning in deep SNNs. |
Wei Fang; Zhaofei Yu; Yanqi Chen; Tiejun Huang; Timoth�e Masquelier; Yonghong Tian; | code |
1612 | Duplex Sequence-to-Sequence Learning for Reversible Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose REDER (Reversible Duplex Transformer), a parameter-efficient model and apply it to machine translation. |
Zaixiang Zheng; Hao Zhou; Shujian Huang; Jiajun Chen; Jingjing Xu; Lei Li; | |
1613 | Improved Coresets and Sublinear Algorithms for Power Means in Euclidean Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of finding high dimensional power means: given a set $A$ of $n$ points in $\R^d$, find the point $m$ that minimizes the sum of Euclidean distance, raised to the power $z$, over all input points. |
Vincent Cohen-Addad; David Saulpic; Chris Schwiegelshohn; | |
1614 | Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formulate the problem of finding the optimal transposable-mask as a minimum-cost flow problem. |
Itay Hubara; Brian Chmiel; Moshe Island; Ron Banner; Joseph Naor; Daniel Soudry; | code |
1615 | Learning and Generalization in RNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we make progress towards remedying this situation by proving that RNNs can learn functions of sequences. |
Abhishek Panigrahi; Navin Goyal; | |
1616 | Improving Visual Quality of Image Synthesis By A Token-based Generator with Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. |
Yanhong Zeng; Huan Yang; Hongyang Chao; Jianbo Wang; Jianlong Fu; | |
1617 | The Effect of The Intrinsic Dimension on The Generalization of Quadratic Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find that this sensitivity to the data distribution is not exclusive to neural networks, and the same phenomenon can be observed on the class of quadratic classifiers (i.e., the sign of a quadratic polynomial) with a nuclear-norm constraint. |
Fabian Latorre; Leello Tadesse Dadi; Paul Rolland; Volkan Cevher; | |
1618 | DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces DeepReduce, a versatile framework for the compressed communication of sparse tensors, tailored to federated deep learning. |
Hang Xu; Kelly Kostopoulou; Aritra Dutta; Xin Li; Alexandros Ntoulas; Panos Kalnis; | code |
1619 | Provably Efficient Causal Reinforcement Learning with Confounded Observational Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study how to incorporate the dataset collected in the offline setting to improve the sample efficiency in the online setting. |
Lingxiao Wang; Zhuoran Yang; Zhaoran Wang; | |
1620 | Predicting Deep Neural Network Generalization with Perturbation Response Curves Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new framework for evaluating the generalization capabilities of trained networks. |
Yair Schiff; Brian Quanz; Payel Das; Pin-Yu Chen; | |
1621 | Exploiting Domain-Specific Features to Enhance Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose meta-Domain Specific-Domain Invariant (mDSDI) – a novel theoretically sound framework that extends beyond the invariance view to further capture the usefulness of domain-specific information. |
Manh-Ha Bui; Toan Tran; Anh Tran; Dinh Phung; | |
1622 | Optimal Order Simple Regret for Gaussian Process Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: When $N$ is the number of exploration trials and $\gamma_N$ is the maximal information gain, we prove an $\tilde{\mathcal{O}}(\sqrt{\gamma_N/N})$ bound on the simple regret performance of a pure exploration algorithm that is significantly tighter than the existing bounds. |
Sattar Vakili; Nacime Bouziani; Sepehr Jalali; Alberto Bernacchia; Da-shan Shiu; | |
1623 | Generalization Guarantee of SGD for Pairwise Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a systematic study on the generalization analysis of SGD for pairwise learning to understand the balance between generalization and optimization. |
Yunwen Lei; Mingrui Liu; Yiming Ying; | |
1624 | Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our contribution posits a meta-distributional scenario, where the causal generating mechanism for label-conditional features is invariant across different labels. |
Junya Chen; Zidi Xiu; Benjamin Goldstein; Ricardo Henao; Lawrence Carin; Chenyang Tao; | |
1625 | Heavy Ball Momentum for Conditional Gradient Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This limitation motivates the present work, which deals with heavy ball momentum, and its impact to FW. |
Bingcong Li; Alireza Sadeghi; Georgios Giannakis; | |
1626 | PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the existence of sparse subnetworks in pre-trained speech SSL models that achieve even better low-resource ASR results. |
Cheng-I Jeff Lai; Yang Zhang; Alexander H. Liu; Shiyu Chang; Yi-Lun Liao; Yung-Sung Chuang; Kaizhi Qian; Sameer Khurana; David Cox; Jim Glass; | |
1627 | Robust Learning of Optimal Auctions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of learning revenue-optimal multi-bidder auctions from samples when the samples of bidders’ valuations can be adversarially corrupted or drawn from distributions that are adversarially perturbed. |
Wenshuo Guo; Michael Jordan; Emmanouil Zampetakis; | |
1628 | Disrupting Deep Uncertainty Estimation Without Harming Accuracy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a novel and simple attack, which unlike adversarial attacks, does not cause incorrect predictions but instead cripples the network’s capacity for uncertainty estimation. |
Ido Galil; Ran El-Yaniv; | |
1629 | SOFT: Softmax-free Transformer with Linear Complexity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this insight, for the first time, a softmax-free transformer or SOFT is proposed. |
Jiachen Lu; Jinghan Yao; Junge Zhang; Xiatian Zhu; Hang Xu; Weiguo Gao; Chunjing XU; Tao Xiang; Li Zhang; | |
1630 | Task-Adaptive Neural Network Retrieval with Meta-Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such limitations, we introduce a novel problem of Neural Network Search (NNS), whose goal is to search for the optimal pretrained network for a novel dataset and constraints (e.g. number of parameters), from a model zoo. |
Wonyong Jeong; Hayeon Lee; Geon Park; Eunyoung Hyung; Jinheon Baek; Sung Ju Hwang; | code |
1631 | Neural Flows: Efficient Alternative to Neural ODEs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose an alternative by directly modeling the solution curves – the flow of an ODE – with a neural network. |
Marin Bilo�; Johanna Sommer; Syama Sundar Rangapuram; Tim Januschowski; Stephan G�nnemann; | |
1632 | Multi-Objective Meta Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from those works, in this paper, we propose a gradient-based Multi-Objective Meta Learning (MOML) framework without manually tuning weights. |
Feiyang YE; Baijiong Lin; Zhixiong Yue; Pengxin Guo; Qiao Xiao; Yu Zhang; | code |
1633 | A Self Consistent Theory of Gaussian Processes Captures Feature Learning Effects in Finite CNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we consider DNNs trained with noisy gradient descent on a large training set and derive a self-consistent Gaussian Process theory accounting for \textit{strong} finite-DNN and feature learning effects. |
Gadi Naveh; Zohar Ringel; | |
1634 | Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new property termed Mini-Batch Consistency (MBC) that is required for large scale mini-batch set encoding. |
Andreis Bruno; Jeffrey Willette; Juho Lee; Sung Ju Hwang; | |
1635 | Efficient and Local Parallel Random Walks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new algorithm that overcomes this limitation by building random walks efficiently and locally at the same time. |
Michael Kapralov; Silvio Lattanzi; Navid Nouri; Jakab Tardos; | |
1636 | Amortized Variational Inference for Simple Hierarchical Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, this paper suggests an amortized approach where shared parameters simultaneously represent all local distributions. |
Abhinav Agrawal; Justin Domke; | |
1637 | Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by sequential budgeted allocation problems, we investigate online matching problems where connections between vertices are not i.i.d., but they have fixed degree distributions — the so-called configuration model. |
Nathan Noiry; Vianney Perchet; Flore Sentenac; | |
1638 | End-to-end Reconstruction Meets Data-driven Regularization for Inverse Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new approach for learning end-to-end reconstruction operators based on unpaired training data for ill-posed inverse problems. |
Subhadip Mukherjee; Marcello Carioni; Ozan �ktem; Carola Schoenlieb; | |
1639 | An Online Passive-aggressive Algorithm for Difference-of-squares Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate a low-rank model of quadratic classification inspired by previous work on factorization machines, polynomial networks, and capsule-based architectures for visual object recognition. |
Lawrence Saul; | |
1640 | Finite-Sample Analysis of Off-Policy TD-Learning Via Generalized Bellman Operators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive finite-sample bounds for any general off-policy TD-like stochastic approximation algorithm that solves for the fixed-point of this generalized Bellman operator. |
Zaiwei Chen; Siva Theja Maguluri; Sanjay Shakkottai; Karthikeyan Shanmugam; | |
1641 | A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a hybrid approach to combine the best of the two worlds, in which a bi-level framework is developed with an upper-level learning method to optimize the graph (e.g. add, delete or modify edges in a graph), fused with a lower-level heuristic algorithm solving on the optimized graph. |
Runzhong Wang; Zhigang Hua; Gan Liu; Jiayi Zhang; Junchi Yan; Feng Qi; Shuang Yang; Jun Zhou; Xiaokang Yang; | |
1642 | Improved Learning Rates of A Functional Lasso-type SVM with Sparse Multi-Kernel Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation. |
shaogao lv; Junhui Wang; Jiankun Liu; Yong Liu; | |
1643 | When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Equipped with our new designs, we propose AdvCL, a novel adversarial contrastive pretraining framework. |
Lijie Fan; Sijia Liu; Pin-Yu Chen; Gaoyuan Zhang; Chuang Gan; | |
1644 | Learning Transferable Features for Point Cloud Detection Via 3D Contrastive Co-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we introduce the framework of 3D Contrastive Co-training (3D-CoCo) with two technical contributions. |
Zeng Yihan; Chunwei Wang; Yunbo Wang; Hang Xu; Chaoqiang Ye; Zhen Yang; Chao Ma; | |
1645 | SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the multi-environment Symbolic Interactive Language Grounding benchmark (SILG), which unifies a collection of diverse grounded language learning environments under a common interface. |
Victor Zhong; Austin Hanjie; Sida Wang; Karthik Narasimhan; Luke Zettlemoyer; | |
1646 | A Surrogate Objective Framework for Prediction+Programming with Soft Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel analytically differentiable surrogate objective framework for real-world linear and semi-definite negative quadratic programming problems with soft linear and non-negative hard constraints. |
Kai Yan; Jie Yan; Chuan Luo; Liting Chen; Qingwei Lin; Dongmei Zhang; | |
1647 | Learning to Predict Trustworthiness with Steep Slope Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the problem of predicting trustworthiness on real-world large-scale datasets, where the task is more challenging due to high-dimensional features, diverse visual concepts, and a large number of samples. |
Yan Luo; Yongkang Wong; Mohan S. Kankanhalli; Qi Zhao; | code |
1648 | On The Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that their combined use may result in a surprising periodic behavior of optimization dynamics: the training process regularly exhibits destabilizations that, however, do not lead to complete divergence but cause a new period of training. |
Ekaterina Lobacheva; Maxim Kodryan; Nadezhda Chirkova; Andrey Malinin; Dmitry P. Vetrov; | |
1649 | NeRV: Neural Representations for Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. |
Hao Chen; Bo He; Hanyu Wang; Yixuan Ren; Ser Nam Lim; Abhinav Shrivastava; | code |
1650 | Surrogate Regret Bounds for Polyhedral Losses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide two general results. The first gives a linear surrogate regret bound for any polyhedral (piecewise-linear and convex) surrogate, meaning that surrogate generalization rates translate directly to target rates. The second shows that for sufficiently non-polyhedral surrogates, the regret bound is a square root, meaning fast surrogate generalization rates translate to slow rates for the target. |
Rafael Frongillo; Bo Waggoner; | |
1651 | Last Iterate Convergence of SGD for Least-Squares in The Interpolation Regime Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this context, our contribution is two fold: (i) \emph{from a (stochastic) optimization perspective}, we exhibit an archetypal problem where we can show explicitly the convergence of SGD final iterate for a non-strongly convex problem with constant step-size whereas usual results use some form of average and (ii) \emph{from a statistical perspective}, we give explicit non-asymptotic convergence rates in the over-parameterized setting and leverage a \emph{fine-grained} parameterization of the problem to exhibit polynomial rates that can be faster than $O(1/T)$. |
Aditya Vardhan Varre; Loucas Pillaud-Vivien; Nicolas Flammarion; | |
1652 | Generative Vs. Discriminative: Rethinking The Meta-Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage meta-learning to encourage the model to learn how to learn continually. |
Mohammadamin Banayeeanzade; Rasoul Mirzaiezadeh; Hosein Hasani; Mahdieh Soleymani; | |
1653 | Model, Sample, and Epoch-wise Descents: Exact Solution of Gradient Flow in The Random Feature Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this contribution, we analyze the whole temporal behavior of the generalization and training errors under gradient flow for the random feature model. |
Antoine Bodin; Nicolas Macris; | |
1654 | Rethinking Graph Transformers with Spectral Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present the \textit{Spectral Attention Network} (SAN), which uses a learned positional encoding (LPE) that can take advantage of the full Laplacian spectrum to learn the position of each node in a given graph. |
Devin Kreuzer; Dominique Beaini; Will Hamilton; Vincent L�tourneau; Prudencio Tossou; | |
1655 | Perceptual Score: What Data Modalities Does Your Model Perceive? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To study and quantify this concern, we introduce the perceptual score, a metric that assesses the degree to which a model relies on the different subsets of the input features, i.e., modalities. |
Itai Gat; Idan Schwartz; Alex Schwing; | |
1656 | PiRank: Scalable Learning To Rank Via Differentiable Sorting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose PiRank, a new class of differentiable surrogates for ranking, which employ a continuous, temperature-controlled relaxation to the sorting operator based on NeuralSort [1]. |
Robin Swezey; Aditya Grover; Bruno Charron; Stefano Ermon; | |
1657 | Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator. |
Liming Jiang; Bo Dai; Wayne Wu; Chen Change Loy; | code |
1658 | CoFrNets: Interpretable Neural Architecture Inspired By Continued Fractions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel neural architecture, CoFrNet, inspired by the form of continued fractions which are known to have many attractive properties in number theory, such as fast convergence of approximations to real numbers. |
Isha Puri; Amit Dhurandhar; Tejaswini Pedapati; Karthikeyan Shanmugam; Dennis Wei; Kush R. Varshney; | |
1659 | Iterative Teaching By Label Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. |
Weiyang Liu; Zhen Liu; Hanchen Wang; Liam Paull; Bernhard Sch�lkopf; Adrian Weller; | |
1660 | On Density Estimation with Diffusion Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We answer this in the affirmative, and introduce a family of diffusion-based generative models that obtain state-of-the-art likelihoods on standard image density estimation benchmarks. |
Diederik Kingma; Tim Salimans; Ben Poole; Jonathan Ho; | |
1661 | FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, observing distinctive error patterns and correction operations (i.e., insertion, deletion, and substitution) in ASR, we propose FastCorrect, a novel NAR error correction model based on edit alignment. |
Yichong Leng; Xu Tan; Linchen Zhu; Jin Xu; Renqian Luo; Linquan Liu; Tao Qin; Xiangyang Li; Edward Lin; Tie-Yan Liu; | |
1662 | Integrated Latent Heterogeneity and Invariance Learning in Kernel Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Kernelized Heterogeneous Risk Minimization (KerHRM) algorithm, which achieves both the latent heterogeneity exploration and invariant learning in kernel space, and then gives feedback to the original neural network by appointing invariant gradient direction. |
Jiashuo Liu; Zheyuan Hu; Peng Cui; Bo Li; Zheyan Shen; | |
1663 | Hierarchical Reinforcement Learning with Timed Subgoals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Hierarchical reinforcement learning with Timed Subgoals (HiTS), an HRL algorithm that enables the agent to adapt its timing to a dynamic environment by not only specifying what goal state is to be reached but also when. |
Nico G�rtler; Dieter B�chler; Georg Martius; | |
1664 | Fair Scheduling for Time-dependent Resources Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a fair resource scheduling problem, where a set of interval jobs are to be allocated to heterogeneous machines controlled by intellectual agents. |
Bo Li; Minming Li; Ruilong Zhang; | |
1665 | SNIPS: Solving Noisy Inverse Problems Stochastically Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we introduce a novel stochastic algorithm dubbed SNIPS, which draws samples from the posterior distribution of any linear inverse problem, where the observation is assumed to be contaminated by additive white Gaussian noise. |
Bahjat Kawar; Gregory Vaksman; Michael Elad; | |
1666 | Stateful ODE-Nets Using Basis Function Expansions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we reconsider formulations of the weights as continuous-in-depth functions using linear combinations of basis functions which enables us to leverage parameter transformations such as function projections. |
Alejandro Queiruga; N. Benjamin Erichson; Liam Hodgkinson; Michael W. Mahoney; | |
1667 | Beyond The Signs: Nonparametric Tensor Completion Via Sign Series Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of tensor estimation from noisy observations with possibly missing entries. |
Chanwoo Lee; Miaoyan Wang; | |
1668 | Functional Variational Inference Based on Stochastic Process Generators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new solution to this problem called Functional Variational Inference (FVI). |
Chao Ma; Jos� Miguel Hern�ndez-Lobato; | |
1669 | TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce a test-time feature alignment strategy utilizing offline feature summarization and online moment matching, which regularizes adaptation without revisiting training data. |
Yuejiang Liu; Parth Kothari; Bastien van Delft; Baptiste Bellot-Gurlet; Taylor Mordan; Alexandre Alahi; | |
1670 | Double Machine Learning Density Estimation for Local Treatment Effects with Instruments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of estimating the density of the causal effect of a binary treatment on a continuous outcome given a binary instrumental variable in the presence of covariates. |
Yonghan Jung; Jin Tian; Elias Bareinboim; | |
1671 | Dirichlet Energy Constrained Learning for Deep Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs. |
Kaixiong Zhou; Xiao Huang; Daochen Zha; Rui Chen; Li Li; Soo-Hyun Choi; Xia Hu; | |
1672 | Accelerating Robotic Reinforcement Learning Via Parameterized Action Primitives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy. |
Murtaza Dalal; Deepak Pathak; Russ R. Salakhutdinov; | |
1673 | Boosted CVaR Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To learn such randomized classifiers, we propose the Boosted CVaR Classification framework which is motivated by a direct relationship between CVaR and a classical boosting algorithm called LPBoost. |
Runtian Zhai; Chen Dan; Arun Suggala; J. Zico Kolter; Pradeep Ravikumar; | |
1674 | Disentangled Contrastive Learning on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the Disentangled Graph Contrastive Learning (DGCL) method, which is able to learn disentangled graph-level representations with self-supervision. |
Haoyang Li; Xin Wang; Ziwei Zhang; Zehuan Yuan; Hang Li; Wenwu Zhu; | |
1675 | Widening The Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the first study of using human visual explanations in human-in-the-loop reinforcement learning (HIRL). |
Lin Guan; Mudit Verma; Sihang Guo; Ruohan Zhang; Subbarao Kambhampati; | |
1676 | SOLQ: Segmenting Objects By Learning Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an end-to-end framework for instance segmentation. |
Bin Dong; Fangao Zeng; Tiancai Wang; Xiangyu Zhang; Yichen Wei; | |
1677 | Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a differentiable contact model, which can capture contact mechanics: frictionless/frictional, as well as elastic/inelastic. |
Yaofeng Desmond Zhong; Biswadip Dey; Amit Chakraborty; | |
1678 | Best-case Lower Bounds in Online Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we initiate the study of best-case lower bounds in online convex optimization, wherein we bound the largest \emph{improvement} an algorithm can obtain relative to the single best action in hindsight. |
Crist�bal Guzm�n; Nishant Mehta; Ali Mortazavi; | |
1679 | A Comprehensively Tight Analysis of Gradient Descent for PCA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide a general tight analysis for the gap-dependent rate at $O(\frac{1}{\Delta}\log\frac{1}{\epsilon})$ that holds for any real symmetric matrix. |
Zhiqiang Xu; Ping Li; | |
1680 | On Robust Optimal Transport: Computational Complexity and Barycenter Computation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider robust variants of the standard optimal transport, named robust optimal transport, where marginal constraints are relaxed via Kullback-Leibler divergence. |
Khang Le; Huy Nguyen; Quang Nguyen; Tung Pham; Hung Bui; Nhat Ho; | |
1681 | Asymptotically Best Causal Effect Identification with Multi-Armed Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce new tools for constructing finite-sample confidence bounds on estimates of the asymptotic variance that account for the estimation of potentially complex nuisance functions, and adapt the best-arm-identification algorithms of LUCB and Successive Elimination to use these bounds. |
Alan Malek; Silvia Chiappa; | |
1682 | Learning Rule Influences Recurrent Network Representations But Not Attractor Structure in Decision-making Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We focus our investigation on how RNN learning rule and task design affect RNN computation. |
Brandon McMahan; Michael Kleinman; Jonathan Kao; | |
1683 | Few-Shot Segmentation Via Cycle-Consistent Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on utilizing pixel-wise relationships between support and target images to facilitate the few-shot semantic segmentation task. |
Gengwei Zhang; Guoliang Kang; Yi Yang; Yunchao Wei; | |
1684 | DropGNN: Random Dropouts Increase The Expressiveness of Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. |
P�l Andr�s Papp; Karolis Martinkus; Lukas Faber; Roger Wattenhofer; | |
1685 | Photonic Differential Privacy with Direct Feedback Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a theoretical analysis of our adaptive privacy mechanism, carefully measuring how the noise of optical random projections propagates in the process and gives rise to provable Differential Privacy. |
Ruben Ohana; Hamlet Medina; Julien Launay; Alessandro Cappelli; Iacopo Poli; Liva Ralaivola; Alain Rakotomamonjy; | |
1686 | Searching Parameterized AP Loss for Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation. |
Tao Chenxin; Zizhang Li; Xizhou Zhu; Gao Huang; Yong Liu; jifeng dai; | |
1687 | Fair Exploration Via Axiomatic Bargaining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the consideration of fairly sharing the cost of exploration between multiple groups in learning problems, we develop the Nash bargaining solution in the context of multi-armed bandits. |
Jackie Baek; Vivek Farias; | |
1688 | Unifying Lower Bounds on Prediction Dimension of Convex Surrogates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new tool based on property elicitation, $d$-flats, for lower-bounding convex consistency dimension. |
Jessica Finocchiaro; Rafael Frongillo; Bo Waggoner; | |
1689 | Ultrahyperbolic Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a method to learn parametric models in ultrahyperbolic space. |
Marc Law; | |
1690 | NeuroMLR: Robust & Reliable Route Recommendation on Road Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: First, our study reveals that a significant portion of the routes recommended by existing methods fail to reach the destination. Second, existing techniques are transductive in nature; hence, they fail to recommend routes if unseen roads are encountered at inference time. In this paper, we address these limitations through an inductive algorithm called NeuroMLR. |
Jayant Jain; Vrittika Bagadia; Sahil Manchanda; Sayan Ranu; | |
1691 | Risk Bounds and Calibration for A Smart Predict-then-Optimize Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we greatly expand upon the consistency results for the SPO+ loss provided by Elmachtoub and Grigas [2021]. |
Heyuan Liu; Paul Grigas; | |
1692 | Three-dimensional Spike Localization and Improved Motion Correction for Neuropixels Recordings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we introduce several new methods for extracting useful spiking information from NP probes. |
Julien Boussard; Erdem Varol; Hyun Dong Lee; Nishchal Dethe; Liam Paninski; | |
1693 | Semi-Supervised Semantic Segmentation Via Adaptive Equalization Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we look into this problem, and propose a novel framework for semi-supervised semantic segmentation, named adaptive equalization learning (AEL). |
Hanzhe Hu; Fangyun Wei; Han Hu; Qiwei Ye; Jinshi Cui; Liwei Wang; | code |
1694 | On The Bias-Variance-Cost Tradeoff of Stochastic Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a systematic study of their convergences and total computation complexities for strongly convex, convex, and nonconvex objectives, and demonstrate their superiority over the naive biased stochastic gradient method. |
Yifan Hu; Xin Chen; Niao He; | |
1695 | Averaging on The Bures-Wasserstein Manifold: Dimension-free Convergence of Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we prove new geodesic convexity results which provide stronger control of the iterates, yielding a dimension-free convergence rate. |
Jason Altschuler; Sinho Chewi; Patrik Gerber; Austin Stromme; | |
1696 | Reinforcement Learning in Newcomblike Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study value-based reinforcement learning algorithms in the Newcomblike setting, and answer some of the fundamental theoretical questions about the behaviour of such algorithms in these environments. |
James Bell; Linda Linsefors; Caspar Oesterheld; Joar Skalse; | |
1697 | Comprehensive Knowledge Distillation with Causal Intervention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these two issues, in this paper, we propose comprehensive, interventional distillation (CID) that captures both sample and class representations from the teacher while removing the bias with causal intervention. |
Xiang Deng; Zhongfei Zhang; | |
1698 | Reinforcement Learning with Latent Flow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by leading video classification architectures, we introduce the Flow of Latents for Reinforcement Learning (Flare), a network architecture for RL that explicitly encodes temporal information through latent vector differences. |
Wenling Shang; Xiaofei Wang; Aravind Srinivas; Aravind Rajeswaran; Yang Gao; Pieter Abbeel; Misha Laskin; | |
1699 | Understanding How Encoder-Decoder Architectures Attend Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate how encoder-decoder networks solve different sequence-to-sequence tasks. |
Kyle Aitken; Vinay Ramasesh; Yuan Cao; Niru Maheswaranathan; | |
1700 | Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a first step to address these challenges, we propose LaSynth and show its efficacy in a restricted-C domain (i.e., C code with tens of tokens, with sequential, branching, loop and simple arithmetic operations but no library call). |
Xinyun Chen; Dawn Song; Yuandong Tian; | |
1701 | Two Steps to Risk Sensitivity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we consider a particularly relevant risk measure for modeling human and animal planning, called conditional value-at-risk (CVaR), which quantifies worst-case outcomes (e.g., vehicle accidents or predation). |
Christopher Gagne; Peter Dayan; | |
1702 | DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce DECAF: a GAN-based fair synthetic data generator for tabular data. |
Boris van Breugel; Trent Kyono; Jeroen Berrevoets; Mihaela van der Schaar; | |
1703 | EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present EvoGrad, a new approach to meta-learning that draws upon evolutionary techniques to more efficiently compute hypergradients. |
Ondrej Bohdal; Yongxin Yang; Timothy Hospedales; | |
1704 | Biological Key-value Memory Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an implementation of basic key-value memory that stores inputs using a combination of biologically plausible three-factor plasticity rules. |
Danil Tyulmankov; Ching Fang; Annapurna Vadaparty; Guangyu Robert Yang; | |
1705 | Correlated Stochastic Block Models: Exact Graph Matching with Applications to Recovering Communities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the task of learning latent community structure from multiple correlated networks. |
Miklos Racz; Anirudh Sridhar; | |
1706 | Twice Regularized MDPs and The Equivalence Between Robustness and Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to learn robust MDPs using regularization. |
Esther Derman; Matthieu Geist; Shie Mannor; | |
1707 | Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a model-based algorithm named UCBVI-$\gamma$, which is based on the \emph{optimism in the face of uncertainty principle} and the Bernstein-type bonus. |
jiafan he; Dongruo Zhou; Quanquan Gu; | |
1708 | Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a new framework for sparse deep learning, which has the above issues addressed in a coherent way. |
Yan Sun; Wenjun Xiong; Faming Liang; | |
1709 | Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a new notion—decision calibration—that requires the predicted distribution and true distribution over classes to be “indistinguishable” to downstream decision-makers. |
Shengjia Zhao; Michael Kim; Roshni Sahoo; Tengyu Ma; Stefano Ermon; | |
1710 | Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the task of minimizing the sum of smooth and strongly convex functions stored in a decentralized manner across the nodes of a communication network whose links are allowed to change in time. |
Dmitry Kovalev; Elnur Gasanov; Alexander Gasnikov; Peter Richtarik; | |
1711 | Testing Probabilistic Circuits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The primary contribution of this paper is a closeness test for PCs with respect to the total variation distance metric. |
Yash Pralhad Pote; Kuldeep S Meel; | |
1712 | Pseudo-Spherical Contrastive Divergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose pseudo-spherical contrastive divergence (PS-CD) to generalize maximum likelihood learning of EBMs. |
Lantao Yu; Jiaming Song; Yang Song; Stefano Ermon; | |
1713 | NORESQA: A Framework for Speech Quality Assessment Using Non-Matching References Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new direction for speech quality assessment. |
Pranay Manocha; Buye Xu; Anurag Kumar; | |
1714 | AFEC: Active Forgetting of Negative Transfer in Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the biological active forgetting, we propose to actively forget the old knowledge that limits the learning of new tasks to benefit continual learning. |
Liyuan Wang; Mingtian Zhang; Zhongfan Jia; Qian Li; Chenglong Bao; Kaisheng Ma; Jun Zhu; Yi Zhong; | |
1715 | Heterogeneous Multi-player Multi-armed Bandits: Closing The Gap and Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose BEACON — Batched Exploration with Adaptive COmmunicatioN — that closes this gap. |
Chengshuai Shi; Wei Xiong; Cong Shen; Jing Yang; | |
1716 | SWAD: Domain Generalization By Seeking Flat Minima Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we theoretically show that finding flat minima results in a smaller domain generalization gap. |
Junbum Cha; Sanghyuk Chun; Kyungjae Lee; Han-Cheol Cho; Seunghyun Park; Yunsung Lee; Sungrae Park; | code |
1717 | Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the long-term forecasting problem of time series. |
haixu wu; Jiehui Xu; Jianmin Wang; Mingsheng Long; | code |
1718 | Predicting Event Memorability from Contextual Visual Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we investigate factors that affect event memorability according to a cued recall process. |
Qianli Xu; Fen Fang; Ana Molino; Vigneshwaran Subbaraju; Joo-Hwee Lim; | code |
1719 | Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel model called CTR to solve these problems. |
Zixuan Ke; Bing Liu; Nianzu Ma; Hu Xu; Lei Shu; | |
1720 | Bandits with Many Optimal Arms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider a stochastic bandit problem with a possibly infinite number of arms. |
Rianne de Heide; James Cheshire; Pierre M�nard; Alexandra Carpentier; | |
1721 | Combiner: Full Attention Transformer with Sparse Computation Cost Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we propose Combiner, which provides full attention capability in each attention head while maintaining low computation and memory complexity. |
Hongyu Ren; Hanjun Dai; Zihang Dai; Mengjiao Yang; Jure Leskovec; Dale Schuurmans; Bo Dai; | |
1722 | Geometry Processing with Neural Fields Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper instead proposes the use of neural fields for geometry processing. |
Guandao Yang; Serge Belongie; Bharath Hariharan; Vladlen Koltun; | code |
1723 | Contextual Recommendations and Low-Regret Cutting-Plane Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the following variant of contextual linear bandits motivated by routing applications in navigational engines and recommendation systems. |
Sreenivas Gollapudi; Guru Guruganesh; Kostas Kollias; Pasin Manurangsi; Renato Leme; Jon Schneider; | |
1724 | Speech Separation Using An Asynchronous Fully Recurrent Convolutional Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to use a bio-inspired architecture called Fully Recurrent Convolutional Neural Network (FRCNN) to solve the separation task. |
Xiaolin Hu; Kai Li; Weiyi Zhang; Yi Luo; Jean-Marie Lemercier; Timo Gerkmann; | |
1725 | Reinforcement Learning Enhanced Explainer for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose a RL-enhanced GNN explainer, RG-Explainer, which consists of three main components: starting point selection, iterative graph generation and stopping criteria learning. |
Caihua Shan; Yifei Shen; Yao Zhang; Xiang Li; Dongsheng Li; | |
1726 | NAS-Bench-x11 and The Power of Learning Curves Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a method using singular value decomposition and noise modeling to create surrogate benchmarks, NAS-Bench-111, NAS-Bench-311, and NAS-Bench-NLP11, that output the full training information for each architecture, rather than just the final validation accuracy. |
Shen Yan; Colin White; Yash Savani; Frank Hutter; | |
1727 | Observation-Free Attacks on Stochastic Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study data corruption attacks on stochastic multi arm bandit algorithms. |
Yinglun Xu; Bhuvesh Kumar; Jacob D. Abernethy; | |
1728 | Learning Disentangled Behavior Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design Disentangled Behavior Embedding (DBE) to learn robust behavioral embeddings from unlabeled, multi-view, high-resolution behavioral videos across different animals and multiple sessions. |
Changhao Shi; Sivan Schwartz; Shahar Levy; Shay Achvat; Maisan Abboud; Amir Ghanayim; Jackie Schiller; Gal Mishne; | |
1729 | The Sensory Neuron As A Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the emergence of collective behavior from complex cellular systems, we build systems that feed each sensory input from the environment into distinct, but identical neural networks, each with no fixed relationship with one another. |
Yujin Tang; David Ha; | code |
1730 | Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Built upon EG+ and EAG, this paper proposes a two-time-scale EG with anchoring, named fast extragradient (FEG), that has a fast $\mathcal{O}(1/k^2)$ rate on the squared gradient norm for smooth structured nonconvex-nonconcave problems; the corresponding saddle-gradient operator satisfies the negative comonotonicity condition. |
Sucheol Lee; Donghwan Kim; | |
1731 | Analysis of Sensing Spectral for Signal Recovery Under A Generalized Linear Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main goal in this paper is to understand the impact of sensing matrices, or more specifically the spectrum of sensing matrices, on the difficulty of recovering $\mathbf{x}$ from $\mathbf{y}$. |
Junjie Ma; Ji Xu; Arian Maleki; | |
1732 | Revisiting ResNets: Improved Training and Scaling Strategies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our work revisits the canonical ResNet and studies these three aspects in an effort to disentangle them. |
Irwan Bello; William Fedus; Xianzhi Du; Ekin Dogus Cubuk; Aravind Srinivas; Tsung-Yi Lin; Jonathon Shlens; Barret Zoph; | |
1733 | Sparse Flows: Pruning Continuous-depth Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we design a framework to decipher the internal dynamics of these continuous depth models by pruning their network architectures. |
Lucas Liebenwein; Ramin Hasani; Alexander Amini; Daniela Rus; | |
1734 | Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel blind SR framework to super-resolve LR images degraded by arbitrary blur kernel with accurate kernel estimation in frequency domain. |
Guangpin Tao; Xiaozhong Ji; Wenzhuo Wang; Shuo Chen; Chuming Lin; Yun Cao; Tong Lu; Donghao Luo; Ying Tai; | |
1735 | On The Rate of Convergence of Regularized Learning in Games: From Bandits and Uncertainty to Optimism and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we examine the convergence rate of a wide range of regularized methods for learning in games. |
Angeliki Giannou; Emmanouil-Vasileios Vlatakis-Gkaragkounis; Panayotis Mertikopoulos; | |
1736 | SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the Simultaneous Learning of Adjacency and GNN Parameters with Self-supervision, or SLAPS, a method that provides more supervision for inferring a graph structure through self-supervision. |
Bahare Fatemi; Layla El Asri; Seyed Mehran Kazemi; | |
1737 | Aligning Pretraining for Detection Via Object-Level Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we follow this principle with a pretraining method specifically designed for the task of object detection. |
Fangyun Wei; Yue Gao; Zhirong Wu; Han Hu; Stephen Lin; | code |
1738 | Double/Debiased Machine Learning for Dynamic Treatment Effects Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an extension of the double/debiased machine learning framework to estimate the dynamic effects of treatments and apply it to a concrete linear Markovian high-dimensional state space model and to general structural nested mean models. |
Greg Lewis; Vasilis Syrgkanis; | |
1739 | Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Borrowing inspiration from Independent Component Analysis (ICA) and sparse coding, we propose applying an $L_1$ loss to the VAE’s generative Jacobian during training to encourage local latent variable alignment with independent factors of variation in images of multiple objects or images with multiple parts. |
Travers Rhodes; Daniel Lee; | |
1740 | Design of Experiments for Stochastic Contextual Linear Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a theoretical analysis as well as numerical experiments on both synthetic and real-world datasets. |
Andrea Zanette; Kefan Dong; Jonathan Lee; Emma Brunskill; | |
1741 | Encoding Spatial Distribution of Convolutional Features for Texture Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the context of texture representation, this paper addressed the issue by proposing Fractal Encoding (FE), a feature encoding module grounded by multi-fractal geometry. |
Yong Xu; Feng Li; Zhile Chen; Jinxiu Liang; Yuhui Quan; | |
1742 | Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an efficient and trainable \emph{local} Lipschitz upper bound by considering the interactions between activation functions (e.g. ReLU) and weight matrices. |
Yujia Huang; Huan Zhang; Yuanyuan Shi; J. Zico Kolter; Anima Anandkumar; | |
1743 | Average-Reward Learning and Planning with Options Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our contributions include general convergent off-policy inter-option learning algorithms, intra-option algorithms for learning values and models, as well as sample-based planning variants of our learning algorithms. |
Yi Wan; Abhishek Naik; Rich Sutton; | |
1744 | SSAL: Synergizing Between Self-Training and Adversarial Learning for Domain Adaptive Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to leverage model’s predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment. |
Muhammad Akhtar Munir; Muhammad Haris Khan; M. Sarfraz; Mohsen Ali; | |
1745 | Counterexample Guided RL Policy Refinement Using Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a methodology for counterexample guided refinement of a trained RL policy against a given safety specification. |
Briti Gangopadhyay; Pallab Dasgupta; | |
1746 | Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel way to accelerate attention calculation for Transformers with RPE on top of the kernelized attention. |
Shengjie Luo; Shanda Li; Tianle Cai; Di He; Dinglan Peng; Shuxin Zheng; Guolin Ke; Liwei Wang; Tie-Yan Liu; | |
1747 | Learning in Non-Cooperative Configurable Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two learning algorithms to minimize the configurator’s expected regret, which exploits the problem’s structure, depending on the agent’s feedback. |
Giorgia Ramponi; Alberto Maria Metelli; Alessandro Concetti; Marcello Restelli; | |
1748 | Identification of Partially Observed Linear Causal Models: Graphical Conditions for The Non-Gaussian and Heterogeneous Cases Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider partially observed linear models with either non-Gaussian or heterogeneous errors. |
Jeffrey Adams; Niels Hansen; Kun Zhang; | |
1749 | DIB-R++: Learning to Predict Lighting and Material with A Hybrid Differentiable Renderer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose DIBR++, a hybrid differentiable renderer which supports these photorealistic effects by combining rasterization and ray-tracing, taking the advantage of their respective strengths—speed and realism. |
Wenzheng Chen; Joey Litalien; Jun Gao; Zian Wang; Clement Fuji Tsang; Sameh Khamis; Or Litany; Sanja Fidler; | |
1750 | Coresets for Time Series Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is an algorithm to construct coresets for the maximum likelihood objective for this mixture model. |
Lingxiao Huang; K Sudhir; Nisheeth Vishnoi; | |
1751 | A Variational Perspective on Diffusion-Based Generative Models and Score Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we approach the (continuous-time) generative diffusion directly and derive a variational framework for likelihood estimation, which includes continuous-time normalizing flows as a special case, and can be seen as an infinitely deep variational autoencoder. |
Chin-Wei Huang; Jae Hyun Lim; Aaron C. Courville; | |
1752 | Online Active Learning with Surrogate Loss Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive a novel active learning algorithm in the streaming setting for binary classification tasks. |
Giulia DeSalvo; Claudio Gentile; Tobias Sommer Thune; | |
1753 | Does Preprocessing Help Training Over-parameterized Neural Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose two novel preprocessing ideas to bypass this $\Omega(mnd)$ barrier:* First, by preprocessing the initial weights of the neural networks, we can train the neural network in $\widetilde{O}(m^{1-\Theta(1/d)} n d)$ cost per iteration. |
Zhao Song; Shuo Yang; Ruizhe Zhang; | |
1754 | Causal Influence Detection for Improving Efficiency in Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our idea in this work is that learning can be efficiently guided by knowing when and what the agent can influence with its actions. |
Maximilian Seitzer; Bernhard Sch�lkopf; Georg Martius; | |
1755 | LADA: Look-Ahead Data Acquisition Via Augmentation for Deep Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes Look-Ahead Data Acquisition via augmentation, or LADA framework, that looks ahead the effect of data augmentation in the process of acquisition. |
Yoon-Yeong Kim; Kyungwoo Song; JoonHo Jang; Il-chul Moon; | |
1756 | Policy Optimization in Adversarial MDPs: Improved Exploration Via Dilated Bonuses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To eliminate the need of such assumptions, in this work, we develop a general solution that adds dilated bonuses to the policy update to facilitate global exploration. |
Haipeng Luo; Chen-Yu Wei; Chung-Wei Lee; | |
1757 | Multiclass Versus Binary Differentially Private PAC Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show a generic reduction from multiclass differentially private PAC learning to binary private PAC learning. |
Satchit Sivakumar; Mark Bun; Marco Gaboardi; | |
1758 | Adversarially Robust Change Point Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate a phase transition phenomenon in change point detection. |
Mengchu Li; Yi Yu; | |
1759 | Cycle Self-Training for Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Cycle Self-Training (CST), a principled self-training algorithm that explicitly enforces pseudo-labels to generalize across domains. |
Hong Liu; Jianmin Wang; Mingsheng Long; | |
1760 | Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from other different but relevant categories. |
Bingchen Zhao; Kai Han; | |
1761 | Stochastic Anderson Mixing for Nonconvex Stochastic Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, by introducing damped projection and adaptive regularization to the classical AM, we propose a Stochastic Anderson Mixing (SAM) scheme to solve nonconvex stochastic optimization problems. |
Fuchao Wei; Chenglong Bao; Yang Liu; | |
1762 | Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with A Generative Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper considers a Markov decision process (MDP) that admits a set of state-action features, which can linearly express (or approximate) its probability transition kernel. |
Bingyan Wang; Yuling Yan; Jianqing Fan; | |
1763 | NN-Baker: A Neural-network Infused Algorithmic Framework for Optimization Problems on Geometric Intersection Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the geometric setting, where graphs are induced by points in a fixed dimensional Euclidean space. |
Evan McCarty; Qi Zhao; Anastasios Sidiropoulos; Yusu Wang; | |
1764 | A Note on Sparse Generalized Eigenvalue Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a detailed sensitivity analysis for SGEP and establish the rate-optimal perturbation bound under the sparse setting. |
Yunfeng Cai; Guanhua Fang; Ping Li; | |
1765 | RMIX: Learning Risk-Sensitive Policies ForCooperative Reinforcement Learning Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose RMIX, a novel cooperative MARL method with the Conditional Value at Risk (CVaR) measure over the learned distributions of individuals’ Q values. |
Wei Qiu; Xinrun Wang; Runsheng Yu; Rundong Wang; Xu He; Bo An; Svetlana Obraztsova; Zinovi Rabinovich; | |
1766 | Optimal Policies Tend To Seek Power Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To clarify this debate, we develop the first formal theory of the statistical tendencies of optimal policies. |
Alex Turner; Logan Smith; Rohin Shah; Andrew Critch; Prasad Tadepalli; | |
1767 | Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we theoretically show that inductive biases on both the training framework and the data are needed to develop a compositional communication. |
Lukasz Kucinski; Tomasz Korbak; Pawel Kolodziej; Piotr Milos; | |
1768 | PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that the landscape can be significantly simplified by taking a general approach of mapping a graph to a sequence of tokens and pointers. |
Zimin Chen; Vincent Hellendoorn; Pascal Lamblin; Petros Maniatis; Pierre-Antoine Manzagol; Daniel Tarlow; Subhodeep Moitra; | code |
1769 | COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. |
Yu Meng; Chenyan Xiong; Payal Bajaj; saurabh tiwary; Paul Bennett; Jiawei Han; XIA SONG; | |
1770 | Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we develop a novel sensitivity analysis of the proximal mapping involved in each algorithm iteration. |
Qi Deng; Wenzhi Gao; | |
1771 | XDO: A Double Oracle Algorithm for Extensive-Form Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Extensive-Form Double Oracle (XDO), an extensive-form double oracle algorithm for two-player zero-sum games that is guaranteed to converge to an approximate Nash equilibrium linearly in the number of infostates. |
Stephen McAleer; JB Lanier; Kevin Wang; Pierre Baldi; Roy Fox; | |
1772 | Active Assessment of Prediction Services As Accuracy Surface Over Attribute Combinations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to evaluate the accuracy of a black-box classification model, not as a single aggregate on a given test data distribution, but as a surface over a large number of combinations of attributes characterizing multiple test data distributions. |
Vihari Piratla; Soumen Chakrabarti; Sunita Sarawagi; | |
1773 | A Mechanistic Multi-area Recurrent Network Model of Decision-making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to use multi-area RNNs with neuroscience-inspired architecture constraints to derive key features of multi-area computation. |
Michael Kleinman; Chandramouli Chandrasekaran; Jonathan Kao; | |
1774 | Learning to Compose Visual Relations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we instead propose to represent each relation as an unnormalized density (an energy-based model), enabling us to compose separate relations in a factorized manner. |
Nan Liu; Shuang Li; Yilun Du; Josh Tenenbaum; Antonio Torralba; | |
1775 | Identity Testing for Mallows Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we devise identity tests for ranking data that is generated from Mallows model both in the \emph{asymptotic} and \emph{non-asymptotic} settings. |
R�bert Busa-Fekete; Dimitris Fotakis; Balazs Szorenyi; Emmanouil Zampetakis; | |
1776 | Bandits with Knapsacks Beyond The Worst Case Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While worst-case regret bounds for BwK are well-understood, we present three results that go beyond the worst-case perspective. |
Karthik Abinav Sankararaman; Aleksandrs Slivkins; | |
1777 | Closing The Loop in Medical Decision Support By Understanding Clinical Decision-making: A Case Study on Organ Transplantation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In light of this, we highlight that more attention on understanding clinical decision-making is required both to elucidate current clinical practices and to enable effective human-machine interactions. |
Yuchao Qin; Fergus Imrie; Alihan H�y�k; Daniel Jarrett; alexander gimson; Mihaela van der Schaar; | |
1778 | Change Point Detection Via Multivariate Singular Spectrum Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop and analyze an algorithm for CPD that is inspired by a variant of the classical singular spectrum analysis (SSA) approach for time series by combining it with the classical cumulative sum (CUSUM) statistic from sequential hypothesis testing. |
Arwa Alanqary; Abdullah Alomar; Devavrat Shah; | |
1779 | Meta-learning to Improve Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an efficient, gradient-based algorithm to meta-learn PT hyperparameters. |
Aniruddh Raghu; Jonathan Lorraine; Simon Kornblith; Matthew McDermott; David K. Duvenaud; | |
1780 | Fair Sparse Regression with Clustering: An Invex Relaxation for A Combinatorial Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the problem of fair sparse regression on a biased dataset where bias depends upon a hidden binary attribute. |
Adarsh Barik; Jean Honorio; | |
1781 | Probabilistic Margins for Instance Reweighting in Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighing adversarial data. |
qizhou wang; Feng Liu; Bo Han; Tongliang Liu; Chen Gong; Gang Niu; Mingyuan Zhou; Masashi Sugiyama; | |
1782 | Unbalanced Optimal Transport Through Non-negative Penalized Linear Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper addresses the problem of Unbalanced Optimal Transport (UOT) in which the marginal conditions are relaxed (using weighted penalties in lieu of equality) and no additional regularization is enforced on the OT plan. |
Laetitia Chapel; R�mi Flamary; Haoran Wu; C�dric F�votte; Gilles Gasso; | |
1783 | The Difficulty of Passive Learning in Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the vein of Held & Hein’s classic 1963 experiment, we propose the tandem learning experimental paradigm which facilitates our empirical analysis of the difficulties in offline reinforcement learning. |
Georg Ostrovski; Pablo Samuel Castro; Will Dabney; | |
1784 | Intriguing Properties of Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: An important question is how such flexibility (in attending image-wide context conditioned on a given patch) can facilitate handling nuisances in natural images e.g., severe occlusions, domain shifts, spatial permutations, adversarial and natural perturbations. We systematically study this question via an extensive set of experiments encompassing three ViT families and provide comparisons with a high-performing convolutional neural network (CNN). |
Muhammad Muzammal Naseer; Kanchana Ranasinghe; Salman H. Khan; Munawar Hayat; Fahad Shahbaz Khan; Ming-Hsuan Yang; | |
1785 | PartialFed: Cross-Domain Personalized Federated Learning Via Partial Initialization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenging problem, we propose a novel idea, PartialFed, which loads a subset of the global model’s parameters rather than loading the entire model used in most previous works. |
Benyuan Sun; Hongxing Huo; YI YANG; Bo Bai; | |
1786 | Adaptive Diffusion in Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose the adaptive diffusion convolution (ADC) strategy to automatically learn the optimal neighborhood size from the data. |
Jialin Zhao; Yuxiao Dong; Ming Ding; Evgeny Kharlamov; Jie Tang; | |
1787 | Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend the above direction to a combinatorial semi-bandit setting and study a variant of stochastic MAB, where arms are subject to matroid constraints and each arm becomes unavailable (blocked) for a fixed number of rounds after each play. |
Orestis Papadigenopoulos; Constantine Caramanis; | |
1788 | Representer Point Selection Via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the RPS approach, we propose an alternative method based on a local Jacobian Taylor expansion (LJE) of the Jacobian.We empirically compared RPS-LJE with the original RPS-$l_2$ on image classification (with ResNet), text classification recurrent neural networks (with Bi-LSTM), and tabular classification (with XGBoost) tasks. |
Yi Sui; Ga Wu; Scott Sanner; | |
1789 | Editing A Classifier By Rewriting Its Prediction Rules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. |
Shibani Santurkar; Dimitris Tsipras; Mahalaxmi Elango; David Bau; Antonio Torralba; Aleksander Madry; | |
1790 | How Modular Should Neural Module Networks Be for Systematic Generalization? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate that the degree of modularity of the NMN have large influence on systematic generalization. |
Vanessa D'Amario; Tomotake Sasaki; Xavier Boix; | |
1791 | Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Contrast and Mix (CoMix), a new contrastive learning framework that aims to learn discriminative invariant feature representations for unsupervised video domain adaptation. |
Aadarsh Sahoo; Rutav Shah; Rameswar Panda; Kate Saenko; Abir Das; | code |
1792 | The Flip Side of The Reweighted Coin: Duality of Adaptive Dropout and Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that any dropout strategy that adapts to the weights in a monotonic way corresponds to an effective subquadratic regularization penalty, and therefore leads to sparse solutions. |
Daniel LeJeune; Hamid Javadi; Richard Baraniuk; | |
1793 | Active Learning of Convex Halfspaces on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We systematically study the query complexity of learning geodesically convex halfspaces on graphs. |
Maximilian Thiessen; Thomas Gaertner; | |
1794 | Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the introduced finite difference gradient, we propose a new family of Differentiable Spike (Dspike) functions that can adaptively evolve during training to find the optimal shape and smoothness for gradient estimation. |
Yuhang Li; Yufei Guo; Shanghang Zhang; Shikuang Deng; Yongqing Hai; Shi Gu; | |
1795 | Probabilistic Entity Representation Model for Reasoning Over Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Probabilistic Entity Representation Model (PERM) to encode entities as a Multivariate Gaussian density with mean and covariance parameters to capture its semantic position and smooth decision boundary, respectively. |
Nurendra Choudhary; Nikhil Rao; Sumeet Katariya; Karthik Subbian; Chandan Reddy; | |
1796 | Black Box Probabilistic Numerics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, this paper proposes to construct probabilistic numerical methods based only on the final output from a traditional method. |
Onur Teymur; Christopher Foley; Philip Breen; Toni Karvonen; Chris J. Oates; | |
1797 | Interpolation Can Hurt Robust Generalization Even When There Is No Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove this phenomenon for the robust risk of both linear regression and classification, and hence provide the first theoretical result on \emph{robust overfitting}. |
Konstantin Donhauser; Alexandru Tifrea; Michael Aerni; Reinhard Heckel; Fanny Yang; | |
1798 | On The Equivalence Between Neural Network and Support Vector Machine Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent. |
Yilan Chen; Wei Huang; Lam Nguyen; Tsui-Wei Weng; | |
1799 | Learning Semantic Representations to Verify Hardware Designs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a first approach to this new problem, we introduce Design2Vec, a deep architecture that learns semantic abstractions of hardware designs. |
Shobha Vasudevan; Wenjie (Joe) Jiang; David Bieber; Rishabh Singh; hamid shojaei; C. Richard Ho; Charles Sutton; | |
1800 | Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce two cures for ACGAN. |
Minguk Kang; Woohyeon Shim; Minsu Cho; Jaesik Park; | code |
1801 | Towards A Theoretical Framework of Out-of-Distribution Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take the first step towards rigorous and quantitative definitions of 1) what is OOD; and 2) what does it mean by saying an OOD problem is learnable. |
Haotian Ye; Chuanlong Xie; Tianle Cai; Ruichen Li; Zhenguo Li; Liwei Wang; | |
1802 | Slice Sampling Reparameterization Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we describe how to differentiate samples from slice sampling to compute \textit{slice sampling reparameterization gradients}, enabling a richer class of Monte Carlo objective functions to be optimized. |
David Zoltowski; Diana Cai; Ryan P. Adams; | |
1803 | Multi-Label Learning with Pairwise Relevance Ordering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize this problem as a novel learning framework, called multi-label learning with pairwise relevance ordering (PRO). |
Ming-Kun Xie; Sheng-Jun Huang; | |
1804 | Sampling with Trusthworthy Constraints: A Variational Gradient Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function. |
Xingchao Liu; Xin Tong; Qiang Liu; | |
1805 | Robust and Decomposable Average Precision for Image Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a method for robust and decomposable average precision (ROADMAP) addressing two major challenges for end-to-end training of deep neural networks with AP: non-differentiability and non-decomposability. |
Elias Ramzi; Nicolas THOME; Cl�ment Rambour; Nicolas Audebert; Xavier Bitot; | code |
1806 | Fast Rates for Prediction with Limited Expert Advice Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the problem of minimizing the excess generalization error with respect to the best expert prediction in a finite family in the stochastic setting, under limited access to information. |
El Mehdi Saad; Gilles Blanchard; | |
1807 | Probabilistic Transformer For Time Series Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose deep probabilistic methods that combine state-space models (SSMs) with transformer architectures. |
Binh Tang; David Matteson; | |
1808 | A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel hierarchical optimization framework to better solve large-scale DPDPs. |
Yi Ma; Xiaotian Hao; Jianye Hao; Jiawen Lu; Xing Liu; Tong Xialiang; Mingxuan Yuan; Zhigang Li; Jie Tang; Zhaopeng Meng; | |
1809 | Spatio-Temporal Variational Gaussian Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a scalable approach to Gaussian process inference that combines spatio-temporal filtering with natural gradient variational inference, resulting in a non-conjugate GP method for multivariate data that scales linearly with respect to time. |
Oliver Hamelijnck; William Wilkinson; Niki Loppi; Arno Solin; Theodoros Damoulas; | |
1810 | MERLOT: Multimodal Neural Script Knowledge Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech — in an entirely label-free, self-supervised manner. |
Rowan Zellers; Ximing Lu; Jack Hessel; Youngjae Yu; Jae Sung Park; Jize Cao; Ali Farhadi; Yejin Choi; | |
1811 | Fast Approximate Dynamic Programming for Infinite-Horizon Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we consider the infinite-horizon, discounted cost, optimal control of stochastic nonlinear systems with separable cost and constraints in the state and input variables. |
Mohamad Amin Sharifi Kolarijani; Gyula Max; Peyman Mohajerin Mohajerin Esfahani; | |
1812 | Adaptive Risk Minimization: Learning to Adapt to Domain Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts, corresponding to new domains or domain distributions. |
Marvin Zhang; Henrik Marklund; Nikita Dhawan; Abhishek Gupta; Sergey Levine; Chelsea Finn; | |
1813 | Learning State Representations from Random Deep Action-conditional Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution in this work is an empirical finding that random General Value Functions (GVFs), i.e., deep action-conditional predictions—random both in what feature of observations they predict as well as in the sequence of actions the predictions are conditioned upon—form good auxiliary tasks for reinforcement learning (RL) problems. |
Zeyu Zheng; Vivek Veeriah; Risto Vuorio; Richard L. Lewis; Satinder Singh; | code |
1814 | Mixability Made Efficient: Fast Online Multiclass Logistic Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we use quadratic surrogates to make aggregating forecasters more efficient. |
R�mi J�z�quel; Pierre Gaillard; Alessandro Rudi; | |
1815 | Tracking People with 3D Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel approach for tracking multiple people in video. |
Jathushan Rajasegaran; Georgios Pavlakos; Angjoo Kanazawa; Jitendra Malik; | code |
1816 | Off-Policy Risk Assessment in Contextual Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Lipschitz risk functionals, a broad class of objectives that subsumes conditional value-at-risk (CVaR), variance, mean-variance, many distorted risks, and CPT risks, among others. |
Audrey Huang; Liu Leqi; Zachary Lipton; Kamyar Azizzadenesheli; | |
1817 | Adaptive Denoising Via GainTuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose "GainTuning”, a methodology by which CNN models pre-trained on large datasets can be adaptively and selectively adjusted for individual test images. |
Sreyas Mohan; Joshua Vincent; Ramon Manzorro; Peter Crozier; Carlos Fernandez-Granda; Eero Simoncelli; | |
1818 | Optimal Sketching for Trace Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we close the gap between non-adaptive and adaptive algorithms, showing that even non-adaptive algorithms can achieve $O(\sqrt{\log(1/\delta)}/\epsilon + \log(1/\delta))$ matrix-vector products. |
Shuli Jiang; Hai Pham; David Woodruff; Richard Zhang; | |
1819 | Estimating Multi-cause Treatment Effects Via Single-cause Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Single-cause Perturbation (SCP), a novel two-step procedure to estimate the multi-cause treatment effect. |
Zhaozhi Qian; Alicia Curth; Mihaela van der Schaar; | |
1820 | Be Confident! Towards Trustworthy Graph Neural Networks Via Confidence Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel trustworthy GNN model by designing a topology-aware post-hoc calibration function. |
Xiao Wang; Hongrui Liu; Chuan Shi; Cheng Yang; | |
1821 | Learning Riemannian Metric for Disease Progression Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend this approach by learning the metric from the data allowing more flexibility while keeping the interpretability. |
Samuel Gruffaz; Pierre-Emmanuel Poulet; Etienne Maheux; Bruno Jedynak; Stanley DURRLEMAN; | |
1822 | Bias and Variance of The Bayesian-mean Decoder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present widely-applicable approximations to the bias and to the variance of the Bayesian mean, obtained under the minimal and biologically-relevant assumption that the encoding results from a series of independent, though not necessarily identically-distributed, signals. |
Arthur Prat-Carrabin; Michael Woodford; | |
1823 | MIRACLE: Causally-Aware Imputation Via Learning Missing Data Mechanisms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Starting from the premise that imputation methods should preserve the causal structure of the data, we develop a regularization scheme that encourages any baseline imputation method to be causally consistent with the underlying data generating mechanism. |
Trent Kyono; Yao Zhang; Alexis Bellot; Mihaela van der Schaar; | |
1824 | Efficient Training of Visual Transformers with Small Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we empirically analyse different VTs, comparing their robustness in a small training set regime, and we show that, despite having a comparable accuracy when trained on ImageNet, their performance on smaller datasets can be largely different. |
Yahui Liu; Enver Sangineto; Wei Bi; Nicu Sebe; Bruno Lepri; Marco Nadai; | code |
1825 | Small Random Initialization Is Akin to Spectral Learning: Optimization and Generalization Guarantees for Overparameterized Low-rank Matrix Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take a step towards demystifying this role by proving that small random initialization followed by a few iterations of gradient descent behaves akin to popular spectral methods. |
Dominik St�ger; Mahdi Soltanolkotabi; | |
1826 | Efficient Combination of Rematerialization and Offloading for Training DNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We precisely model the costs and constraints corresponding to Deep Learning frameworks such as PyTorch or Tensorflow, we propose optimal algorithms to find a valid sequence of memory-constrained operations and finally, we evaluate the performance of proposed algorithms on realistic networks and computation platforms. |
Olivier Beaumont; Lionel Eyraud-Dubois; Alena Shilova; | |
1827 | Particle Cloud Generation with Message Passing Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a new particle cloud dataset (JetNet), and apply to it existing point cloud GANs. |
Raghav Kansal; Javier Duarte; Hao Su; Breno Orzari; Thiago Tomei; Maurizio Pierini; Mary Touranakou; jean-roch vlimant; Dimitrios Gunopulos; | |
1828 | CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we present CoFiNet – Coarse-to-Fine Network which extracts hierarchical correspondences from coarse to fine without keypoint detection. |
Hao Yu; Fu Li; Mahdi Saleh; Benjamin Busam; Slobodan Ilic; | |
1829 | Partial Success in Closing The Gap Between Human and Machine Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our results give reason for cautious optimism: While there is still much room for improvement, the behavioural difference between human and machine vision is narrowing. |
Robert Geirhos; Kantharaju Narayanappa; Benjamin Mitzkus; Tizian Thieringer; Matthias Bethge; Felix A. Wichmann; Wieland Brendel; | code |
1830 | LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel method for $\textbf{L}$earning $\textbf{L}$ow-dimensional binary $\textbf{C}$odes $(\textbf{LLC})$ for instances as well as classes. |
Aditya Kusupati; Matthew Wallingford; Vivek Ramanujan; Raghav Somani; Jae Sung Park; Krishna Pillutla; Prateek Jain; Sham Kakade; Ali Farhadi; | code |
1831 | Analytic Insights Into Structure and Rank of Neural Network Hessian Maps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we develop theoretical tools to analyze the range of the Hessian map, which provide us with a precise understanding of its rank deficiency and the structural reasons behind it. |
Sidak Pal Singh; Gregor Bachmann; Thomas Hofmann; | |
1832 | Well-tuned Simple Nets Excel on Tabular Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we hypothesize that the key to boosting the performance of neural networks lies in rethinking the joint and simultaneous application of a large set of modern regularization techniques. |
Arlind Kadra; Marius Lindauer; Frank Hutter; Josif Grabocka; | |
1833 | POODLE: Improving Few-shot Learning Via Penalizing Out-of-Distribution Samples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. |
Duong Le; Khoi Nguyen; Quoc-Huy Tran; Rang Nguyen; Binh-Son Hua; | |
1834 | Combinatorial Pure Exploration with Bottleneck Reward Function Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the Combinatorial Pure Exploration problem with the Bottleneck reward function (CPE-B) under the fixed-confidence (FC) and fixed-budget (FB) settings. |
Yihan Du; Yuko Kuroki; Wei Chen; | |
1835 | Densely Connected Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We precondition the noise in accordance with previous invertible units, which we describe as cross-unit coupling. |
Matej Grcic; Ivan Grubi�ic; Sini�a �egvic; | |
1836 | Snowflake: Scaling GNNs to High-dimensional Continuous Control Via Parameter Freezing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To combat this, we introduce Snowflake, a GNN training method for high-dimensional continuous control that freezes parameters in selected parts of the network. |
Charles Blake; Vitaly Kurin; Maximilian Igl; Shimon Whiteson; | |
1837 | Subgame Solving Without Common Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an approach that overcomes this obstacle, by instead working with only low-order knowledge. |
Brian Zhang; Tuomas Sandholm; | |
1838 | Fair Algorithms for Multi-Agent Multi-Armed Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a multi-agent variant of the classical multi-armed bandit problem, in which there are $N$ agents and $K$ arms, and pulling an arm generates a (possibly different) stochastic reward for each agent. |
Safwan Hossain; Evi Micha; Nisarg Shah; | |
1839 | VAST: Value Function Factorization with Variable Agent Sub-Teams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We hypothesize that this is due to the flat factorization scheme, where the VFF operator becomes a performance bottleneck with an increasing number of agents. Therefore, we propose VFF with variable agent sub-teams (VAST). |
Thomy Phan; Fabian Ritz; Lenz Belzner; Philipp Altmann; Thomas Gabor; Claudia Linnhoff-Popien; | |
1840 | On The Stochastic Stability of Deep Markov Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel stability analysis method and provide sufficient conditions of DMM’s stochastic stability. |
Jan Drgona; Sayak Mukherjee; Jiaxin Zhang; Frank Liu; Mahantesh Halappanavar; | |
1841 | Multiwavelet-based Operator Learning for Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this end, we introduce a $\textit{multiwavelet-based neural operator learning scheme}$ that compresses the associated operator’s kernel using fine-grained wavelets. |
Gaurav Gupta; Xiongye Xiao; Paul Bogdan; | |
1842 | Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that bringing intermediate layers’ representations of two augmented versions of an image closer together in self-supervised learning helps to improve the momentum contrastive (MoCo) method. |
Aakash Kaku; Sahana Upadhya; Narges Razavian; | |
1843 | An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a pessimistic-optimistic algorithm for this problem, which is efficient in two aspects. |
Xin Liu; Bin Li; Pengyi Shi; Lei Ying; | |
1844 | Efficiently Learning One Hidden Layer ReLU Networks From Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we consider the following problem: given \emph{black-box query access} to a neural network $F$, recover $F$ up to some error. |
Sitan Chen; Adam Klivans; Raghu Meka; | |
1845 | Learning Nonparametric Volterra Kernels with Gaussian Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a method for the nonparametric Bayesian learning of nonlinear operators, through the use of the Volterra series with kernels represented using Gaussian processes (GPs), which we term the nonparametric Volterra kernels model (NVKM). |
Magnus Ross; Michael T. Smith; Mauricio Alvarez; | |
1846 | DiBS: Differentiable Bayesian Structure Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a general, fully differentiable framework for Bayesian structure learning (DiBS) that operates in the continuous space of a latent probabilistic graph representation. |
Lars Lorch; Jonas Rothfuss; Bernhard Sch�lkopf; Andreas Krause; | |
1847 | Nonparametric Estimation of Continuous DPPs with Kernel Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that a restricted version of this maximum likelihood (MLE) problem falls within the scope of a recent representer theorem for nonnegative functions in an RKHS. |
Micha�l Fanuel; R�mi Bardenet; | |
1848 | FINE Samples for Learning with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel detector for filtering label noise. |
Taehyeon Kim; Jongwoo Ko; sangwook Cho; JinHwan Choi; Se-Young Yun; | |
1849 | Residual2Vec: Debiasing Graph Embedding with Random Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we investigate the impact of the random walks’ bias on graph embedding and propose residual2vec, a general graph embedding method that can debias various structural biases in graphs by using random graphs. |
Sadamori Kojaku; Jisung Yoon; Isabel Constantino; Yong-Yeol Ahn; | |
1850 | Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The growing literature on benign overfitting in overparameterized models has been mostly restricted to regression or binary classification settings; however, most success stories of modern machine learning have been recorded in multiclass settings. Motivated by this discrepancy, we study benign overfitting in multiclass linear classification. |
Ke Wang; Vidya Muthukumar; Christos Thrampoulidis; | |
1851 | Instance-Dependent Bounds for Zeroth-order Lipschitz Optimization with Error Certificates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of zeroth-order (black-box) optimization of a Lipschitz function $f$ defined on a compact subset $\mathcal{X}$ of $\mathbb{R}^d$, with the additional constraint that algorithms must certify the accuracy of their recommendations. |
Francois Bachoc; Tom Cesari; S�bastien Gerchinovitz; | |
1852 | Training Neural Networks with Fixed Sparse Masks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that it is possible to induce a fixed sparse mask on the model’s parameters that selects a subset to update over many iterations. |
Yi-Lin Sung; Varun Nair; Colin A. Raffel; | |
1853 | VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. |
Hassan Akbari; Liangzhe Yuan; Rui Qian; Wei-Hong Chuang; Shih-Fu Chang; Yin Cui; Boqing Gong; | |
1854 | Analyzing The Generalization Capability of SGLD Using Properties of Gaussian Channels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider a particular optimization method—the stochastic gradient Langevin dynamics (SGLD) algorithm—and investigate the generalization of models trained by SGLD. |
Hao Wang; Yizhe Huang; RUI GAO; Flavio Calmon; | |
1855 | Learning to Schedule Heuristics in Branch and Bound Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formalize the learning task and propose an efficient algorithm for computing such a schedule. |
Antonia Chmiela; Elias Khalil; Ambros Gleixner; Andrea Lodi; Sebastian Pokutta; | |
1856 | On Training Implicit Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel gradient estimate for implicit models, named phantom gradient, that 1) forgoes the costly computation of the exact gradient; and 2) provides an update direction empirically preferable to the implicit model training. |
Zhengyang Geng; Xin-Yu Zhang; Shaojie Bai; Yisen Wang; Zhouchen Lin; | |
1857 | MLP-Mixer: An All-MLP Architecture for Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. |
Ilya O. Tolstikhin; Neil Houlsby; Alexander Kolesnikov; Lucas Beyer; Xiaohua Zhai; Thomas Unterthiner; Jessica Yung; Andreas Steiner; Daniel Keysers; Jakob Uszkoreit; Mario Lucic; Alexey Dosovitskiy; | |
1858 | A Framework to Learn with Interpretation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. |
Jayneel Parekh; Pavlo Mozharovskyi; Florence D'Alch�; | |
1859 | One Loss for All: Deep Hashing with A Single Cosine Similarity Based Learning Objective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel deep hashing model with only $\textit{a single learning objective}$. |
Jiun Tian Hoe; Kam Woh Ng; Tianyu Zhang; Chee Seng Chan; Yi-Zhe Song; Tao Xiang; | |
1860 | Fast and Accurate Randomized Algorithms for Low-rank Tensor Decompositions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a fast and accurate sketched ALS algorithm for Tucker decomposition, which solves a sequence of sketched rank-constrained linear least squares subproblems. |
Linjian Ma; Edgar Solomonik; | |
1861 | Communication-efficient SGD: From Local SGD to One-Shot Averaging Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we suggest a Local SGD scheme that communicates less overall by communicating less frequently as the number of iterations grows. |
Artin Spiridonoff; Alex Olshevsky; Ioannis Paschalidis; | |
1862 | Memory Efficient Meta-Learning with Large Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We improve on both options by proposing LITE, a general and memory efficient episodic training scheme that enables meta-training on large tasks composed of large images on a single GPU. |
John Bronskill; Daniela Massiceti; Massimiliano Patacchiola; Katja Hofmann; Sebastian Nowozin; Richard Turner; | |
1863 | On The Power of Differentiable Learning Versus PAC and SQ Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the power of learning via mini-batch stochastic gradient descent (SGD) on the loss of a differentiable model or neural network, and ask what learning problems can be learnt using this paradigm. |
Emmanuel Abbe; Pritish Kamath; Eran Malach; Colin Sandon; Nathan Srebro; | |
1864 | Can We Globally Optimize Cross-validation Loss? Quasiconvexity in Ridge Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present paper, we show that, in the case of ridge regression, the CV loss may fail to be quasiconvex and thus may have multiple local optima. |
Will Stephenson; Zachary Frangella; Madeleine Udell; Tamara Broderick; | |
1865 | Adaptive Proximal Gradient Methods for Structured Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this goal, we present a general framework of stochastic proximal gradient descent methods that allows for arbitrary positive preconditioners and lower semi-continuous regularizers. |
Jihun Yun; Aurelie C. Lozano; Eunho Yang; | |
1866 | Discovering and Achieving Goals Via World Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our proposed agent, Latent Explorer Achiever (LEXA), addresses both challenges by learning a world model from image inputs and using it to train an explorer and an achiever policy via imagined rollouts. |
Russell Mendonca; Oleh Rybkin; Kostas Daniilidis; Danijar Hafner; Deepak Pathak; | code |
1867 | Understanding and Improving Early Stopping for Learning with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to separate a DNN into different parts and progressively train them to address this problem. |
Yingbin Bai; Erkun Yang; Bo Han; Yanhua Yang; Jiatong Li; Yinian Mao; Gang Niu; Tongliang Liu; | code |
1868 | Distributionally Robust Imitation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a novel approach to transform the objective function into a convex optimization problem over a polynomial number of variables for a class of loss functions that are additive over state and action spaces. |
Mohammad Ali Bashiri; Brian Ziebart; Xinhua Zhang; | |
1869 | On The Power of Edge Independent Graph Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study the limitations of $edge\ independent\ random\ graph\ models$, in which each edge is added to the graph independently with some probability. |
Sudhanshu Chanpuriya; Cameron Musco; Konstantinos Sotiropoulos; Charalampos Tsourakakis; | |
1870 | Stochastic Online Linear Regression: The Forward Algorithm to Replace Ridge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of online linear regression in the stochastic setting. |
reda ouhamma; Odalric-Ambrym Maillard; Vianney Perchet; | |
1871 | Dr Jekyll & Mr Hyde: The Strange Case of Off-policy Policy Updates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To implement the principles prescribed by our theory, we propose an agent, Dr Jekyll & Mr Hyde (J&H), with a double personality: Dr Jekyll purely exploits while Mr Hyde purely explores. |
Romain Laroche; Remi Tachet des Combes; | |
1872 | Understanding Adaptive, Multiscale Temporal Integration In Deep Speech Recognition Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we show how a recently developed method for studying temporal integration in biological neural systems – the temporal context invariance (TCI) paradigm – can be used to understand temporal integration in DNNs. |
Menoua Keshishian; Samuel Norman-Haignere; Nima Mesgarani; | |
1873 | VidLanKD: Improving Language Understanding Via Video-Distilled Knowledge Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we present VidLanKD, a video-language knowledge distillation method for improving language understanding. |
Zineng Tang; Jaemin Cho; Hao Tan; Mohit Bansal; | |
1874 | Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a transformer-based approach to behavioral stylometry in the context of chess, where one attempts to identify the player who played a set of games. |
Reid McIlroy-Young; Yu Wang; Siddhartha Sen; Jon Kleinberg; Ashton Anderson; | |
1875 | Coupled Gradient Estimators for Discrete Latent Variables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel derivation of their estimator based on importance sampling and statistical couplings, which we extend to the categorical setting. |
Zhe Dong; Andriy Mnih; George Tucker; | |
1876 | AutoGEL: An Automated Graph Neural Network with Explicit Link Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel AutoGNN work that explicitly models the link information, abbreviated to AutoGEL. |
Zhili Wang; Shimin DI; Lei Chen; | |
1877 | RL for Latent MDPs: Regret Guarantees and A Lower Bound Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). |
Jeongyeol Kwon; Yonathan Efroni; Constantine Caramanis; Shie Mannor; | |
1878 | Adaptive Sampling for Minimax Fair Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we consider the problem of adaptively constructing training sets which allow us to learn classifiers that are fair in a {\em minimax} sense. |
Shubhanshu Shekhar; Greg Fields; Mohammad Ghavamzadeh; Tara Javidi; | |
1879 | Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we identify dropout induced sparsity for LSTMs as a suitable mode of computation reduction. |
Anup Sarma; Sonali Singh; Huaipan Jiang; Rui Zhang; Mahmut Kandemir; Chita Das; | |
1880 | Variational Continual Bayesian Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, we propose a Variational Continual Bayesian Meta-Learning (VC-BML) algorithm. |
Qiang Zhang; Jinyuan Fang; Zaiqiao Meng; Shangsong Liang; Emine Yilmaz; | |
1881 | Recognizing Vector Graphics Without Rasterization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider a different data format for images: vector graphics. |
XINYANG JIANG; LU LIU; Caihua Shan; Yifei Shen; Xuanyi Dong; Dongsheng Li; | |
1882 | On Episodes, Prototypical Networks, and Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the usefulness of episodic learning in methods which use nonparametric approaches, such as nearest neighbours, at the level of the episode. |
Steinar Laenen; Luca Bertinetto; | |
1883 | Pointwise Bounds for Distribution Estimation Under Communication Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of estimating a $d$-dimensional discrete distribution from its samples observed under a $b$-bit communication constraint. |
Wei-Ning Chen; Peter Kairouz; Ayfer Ozgur; | |
1884 | CHIP: CHannel Independence-based Pruning for Compact Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, starting from an inter-channel perspective, we propose to perform efficient filter pruning using Channel Independence, a metric that measures the correlations among different feature maps. |
Yang Sui; Miao Yin; Yi Xie; Huy Phan; Saman Aliari Zonouz; Bo Yuan; | code |
1885 | Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To amalgamate these methods and thereby maximize their distinct strengths, here we show that the Vision Transformer, a recently developed deep learning architecture with straightforward decomposable configuration, is ideally suitable for split learning without sacrificing performance. |
Sangjoon Park; Gwanghyun Kim; Jeongsol Kim; Boah Kim; Jong Chul Ye; | |
1886 | Active Offline Policy Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we introduce active offline policy selection — a novel sequential decision approach that combines logged data with online interaction to identify the best policy. |
Ksenia Konyushova; Yutian Chen; Thomas Paine; Caglar Gulcehre; Cosmin Paduraru; Daniel J. Mankowitz; Misha Denil; Nando de Freitas; | |
1887 | Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel unsupervised learning framework for small networks that combines deep self-supervised representation learning and knowledge distillation within one-phase training. |
Hee Min Choi; Hyoa Kang; Dokwan Oh; | |
1888 | Understanding Bandits with Graph Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the notions of the fractional weak domination number $\delta^*$ and the $k$-packing independence number capturing upper bound and lower bound for the regret respectively. |
Houshuang Chen; zengfeng Huang; Shuai Li; Chihao Zhang; | |
1889 | Information-theoretic Generalization Bounds for Black-box Learning Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm. |
Hrayr Harutyunyan; Maxim Raginsky; Greg Ver Steeg; Aram Galstyan; | |
1890 | Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to utilize information more efficiently, this work presents a general yet simple interactive strategy, namely $\textit{your trash is my treasure}$ (YTMT), for constructing dual-stream decomposition networks. |
Qiming Hu; Xiaojie Guo; | code |
1891 | Rot-Pro: Modeling Transitivity By Projection in Knowledge Graph Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we first theoretically show that the transitive relations can be modeled with projections. We then propose the Rot-Pro model which combines the projection and relational rotation together. |
Tengwei Song; Jie Luo; Lei Huang; | |
1892 | Planning from Pixels in Environments with Combinatorially Hard Search Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our contribution is two-fold: (i) we present a method that learns to represent its environment as a latent graph and leverages state reidentification to reduce the complexity of finding a good policy from exponential to linear (ii) we introduce a set of lightweight environments with an underlying discrete combinatorial structure in which planning is challenging even for humans. |
Marco Bagatella; Miroslav Ol��k; Michal Rol�nek; Georg Martius; | |
1893 | PLUGIn: A Simple Algorithm for Inverting Generative Models with Recovery Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a simple novel algorithm, Partially Linearized Update for Generative Inversion (PLUGIn), to estimate $x$ (and thus $\mathcal{G}(x)$). |
Babhru Joshi; Xiaowei Li; Yaniv Plan; Ozgur Yilmaz; | |
1894 | Modular Gaussian Processes for Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a framework for transfer learning based on modular variational Gaussian processes (GP). |
Pablo Moreno-Mu�oz; Antonio Artes; Mauricio Alvarez; | |
1895 | Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim at synthesizing a free-viewpoint video of an arbitrary human performance using sparse multi-view cameras. |
Youngjoong Kwon; Dahun Kim; Duygu Ceylan; Henry Fuchs; | |
1896 | Locally Differentially Private Estimation of Functionals of Discrete Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of estimating non-linear functionals of discrete distributions in the context of local differential privacy. |
Cristina Butucea; Yann ISSARTEL; | |
1897 | Asymptotics of Representation Learning in Finite Bayesian Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we argue that the leading finite-width corrections to the average feature kernels for any Bayesian network with linear readout and Gaussian likelihood have a largely universal form. |
Jacob Zavatone-Veth; Abdulkadir Canatar; Ben Ruben; Cengiz Pehlevan; | |
1898 | Adaptive Ensemble Q-learning: Minimizing Estimation Bias Via Error Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we devise Adaptive Ensemble Q-learning (AdaEQ), a generalized ensemble method with two key steps: (a) approximation error characterization which serves as the feedback for flexibly controlling the ensemble size, and (b) ensemble size adaptation tailored towards minimizing the estimation bias. |
Hang Wang; Sen Lin; Junshan Zhang; | |
1899 | Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide reasoning why when the supports of the source and target data from overlap, any map of $X$ that is fixed across domains may not be suitable for domain adaptation via invariant features. |
Petar Stojanov; Zijian Li; Mingming Gong; Ruichu Cai; Jaime Carbonell; Kun Zhang; | code |
1900 | CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Conditional Score-based Diffusion model (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data. |
Yusuke Tashiro; Jiaming Song; Yang Song; Stefano Ermon; | code |
1901 | Causal Bandits with Unknown Graph Structure Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop novel causal bandit algorithms without knowing the causal graph. |
Yangyi Lu; Amirhossein Meisami; Ambuj Tewari; | |
1902 | Piper: Multidimensional Planner for DNN Parallelization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce Piper, an efficient optimization algorithm for this problem that is based on a two-level dynamic programming approach. |
Jakub M. Tarnawski; Deepak Narayanan; Amar Phanishayee; | |
1903 | Causal Effect Inference for Structured Treatments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given a weak condition on the effect, we propose the generalized Robinson decomposition, which (i) isolates the causal estimand (reducing regularization bias), (ii) allows one to plug in arbitrary models for learning, and (iii) possesses a quasi-oracle convergence guarantee under mild assumptions. |
Jean Kaddour; Yuchen Zhu; Qi Liu; Matt J. Kusner; Ricardo Silva; | |
1904 | Efficient Hierarchical Bayesian Inference for Spatio-temporal Regression Models in Neuroimaging Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Overcoming these limitations, we devise a novel flexible hierarchical Bayesian framework within which the spatio-temporal dynamics of model parameters and noise are modeled to have Kronecker product covariance structure. |
Ali Hashemi; Yijing Gao; Chang Cai; Sanjay Ghosh; Klaus-Robert M�ller; Srikantan Nagarajan; Stefan Haufe; | |
1905 | Topological Attention for Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose topological attention, which allows attending to local topological features within a time horizon of historical data. |
Sebastian Zeng; Florian Graf; Christoph Hofer; Roland Kwitt; | |
1906 | Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a related, but alternative, explanation for this performance gap in the image classification setting, based on finding a sparse signal in the presence of noise. |
Stefani Karp; Ezra Winston; Yuanzhi Li; Aarti Singh; | |
1907 | IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, this paper presents an Interpretability-Aware REDundancy REDuction framework (IA-RED$^2$). |
Bowen Pan; Rameswar Panda; Yifan Jiang; Zhangyang Wang; Rogerio Feris; Aude Oliva; | code |
1908 | Symbolic Regression Via Deep Reinforcement Learning Enhanced Genetic Programming Seeding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a hybrid neural-guided/genetic programming approach to symbolic regression and other combinatorial optimization problems. |
Terrell Mundhenk; Mikel Landajuela; Ruben Glatt; Claudio Santiago; Daniel faissol; Brenden Petersen; | |
1909 | Choose A Transformer: Fourier or Galerkin Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we apply the self-attention from the state-of-the-art Transformer in Attention Is All You Need for the first time to a data-driven operator learning problem related to partial differential equations. |
Shuhao Cao; | |
1910 | A Causal Lens for Controllable Text Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes to formulate controllable text generation from a principled causal perspective which models the two tasks with a unified framework. |
Zhiting Hu; Li Erran Li; | |
1911 | Differentially Private Multi-Armed Bandits in The Shuffle Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give an $(\varepsilon,\delta)$-differentially private algorithm for the Multi-Armed Bandit (MAB) problem in the shuffle model with a distribution-dependent regret of $O\left(\left(\sum_{a:\Delta_a>0}\frac{\log T}{\Delta_a}\right)+\frac{k\sqrt{\log\frac{1}{\delta}}\log T}{\varepsilon}\right)$, and a distribution-independent regret of $O\left(\sqrt{kT\log T}+\frac{k\sqrt{\log\frac{1}{\delta}}\log T}{\varepsilon}\right)$, where $T$ is the number of rounds, $\Delta_a$ is the suboptimality gap of the action $a$, and $k$ is the total number of actions. |
Jay Tenenbaum; Haim Kaplan; Yishay Mansour; Uri Stemmer; | |
1912 | Dual Adaptivity: A Universal Algorithm for Minimizing The Adaptive Regret of Convex Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Along this line of research, this paper presents the first universal algorithm for minimizing the adaptive regret of convex functions. |
Lijun Zhang; Guanghui Wang; Wei-Wei Tu; Wei Jiang; Zhi-Hua Zhou; | |
1913 | Learning Hard Optimization Problems: A Data Generation Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper demonstrates this critical challenge, connects the volatility of the training data to the ability of a model to approximate it, and proposes a method for producing (exact or approximate) solutions to optimization problems that are more amenable to supervised learning tasks. |
James Kotary; Ferdinando Fioretto; Pascal Van Hentenryck; | |
1914 | Canonical Capsules: Self-Supervised Capsules in Canonical Pose Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an unsupervised capsule architecture for 3D point clouds. |
Weiwei Sun; Andrea Tagliasacchi; Boyang Deng; Sara Sabour; Soroosh Yazdani; Geoffrey E. Hinton; Kwang Moo Yi; | |
1915 | Characterizing Generalization Under Out-Of-Distribution Shifts in Deep Metric Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we systematically construct train-test splits of increasing difficulty and present the ooDML benchmark to characterize generalization under out-of-distribution shifts in DML. |
Timo Milbich; Karsten Roth; Samarth Sinha; Ludwig Schmidt; Marzyeh Ghassemi; Bjorn Ommer; | |
1916 | Dynamics-regulated Kinematic Policy for Egocentric Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method for object-aware 3D egocentric pose estimation that tightly integrates kinematics modeling, dynamics modeling, and scene object information. |
Zhengyi Luo; Ryo Hachiuma; Ye Yuan; Kris Kitani; | |
1917 | Never Go Full Batch (in Stochastic Convex Optimization) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the generalization performance of $\text{\emph{full-batch}}$ optimization algorithms for stochastic convex optimization: these are first-order methods that only access the exact gradient of the empirical risk (rather than gradients with respect to individual data points), that include a wide range of algorithms such as gradient descent, mirror descent, and their regularized and/or accelerated variants. |
Idan Amir; Yair Carmon; Tomer Koren; Roi Livni; | |
1918 | Collaborative Learning in The Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two asynchronous solutions to averaging agreement, each we prove optimal according to some dimension. |
El Mahdi El-Mhamdi; Sadegh Farhadkhani; Rachid Guerraoui; Arsany Guirguis; L�-Nguy�n Hoang; S�bastien Rouault; | |
1919 | Not All Low-Pass Filters Are Robust in Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the theory, we present GCN-LFR, a general robust co-training paradigm for GCN-based models, that encourages transferring the robustness of low-frequency components with an auxiliary neural network. |
Heng Chang; Yu Rong; Tingyang Xu; Yatao Bian; Shiji Zhou; Xin Wang; Junzhou Huang; Wenwu Zhu; | |
1920 | Counterfactual Maximum Likelihood Estimation for Training Deep Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we propose a causality-based training framework to reduce the spurious correlations caused by observed confounders. |
Xinyi Wang; Wenhu Chen; Michael Saxon; William Yang Wang; | |
1921 | Robust Optimization for Multilingual Translation with Imbalanced Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that a common situation in multilingual training, data imbalance among languages, poses optimization tension between high resource and low resource languages where the found multilingual solution is often sub-optimal for low resources. |
Xian Li; Hongyu Gong; | |
1922 | A/B/n Testing with Control in The Presence of Subpopulations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a strategy for sequentially choosing one arm per time step so as to discover as fast as possible which arms, if any, have higher weighted expectation than the control. |
Yoan Russac; Christina Katsimerou; Dennis Bohle; Olivier Capp�; Aur�lien Garivier; Wouter M. Koolen; | |
1923 | Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose accounting for high-cardinality categorical features as random effects variables in a regression setting, and consequently adopt the corresponding negative log likelihood loss from the linear mixed models (LMM) statistical literature and integrate it in a deep learning framework. |
Giora Simchoni; Saharon Rosset; | code |
1924 | Learning Debiased Representation Via Disentangled Feature Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we propose a novel feature-level data augmentation technique in order to synthesize diverse bias-conflicting samples. |
Jungsoo Lee; Eungyeup Kim; Juyoung Lee; Jihyeon Lee; Jaegul Choo; | |
1925 | Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Scallop, a system that builds upon probabilistic deductive databases, to bridge this gap. |
Jiani Huang; Ziyang Li; Binghong Chen; Karan Samel; Mayur Naik; Le Song; Xujie Si; | |
1926 | Learning to Synthesize Programs As Interpretable and Generalizable Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a framework that instead learns to synthesize a program, which details the procedure to solve a task in a flexible and expressive manner, solely from reward signals. |
Dweep Kumarbhai Trivedi; Jesse Zhang; Shao-Hua Sun; Joseph J. Lim; | code |
1927 | The Functional Specialization of Visual Cortex Emerges from Training Parallel Pathways with Self-supervised Predictive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we ask whether a single model with a single loss function can capture the properties of both the ventral and the dorsal pathways. |
Shahab Bakhtiari; Patrick Mineault; Timothy Lillicrap; Christopher Pack; Blake Richards; | |
1928 | Adversarial Training Helps Transfer Learning Via Better Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a theoretical model to rigorously analyze how adversarial training helps transfer learning. |
Zhun Deng; Linjun Zhang; Kailas Vodrahalli; Kenji Kawaguchi; James Y. Zou; | |
1929 | Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we seek a lightweight, training-free means of improving existing System 1-like sequence models by adding System 2-inspired logical reasoning. |
Maxwell Nye; Michael Tessler; Josh Tenenbaum; Brenden M. Lake; | |
1930 | Learning The Optimal Tikhonov Regularizer for Inverse Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the linear inverse problem $y=Ax+\varepsilon$, where $A\colon X\to Y$ is a known linear operator between the separable Hilbert spaces $X$ and $Y$, $x$ is a random variable in $X$ and $\epsilon$ is a zero-mean random process in $Y$. |
Giovanni Alberti; Ernesto De Vito; Matti Lassas; Luca Ratti; Matteo Santacesaria; | |
1931 | NovelD: A Simple Yet Effective Exploration Criterion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, inspired by this, we propose a simple but effective criterion called NovelD by weighting every novel area approximately equally. |
Tianjun Zhang; Huazhe Xu; Xiaolong Wang; Yi Wu; Kurt Keutzer; Joseph E. Gonzalez; Yuandong Tian; | |
1932 | On Margin-Based Cluster Recovery with Oracle Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study an active cluster recovery problem where, given a set of $n$ points and an oracle answering queries like “are these two points in the same cluster?” |
Marco Bressan; Nicol� Cesa-Bianchi; Silvio Lattanzi; Andrea Paudice; | |
1933 | Multi-Scale Representation Learning on Proteins Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a multi-scale graph construction of a protein –HoloProt– connecting surface to structure and sequence. |
Vignesh Ram Somnath; Charlotte Bunne; Andreas Krause; | |
1934 | Sparse Quadratic Optimisation Over The Stiefel Manifold with Application to Permutation Synchronisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We fill this gap and propose a simple yet effective sparsity-promoting modification of the Orthogonal Iteration algorithm for finding the dominant eigenspace of a matrix. |
Florian Bernard; Daniel Cremers; Johan Thunberg; | |
1935 | Second-Order Neural ODE Optimizer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). |
Guan-Horng Liu; Tianrong Chen; Evangelos Theodorou; | code |
1936 | Graph Neural Networks with Local Graph Parameters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose local graph parameter enabled GNNs as a framework for studying the latter kind of approaches and precisely characterize their distinguishing power, in terms of a variant of the WL test, and in terms of the graph structural properties that they can take into account. |
Pablo Barcel�; Floris Geerts; Juan Reutter; Maksimilian Ryschkov; | |
1937 | Closing The Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging the hidden smoothness of the problem, this paper presents a tighter analysis of ALSET for stochastic nested problems. |
Tianyi Chen; Yuejiao Sun; Wotao Yin; | |
1938 | Dense Unsupervised Learning for Video Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel approach to unsupervised learning for video object segmentation (VOS). |
Nikita Araslanov; Simone Schaub-Meyer; Stefan Roth; | |
1939 | Charting and Navigating The Space of Solutions for Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a tool to derive the reduced dynamics of networks by generating a compact directed graph describing the essence of the dynamics with regards to behavioral inputs and outputs. |
Elia Turner; Kabir Dabholkar; Omri Barak; | |
1940 | Fast Training Method for Stochastic Compositional Optimization Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose novel decentralized stochastic compositional gradient descent methods to efficiently train the large-scale stochastic compositional optimization problem. |
Hongchang Gao; Heng Huang; | |
1941 | Dual-stream Network for Visual Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a generic Dual-stream Network (DS-Net) to fully explore the representation capacity of local and global pattern features for image classification. |
Mingyuan Mao; peng gao; Renrui Zhang; Honghui Zheng; Teli Ma; Yan Peng; Errui Ding; Baochang Zhang; Shumin Han; | |
1942 | Estimating High Order Gradients of The Data Distribution By Denoising Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we propose a method to directly estimate high order derivatives (scores) of a data density from samples. |
Chenlin Meng; Yang Song; Wenzhe Li; Stefano Ermon; | |
1943 | Machine Versus Human Attention in Deep Reinforcement Learning Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we shed light on the inner workings of such trained models by analyzing the pixels that they attend to during task execution, and comparing them with the pixels attended to by humans executing the same tasks. |
Sihang Guo; Ruohan Zhang; Bo Liu; Yifeng Zhu; Dana Ballard; Mary Hayhoe; Peter Stone; | |
1944 | Reusing Combinatorial Structure: Faster Iterative Projections Over Submodular Base Polytopes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this trade-off in runtime v/s convergence rates, we consider iterative projections of close-by points over widely-prevalent submodular base polytopes $B(f)$. |
Jai Moondra; Hassan Mortagy; Swati Gupta; | |
1945 | Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we pose the training of a DNN for binary classification as a constrained optimization problem and introduce a novel constraint that can be used with existing loss functions to enforce maximal area under the ROC curve (AUC) through prioritizing FPR reduction at high TPR. |
Sara Sangalli; Ertunc Erdil; Andeas H�tker; Olivio Donati; Ender Konukoglu; | |
1946 | Collapsed Variational Bounds for Bayesian Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we treat prior parameters in a distributional way by extending the model and collapsing the variational bound with respect to their posteriors. |
Marcin Tomczak; Siddharth Swaroop; Andrew Foong; Richard Turner; | |
1947 | Consistent Estimation for PCA and Sparse Regression with Oblivious Outliers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop machinery to design efficiently computable and \emph{consistent} estimators, achieving estimation error approaching zero as the number of observations grows, when facing an oblivious adversary that may corrupt responses in all but an $\alpha$ fraction of the samples. |
Tommaso d'Orsi; Chih-Hung Liu; Rajai Nasser; Gleb Novikov; David Steurer; Stefan Tiegel; | |
1948 | Offline Constrained Multi-Objective Reinforcement Learning Via Pessimistic Dual Value Iteration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To the best of our knowledge, we propose the first provably efficient constrained multi-objective RL algorithm with offline data without any assumption on the coverage of the dataset. |
Runzhe Wu; Yufeng Zhang; Zhuoran Yang; Zhaoran Wang; | |
1949 | Absolute Neighbour Difference Based Correlation Test for Detecting Heteroscedastic Relationships Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a new statistical measure, named the absolute neighbour difference based neighbour correlation coefficient, to detect the associations between variables through examining the heteroscedasticity of the unpredictable variation of dependent variables. |
Lifeng Zhang; | |
1950 | Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to reduce the optimization cost while maximizing the benefit-cost ratio, in this paper we propose Batch Multi-fidelity Bayesian Optimization with Deep Auto-Regressive Networks (BMBO-DARN). |
Shibo Li; Robert Kirby; Shandian Zhe; | |
1951 | Mastering Atari Games with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a sample efficient model-based visual RL algorithm built on MuZero, which we name EfficientZero. |
Weirui Ye; Shaohuai Liu; Thanard Kurutach; Pieter Abbeel; Yang Gao; | code |
1952 | Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of the identification of m arms with largest means under a fixed error rate $\delta$ (fixed-confidence Top-m identification), for misspecified linear bandit models. |
Cl�mence R�da; Andrea Tirinzoni; R�my Degenne; | |
1953 | Why Generalization in RL Is Difficult: Epistemic POMDPs and Implicit Partial Observability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that the sequential structure of the RL problem necessitates new approaches to generalization beyond the well-studied techniques used in supervised learning. |
Dibya Ghosh; Jad Rahme; Aviral Kumar; Amy Zhang; Ryan P. Adams; Sergey Levine; | |
1954 | Set Prediction in The Latent Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method for learning the distance function by performing the matching in the latent space learned from encoding networks. |
Konpat Preechakul; Chawan Piansaddhayanon; Burin Naowarat; Tirasan Khandhawit; Sira Sriswasdi; Ekapol Chuangsuwanich; | |
1955 | Best of Both Worlds: Practical and Theoretically Optimal Submodular Maximization in Parallel Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For the problem of maximizing a monotone, submodular function with respect to a cardinality constraint $k$ on a ground set of size $n$, we provide an algorithm that achieves the state-of-the-art in both its empirical performance and its theoretical properties, in terms of adaptive complexity, query complexity, and approximation ratio; that is, it obtains, with high probability, query complexity of $O(n)$ in expectation, adaptivity of $O(\log(n))$, and approximation ratio of nearly $1-1/e$. |
Yixin Chen; Tonmoy Dey; Alan Kuhnle; | |
1956 | Fine-grained Generalization Analysis of Inductive Matrix Completion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we bridge the gap between the state-of-the-art theoretical results for matrix completion with the nuclear norm and their equivalent in \textit{inductive matrix completion}: (1) In the distribution-free setting, we prove bounds improving the previously best scaling of $O(rd^2)$ to $\widetilde{O}(d^{3/2}\sqrt{r})$, where $d$ is the dimension of the side information and $r$ is the rank. |
Antoine Ledent; Rodrigo Alves; Yunwen Lei; Marius Kloft; | |
1957 | Learning Frequency Domain Approximation for Binary Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose to estimate the gradient of sign function in the Fourier frequency domain using the combination of sine functions for training BNNs, namely frequency domain approximation (FDA). |
Yixing Xu; Kai Han; Chang Xu; Yehui Tang; Chunjing XU; Yunhe Wang; | code |
1958 | Reformulating Zero-shot Action Recognition for Multi-label Actions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we propose a ZSAR framework which does not rely on nearest neighbor classification, but rather consists of a pairwise scoring function. |
Alec Kerrigan; Kevin Duarte; Yogesh Rawat; Mubarak Shah; | |
1959 | Optimal Best-Arm Identification Methods for Tail-Risk Measures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is an optimal $\delta$-correct algorithm that acts on general arms, including heavy-tailed distributions, and matches the lower bound on the expected number of samples needed, asymptotically (as $ \delta$ approaches $0$). |
Shubhada Agrawal; Wouter M. Koolen; Sandeep Juneja; | |
1960 | SyMetric: Measuring The Quality of Learnt Hamiltonian Dynamics Inferred from Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we empirically highlight the problems with the existing measures and develop a set of new measures, including a binary indicator of whether the underlying Hamiltonian dynamics have been faithfully captured, which we call Symplecticity Metric or SyMetric. |
Irina Higgins; Peter Wirnsberger; Andrew Jaegle; Aleksandar Botev; | |
1961 | Learning with Holographic Reduced Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to revisit this approach to understand if it is viable for enabling a hybrid neural-symbolic approach to learning as a differential component of a deep learning architecture. |
Ashwinkumar Ganesan; Hang Gao; Sunil Gandhi; Edward Raff; Tim Oates; James Holt; Mark McLean; | |
1962 | Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper explores the possibility of safe RL algorithms with zero training-time safety violations in the challenging setting where we are only given a safe but trivial-reward initial policy without any prior knowledge of the dynamics and additional offline data. |
Yuping Luo; Tengyu Ma; | |
1963 | On The Second-order Convergence Properties of Random Search Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to address this issue, we propose a novel variant of random search that exploits negative curvature by only relying on function evaluations. |
Aurelien Lucchi; Antonio Orvieto; Adamos Solomou; | |
1964 | Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we develop a theoretical framework to study the "geometry of learning dynamics" in neural networks, and reveal a key mechanism of explicit symmetry breaking behind the efficiency and stability of modern neural networks. |
Hidenori Tanaka; Daniel Kunin; | |
1965 | A Theory of The Distortion-Perception Tradeoff in Wasserstein Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive a closed form expression for this distortion-perception (DP) function for the mean squared-error (MSE) distortion and Wasserstein-2 perception index. |
Dror Freirich; Tomer Michaeli; Ron Meir; | |
1966 | Neural Production Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As an alternative, we take inspiration from cognitive science and resurrect a classic approach, production systems, which consist of a set of rule templates that are applied by binding placeholder variables in the rules to specific entities. |
Anirudh Goyal ALIAS PARTH GOYAL; Aniket Didolkar; Nan Rosemary Ke; Charles Blundell; Philippe Beaudoin; Nicolas Heess; Michael C. Mozer; Yoshua Bengio; | |
1967 | Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that when training supervised models, {\em smoothness matrices}—information-rich generalizations of the ubiquitous smoothness constants—can and should be exploited for further dramatic gains, both in theory and practice. |
Mher Safaryan; Filip Hanzely; Peter Richtarik; | |
1968 | Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized By Astrocyte-modulated Plasticity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this disruptive understanding of how brain networks self-tune, we propose the neuron-astrocyte liquid state machine (NALSM) that addresses under-performance through self-organized near-critical dynamics. |
Vladimir Ivanov; Konstantinos Michmizos; | |
1969 | Fair Sortition Made Transparent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this hurdle, in this work we focus on panel selection by uniform lottery, which is easy to realize in an observable way. |
Bailey Flanigan; Gregory Kehne; Ariel D. Procaccia; | |
1970 | A Max-Min Entropy Framework for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a max-min entropy framework for reinforcement learning (RL) to overcome the limitation of the soft actor-critic (SAC) algorithm implementing the maximum entropy RL in model-free sample-based learning. |
Seungyul Han; Youngchul Sung; | |
1971 | Reward Is Enough for Convex MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study convex MDPs in which goals are expressed as convex functions of the stationary distribution and show that they cannot be formulated using stationary reward functions. |
Tom Zahavy; Brendan O'Donoghue; Guillaume Desjardins; Satinder Singh; | |
1972 | Fast Doubly-Adaptive MCMC to Estimate The Gibbs Partition Function with Weak Mixing Time Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel method for reducing the computational complexity of rigorously estimating the partition functions of Gibbs (or Boltzmann) distributions, which arise ubiquitously in probabilistic graphical models. |
Shahrzad Haddadan; Yue Zhuang; Cyrus Cousins; Eli Upfal; | |
1973 | Does Enforcing Fairness Mitigate Biases Caused By Subpopulation Shift? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study whether enforcing algorithmic fairness during training improves the performance of the trained model in the \emph{target domain}. |
Subha Maity; Debarghya Mukherjee; Mikhail Yurochkin; Yuekai Sun; | |
1974 | Implicit Deep Adaptive Design: Policy-Based Experimental Design Without Likelihoods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce implicit Deep Adaptive Design (iDAD), a new method for performing adaptive experiments in real-time with implicit models. |
Desislava Ivanova; Adam Foster; Steven Kleinegesse; Michael U. Gutmann; Thomas Rainforth; | |
1975 | Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper initiates the theoretical study of sample-efficient learning of the Stackelberg equilibrium, in the bandit feedback setting where we only observe noisy samples of the reward. |
Yu Bai; Chi Jin; Huan Wang; Caiming Xiong; | |
1976 | Non-approximate Inference for Collective Graphical Models on Path Graphs Via Discrete Difference of Convex Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve these problems, this paper proposes a new method for MAP inference for CGMs on path graphs. |
Yasunori Akagi; Naoki Marumo; Hideaki Kim; Takeshi Kurashima; Hiroyuki Toda; | |
1977 | Implicit Task-Driven Probability Discrepancy Measure for Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore it is important to warp the probability discrepancy measure towards the end tasks, and we hence propose a new bi-level optimization based approach so that the two distributions are compared not uniformly against the entire hypothesis space, but only with respect to the optimal predictor for the downstream end task. |
Mao Li; Kaiqi Jiang; Xinhua Zhang; | |
1978 | SBO-RNN: Reformulating Recurrent Neural Networks Via Stochastic Bilevel Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we consider the training stability of recurrent neural networks (RNNs) and propose a family of RNNs, namely SBO-RNN, that can be formulated using stochastic bilevel optimization (SBO). |
Ziming Zhang; Yun Yue; Guojun Wu; Yanhua Li; Haichong Zhang; | code |
1979 | Navigating to The Best Policy in Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a problem-dependent lower bound on the average number of steps required before a correct answer can be given with probability at least $1-\delta$. |
Aymen Al Marjani; Aur�lien Garivier; Alexandre Proutiere; | |
1980 | A Faster Decentralized Algorithm for Nonconvex Minimax Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the nonconvex-strongly-concave minimax optimization problem on decentralized setting. |
Wenhan Xian; Feihu Huang; Yanfu Zhang; Heng Huang; | |
1981 | Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. |
Qi CHEN; Changjian Shui; Mario Marchand; | |
1982 | ReLU Regression with Massart Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on ReLU regression in the Massart noise model, a natural and well-studied semi-random noise model. |
Ilias Diakonikolas; Jong Ho Park; Christos Tzamos; | |
1983 | Identification of The Generalized Condorcet Winner in Multi-dueling Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we derive lower bounds on the sample complexity for the task of identifying the GCW under various assumptions. |
Bj�rn Haddenhorst; Viktor Bengs; Eyke H�llermeier; | |
1984 | Robust Inverse Reinforcement Learning Under Transition Dynamics Mismatch Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Leveraging insights from the Robust RL literature, we propose a robust MCE IRL algorithm, which is a principled approach to help with this mismatch. |
Luca Viano; Yu-Ting Huang; Parameswaran Kamalaruban; Adrian Weller; Volkan Cevher; | |
1985 | Re-ranking for Image Retrieval and Transductive Few-shot Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to meta-learn the re-ranking updates such that the similarity graph converges towards the target similarity graph induced by the image labels. |
Xi SHEN; Yang Xiao; Shell Hu; Othman Sbai; Mathieu Aubry; | code |
1986 | Post-processing for Individual Fairness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose general post-processing algorithms for individual fairness (IF). |
Felix Petersen; Debarghya Mukherjee; Yuekai Sun; Mikhail Yurochkin; | |
1987 | OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel Open-set Semi-Supervised Learning (OSSL) approach called OpenMatch.Learning representations of inliers while rejecting outliers is essential for the success of OSSL. |
Kuniaki Saito; Donghyun Kim; Kate Saenko; | code |
1988 | End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. |
Devendra Singh; Siva Reddy; Will Hamilton; Chris Dyer; Dani Yogatama; | |
1989 | Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a fast, exact algorithm for computing the Bellman operator for S-rectangular robust Markov decision processes with $L_\infty$-constrained rectangular ambiguity sets. |
Bahram Behzadian; Marek Petrik; Chin Pang Ho; | |
1990 | Instance-optimal Mean Estimation Under Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper takes a principled approach, yielding a mechanism that is instance-optimal in a strong sense. |
Ziyue Huang; Yuting Liang; Ke Yi; | |
1991 | Look at The Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe a novel attribution method which is grounded in Sensitivity Analysis and uses Sobol indices. |
Thomas FEL; Remi Cadene; Mathieu Chalvidal; Matthieu Cord; David Vigouroux; Thomas Serre; | |
1992 | PatchGame: Learning to Signal Mid-level Patches in Referential Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal. |
Kamal Gupta; Gowthami Somepalli; Anubhav Gupta; Vinoj Yasanga Jayasundara Magalle Hewa; Matthias Zwicker; Abhinav Shrivastava; | |
1993 | Implicit Generative Copulas Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a flexible, yet conceptually simple alternative based on implicit generative neural networks. |
Tim Janke; Mohamed Ghanmi; Florian Steinke; | |
1994 | Tensor Normal Training for Deep Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the so-called tensor normal (TN) distribution, we propose and analyze a brand new approximate natural gradient method, Tensor Normal Training (TNT), which like Shampoo, only requires knowledge of the shape of the training parameters. |
Yi Ren; Donald Goldfarb; | |
1995 | Unintended Selection: Persistent Qualification Rate Disparities and Interventions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that differences in qualification rates between subpopulations can persist indefinitely for a set of non-trivial equilibrium states due to uniformed classifier deployments, even when groups are identical in all aspects except initial qualification densities. |
Reilly Raab; Yang Liu; | |
1996 | Revisiting 3D Object Detection From An Egocentric Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given the insight that SDE would benefit from more accurate geometry descriptions, we propose to represent objects as amodal contours, specifically amodal star-shaped polygons, and devise a simple model, StarPoly, to predict such contours. |
Boyang Deng; Charles R. Qi; Mahyar Najibi; Thomas Funkhouser; Yin Zhou; Dragomir Anguelov; | |
1997 | Optimizing Information-theoretical Generalization Bound Via Anisotropic Noise of SGLD Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we optimize the information-theoretical generalization bound by manipulating the noise structure in SGLD. |
Bohan Wang; Huishuai Zhang; Jieyu Zhang; Qi Meng; Wei Chen; Tie-Yan Liu; | |
1998 | Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources). |
Sen Cui; Weishen Pan; Jian Liang; Changshui Zhang; Fei Wang; | |
1999 | A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a mathematical framework for quantifying the transferability in multi-source transfer learning problems, with both the task similarities and the sample complexity of learning models taken into account. |
Xinyi Tong; Xiangxiang Xu; Shao-Lun Huang; Lizhong Zheng; | |
2000 | Mori� Attack (MA): A New Potential Risk of Screen Photos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we find a special phenomenon in digital image processing, the moiré effect, that could cause unnoticed security threats to DNNs. |
Dantong Niu; Ruohao Guo; Yisen Wang; | code |
2001 | Fast Bayesian Inference for Gaussian Cox Processes Via Path Integral Formulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Bayesian inference scheme for Gaussian Cox processes by exploiting a conceptually-intuitive {¥it path integral} formulation. |
Hideaki Kim; | |
2002 | Lattice Partition Recovery with Dyadic CART Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we consider instead the problem of partition recovery, i.e.~of estimating the partition of the lattice induced by the constancy regions of the unknown signal, using the computationally-efficient dyadic classification and regression tree (DCART) methodology proposed by \citep{donoho1997cart}. |
OSCAR HERNAN MADRID PADILLA; Yi Yu; Alessandro Rinaldo; | |
2003 | Robust Deep Reinforcement Learning Through Adversarial Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against $l_p$-norm bounded adversarial attacks. |
Tuomas Oikarinen; Wang Zhang; Alexandre Megretski; Luca Daniel; Tsui-Wei Weng; | code |
2004 | Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOlin), which provably converges to a local maximum with sample complexity that only depends on the sequential Rademacher complexity of the model class. |
Kefan Dong; Jiaqi Yang; Tengyu Ma; | |
2005 | You Only Look at One Sequence: Rethinking Transformer in Vision Through Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To answer this question, we present You Only Look at One Sequence (YOLOS), a series of object detection models based on the vanilla Vision Transformer with the fewest possible modifications, region priors, as well as inductive biases of the target task. |
Yuxin Fang; Bencheng Liao; Xinggang Wang; Jiemin Fang; Jiyang Qi; Rui Wu; Jianwei Niu; Wenyu Liu; | code |
2006 | Learning to Delegate for Large-scale Vehicle Routing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article presents a novel learning-augmented local search framework to solve large-scale VRP. |
Sirui Li; Zhongxia Yan; Cathy Wu; | |
2007 | Effective Meta-Regularization By Kernelized Proximal Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an algorithm called MetaProx to learn a proximal regularizer for the base learner. |
Weisen Jiang; James Kwok; Yu Zhang; | |
2008 | Towards Context-Agnostic Learning Using Synthetic Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. |
Charles Jin; Martin Rinard; | |
2009 | Minimax Optimal Quantile and Semi-Adversarial Regret Via Root-Logarithmic Regularizers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend existing KL regret upper bounds, which hold uniformly over target distributions, to possibly uncountable expert classes with arbitrary priors; provide the first full-information lower bounds for quantile regret on finite expert classes (which are tight); and provide an adaptively minimax optimal algorithm for the semi-adversarial paradigm that adapts to the true, unknown constraint faster, leading to uniformly improved regret bounds over existing methods. |
Jeffrey Negrea; Blair Bilodeau; Nicol� Campolongo; Francesco Orabona; Dan Roy; | |
2010 | Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving. |
Yu Shen; Laura Zheng; Manli Shu; Weizi Li; Tom Goldstein; Ming Lin; | |
2011 | Deep Proxy Causal Learning and Its Application to Confounded Bandit Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method for PCL, the deep feature proxy variable method (DFPV), to address the case where the proxies, treatments, and outcomes are high-dimensional and have nonlinear complex relationships, as represented by deep neural network features. |
Liyuan Xu; Heishiro Kanagawa; Arthur Gretton; | |
2012 | Certifying Robustness to Programmable Data Bias in Decision Trees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to certify that models produced by a learning algorithm are pointwise-robust to dataset biases. |
Anna Meyer; Aws Albarghouthi; Loris D'Antoni; | |
2013 | T�RF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We replace these priors with measurements from a time-of-flight (ToF) camera, and introduce a neural representation based on an image formation model for continuous-wave ToF cameras. |
Benjamin Attal; Eliot Laidlaw; Aaron Gokaslan; Changil Kim; Christian Richardt; James Tompkin; Matthew O'Toole; | |
2014 | Sequence-to-Sequence Learning with Latent Neural Grammars Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work explores an alternative, hierarchical approach to sequence-to-sequence learning with synchronous grammars, where each node in the target tree is transduced by a subset of nodes in the source tree. |
Yoon Kim; | |
2015 | Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we study smooth Q-learning, a prototypical learning model that explicitly captures the balance between game rewards and exploration costs. |
Stefanos Leonardos; Georgios Piliouras; Kelly Spendlove; | |
2016 | Low-Rank Extragradient Method for Nonsmooth and Low-Rank Matrix Optimization Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we consider standard convex relaxations for such problems. |
Atara Kaplan; Dan Garber; | |
2017 | Which Mutual-Information Representation Learning Objectives Are Sufficient for Control? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize the sufficiency of a state representation for learning and representing the optimal policy, and study several popular MI based objectives through this lens. |
Kate Rakelly; Abhishek Gupta; Carlos Florensa; Sergey Levine; | |
2018 | A Geometric Perspective Towards Neural Calibration Via Sensitivity Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Geometric Sensitivity Decomposition (GSD) which decomposes the norm of a sample feature embedding and the angular similarity to a target classifier into an instance-dependent and an instance-independent com-ponent. |
Junjiao Tian; Dylan Yung; Yen-Chang Hsu; Zsolt Kira; | |
2019 | Towards A Unified Information-Theoretic Framework for Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the expressiveness of the "conditional mutual information" (CMI) framework of Steinke and Zakynthinou (2020) and the prospect of using it to provide a unified framework for proving generalization bounds in the realizable setting. |
Mahdi Haghifam; Gintare Karolina Dziugaite; Shay Moran; Dan Roy; | |
2020 | Bayesian Decision-making Under Misspecified Priors with Applications to Meta-learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate that performance degrades gracefully with misspecification. |
Max Simchowitz; Christopher Tosh; Akshay Krishnamurthy; Daniel J. Hsu; Thodoris Lykouris; Miro Dudik; Robert E. Schapire; | |
2021 | Neural Trees for Learning on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new GNN architecture – the Neural Tree. |
Rajat Talak; Siyi Hu; Lisa Peng; Luca Carlone; | |
2022 | Enabling Fast Differentially Private SGD Via Just-in-Time Compilation and Vectorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We thoroughly demonstrate that by exploiting powerful language primitives, including vectorization, just-in-time compilation, and static graph optimization, one can dramatically reduce these overheads, in many cases nearly matching the best non-private running times. |
Pranav Subramani; Nicholas Vadivelu; Gautam Kamath; | code |
2023 | The Effectiveness of Feature Attribution Methods and Its Correlation with Automatic Evaluation Scores Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct the first user study to measure attribution map effectiveness in assisting humans in ImageNet classification and Stanford Dogs fine-grained classification, and when an image is natural or adversarial (i.e., contains adversarial perturbations). |
Giang Nguyen; Daeyoung Kim; Anh Nguyen; | |
2024 | Coordinated Proximal Policy Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. |
Zifan Wu; Chao Yu; Deheng Ye; Junge Zhang; haiyin piao; Hankz Hankui Zhuo; | |
2025 | Unbiased Classification Through Bias-Contrastive and Bias-Balanced Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this, we propose Bias-Contrastive (BiasCon) loss based on the contrastive learning framework, which effectively leverages the knowledge of bias labels. |
Youngkyu Hong; Eunho Yang; | |
2026 | Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To consider the interdependent knowledge between contextual clips into the network inference, we propose a Siamese Sampling and Reasoning (SiaSamRea) approach, which consists of a siamese sampling mechanism to generate sparse and similar clips (i.e., siamese clips) from the same video, and a novel reasoning strategy for integrating the interdependent knowledge between contextual clips into the network. |
Weijiang Yu; Haoteng Zheng; Mengfei Li; Lei Ji; Lijun Wu; Nong Xiao; Nan Duan; | |
2027 | Identification and Estimation of Joint Probabilities of Potential Outcomes in Observational Studies with Covariate Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the problem, this paper proposes a new statistical estimation method based on the augmented Lagrangian method and shows the asymptotic normality of the proposed estimators. |
Ryusei Shingaki; manabu kuroki; | |
2028 | Online False Discovery Rate Control for Anomaly Detection in Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article proposes novel rules for false discovery rate control (FDRC) geared towards online anomaly detection in time series. |
Quentin Rebjock; Baris Kurt; Tim Januschowski; Laurent Callot; | |
2029 | Pragmatic Image Compression for Human-in-the-Loop Decision-Making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The key insight is to train the model to produce a compressed image that induces the user to take the same action that they would have taken had they seen the original image. |
Sid Reddy; Anca Dragan; Sergey Levine; | |
2030 | Generalized Linear Bandits with Local Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings. |
Yuxuan Han; Zhipeng Liang; Yang Wang; Jiheng Zhang; | |
2031 | On The Algorithmic Stability of Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, this paper studies the algorithmic stability of a generic adversarial training algorithm, which can further help to establish an upper bound for generalization error. |
Yue Xing; Qifan Song; Guang Cheng; | |
2032 | Width-based Lookaheads with Learnt Base Policies and Heuristics Over The Atari-2600 Benchmark Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose new width-based planning and learning algorithms applied over the Atari-2600 benchmark. |
Stefan O'Toole; Nir Lipovetzky; Miquel Ramirez; Adrian Pearce; | |
2033 | Characterizing Possible Failure Modes in Physics-informed Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide evidence that the soft regularization in PINNs, which involves PDE-based differential operators, can introduce a number of subtle problems, including making the problem more ill-conditioned. |
Aditi Krishnapriyan; Amir Gholami; Shandian Zhe; Robert Kirby; Michael W. Mahoney; | |
2034 | Artistic Style Transfer with Internal-external Learning and Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, we propose an internal-external style transfer method with two contrastive losses. |
Haibo Chen; lei zhao; Zhizhong Wang; Huiming Zhang; Zhiwen Zuo; Ailin Li; Wei Xing; Dongming Lu; | |
2035 | Fast Abductive Learning By Similarity-based Consistency Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel abduction strategy, which leverages the similarity between samples, rather than the output information by the perceptual neural network, to guide the search in abduction. |
Yu-Xuan Huang; Wang-Zhou Dai; Le-Wen Cai; Stephen Muggleton; Yuan Jiang; | |
2036 | To Beam Or Not To Beam: That Is A Question of Cooperation for Language GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that our SelfGAN framework, built on this cooperative principle, outperforms Teacher Forcing and obtains state-of-the-art results on two challenging tasks, Summarization and Question Generation. |
Thomas Scialom; Paul-Alexis Dray; Jacopo Staiano; Sylvain Lamprier; Benjamin Piwowarski; | |
2037 | Shapley Residuals: Quantifying The Limits of The Shapley Value for Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we utilize an interpretation of Shapley values as the result of an orthogonal projection between vector spaces to calculate a residual representing the kernel component of that projection. |
Indra Kumar; Carlos Scheidegger; Suresh Venkatasubramanian; Sorelle Friedler; | |
2038 | The Elastic Lottery Ticket Hypothesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We conduct extensive experiments on CIFAR-10 and ImageNet, and propose a variety of strategies to tweak the winning tickets found from different networks of the same model family (e.g., ResNets). |
Xiaohan Chen; Yu Cheng; Shuohang Wang; Zhe Gan; Jingjing Liu; Zhangyang Wang; | code |
2039 | Joint Inference for Neural Network Depth and Dropout Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a unified Bayesian model selection method to jointly infer the most plausible network depth warranted by data, and perform dropout regularization simultaneously. |
Kishan K C; Rui Li; MohammadMahdi Gilany; | |
2040 | Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present a series of conformal building blocks and apply them in experiments with synthetic and real-world data to demonstrate that flows can model manifold-supported distributions without sacrificing tractable likelihoods. |
Brendan Ross; Jesse Cresswell; | |
2041 | The Limits of Optimal Pricing in The Dark Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand the limits of the seller’s learning when facing such a strategic and possibly manipulative buyer, we study a natural yet powerful buyer manipulation strategy. |
Quinlan Dawkins; Minbiao Han; Haifeng Xu; | |
2042 | No RL, No Simulation: Learning to Navigate Without Navigating Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we pose a simple question: Do we really need active interaction, ground-truth maps or even reinforcement-learning (RL) in order to solve the image-goal navigation task? |
Meera Hahn; Devendra Singh Chaplot; Shubham Tulsiani; Mustafa Mukadam; James M. Rehg; Abhinav Gupta; | |
2043 | Analogous to Evolutionary Algorithm: Designing A Unified Sequence Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Analogous to the dynamic local population in EA, we improve the existing transformer structure and propose a more efficient EAT model, and design task-related heads to deal with different tasks more flexibly. |
Jiangning Zhang; Chao Xu; Jian Li; Wenzhou Chen; Yabiao Wang; Ying Tai; Shuo Chen; Chengjie Wang; Feiyue Huang; Yong Liu; | |
2044 | Improving Compositionality of Neural Networks By Decoding Representations to Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With this as motivation, we take a modest first step towards improving deep learning programs by jointly training a generative model to constrain neural network activations to decode back to inputs. |
Mike Wu; Noah Goodman; Stefano Ermon; | |
2045 | The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study this question under the greedy oracle, which is a common (approximation) oracle with theoretical guarantees to solve many (offline) combinatorial optimization problems. |
Fang Kong; Yueran Yang; Wei Chen; Shuai Li; | |
2046 | Universal Semi-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this case, we propose a ”Class-shAring data detection and Feature Adaptation” (CAFA) framework which requires no prior knowledge of the class relationship between the labeled dataset and unlabeled dataset. |
Zhuo Huang; Chao Xue; Bo Han; Jian Yang; Chen Gong; | |
2047 | Improving Deep Learning Interpretability By Saliency Guided Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we tackle this issue and introduce a {\it saliency guided training} procedure for neural networks to reduce noisy gradients used in predictions while retaining the predictive performance of the model. |
Aya Abdelsalam Ismail; Hector Corrada Bravo; Soheil Feizi; | |
2048 | SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of inferring heterogeneous treatment effects from time-to-event data. |
Alicia Curth; Changhee Lee; Mihaela van der Schaar; | |
2049 | Optimal Rates for Nonparametric Density Estimation Under Communication Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider density estimation for Besov spaces when the estimator is restricted to use only a limited number of bits about each sample. |
Jayadev Acharya; Clement Canonne; Aditya Vikram Singh; Himanshu Tyagi; | |
2050 | Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the robust recovery of a low-rank matrix from sparsely and grossly corrupted Gaussian measurements, with no prior knowledge on the intrinsic rank. |
Lijun Ding; Liwei Jiang; Yudong Chen; Qing Qu; Zhihui Zhu; | |
2051 | Improving Computational Efficiency in Visual Reinforcement Learning Via Stored Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Stored Embeddings for Efficient Reinforcement Learning (SEER), a simple modification of existing off-policy RL methods, to address these computational and memory requirements. |
Lili Chen; Kimin Lee; Aravind Srinivas; Pieter Abbeel; | |
2052 | Learning Generalized Gumbel-max Causal Mechanisms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we instead argue for choosing a causal mechanism that is best under a quantitative criteria such as minimizing variance when estimating counterfactual treatment effects. |
Guy Lorberbom; Daniel Johnson; Chris J. Maddison; Daniel Tarlow; Tamir Hazan; | |
2053 | Bandit Learning with Delayed Impact of Actions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formulate this delayed and long-term impact of actions within the context of multi-armed bandits. |
Wei Tang; Chien-Ju Ho; Yang Liu; | |
2054 | A Stochastic Newton Algorithm for Distributed Convex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose and analyze a stochastic Newton algorithm for homogeneous distributed stochastic convex optimization, where each machine can calculate stochastic gradients of the same population objective, as well as stochastic Hessian-vector products (products of an independent unbiased estimator of the Hessian of the population objective with arbitrary vectors), with many such stochastic computations performed between rounds of communication. |
Brian Bullins; Kshitij Patel; Ohad Shamir; Nathan Srebro; Blake E. Woodworth; | |
2055 | Are Transformers More Robust Than CNNs? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to provide the first fair & in-depth comparisons between Transformers and CNNs, focusing on robustness evaluations. |
Yutong Bai; Jieru Mei; Alan L. Yuille; Cihang Xie; | |
2056 | Towards Sharper Generalization Bounds for Structured Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the generalization performance of structured prediction learning and obtain state-of-the-art generalization bounds. |
Shaojie Li; Yong Liu; | |
2057 | Automated Discovery of Adaptive Attacks on Adversarial Defenses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our key observation is that adaptive attacks are composed from a set of reusable building blocks that can be formalized in a search space and used to automatically discover attacks for unknown defenses. |
Chengyuan Yao; Pavol Bielik; Petar Tsankov; Martin Vechev; | |
2058 | PolarStream: Streaming Object Detection and Segmentation with Polar Pillars Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we propose using a polar coordinate system and make two key improvements on this design. |
Qi Chen; Sourabh Vora; Oscar Beijbom; | |
2059 | Representation Costs of Linear Neural Networks: Analysis and Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For different parameterizations (mappings from parameters to predictors), we study the regularization cost in predictor space induced by $l_2$ regularization on the parameters (weights). |
Zhen Dai; Mina Karzand; Nathan Srebro; | |
2060 | Teaching Via Best-Case Counterexamples in The Learning-with-Equivalence-Queries Paradigm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This learning paradigm has been extensively studied when the learner receives worst-case or random counterexamples; in this paper, we consider the optimal teacher who picks best-case counterexamples to teach the target hypothesis within a hypothesis class. |
Akash Kumar; Yuxin Chen; Adish Singla; | |
2061 | Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a holistic framework named MetaHG to automatically detect illicit drug traffickers on social media (i.e., Instagram), by tackling the following two new challenges: (1) different from existing works which merely focus on analyzing post content, MetaHG is capable of jointly modeling multi-modal content and relational structured information on social media for illicit drug trafficker detection; (2) in addition, through the proposed meta-learning technique, MetaHG addresses the issue of requiring sufficient data for model training. |
Yiyue Qian; Yiming Zhang; Yanfang Ye; Chuxu Zhang; | code |
2062 | Curriculum Disentangled Recommendation with Noisy Multi-feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, in this work we propose a Curriculum Disentangled Recommendation (CDR) model that is capable of efficiently learning disentangled representations from complex and noisy multi-feedback for better recommendation. |
Hong Chen; Yudong Chen; Xin Wang; Ruobing Xie; Rui Wang; Feng Xia; Wenwu Zhu; | |
2063 | Interpretable Agent Communication from Scratch (with A Generic Visual Processor Emerging on The Side) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we train two deep nets from scratch to perform realistic referent identification through unsupervised emergent communication. |
Roberto Dessi; Eugene Kharitonov; Baroni Marco; | |
2064 | MAU: A Motion-Aware Unit for Video Prediction and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Motion-Aware Unit (MAU) to capture reliable inter-frame motion information by broadening the temporal receptive field of the predictive units. |
Zheng Chang; Xinfeng Zhang; Shanshe Wang; Siwei Ma; Yan Ye; Xiang Xinguang; Wen Gao; | |
2065 | Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce Successor Feature Landmarks (SFL), a framework for exploring large, high-dimensional environments so as to obtain a policy that is proficient for any goal. |
Christopher Hoang; Sungryull Sohn; Jongwook Choi; Wilka Carvalho; Honglak Lee; | |
2066 | Streaming Belief Propagation for Community Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a simple model for networks growing over time which we refer to as streaming stochastic block model (StSBM). |
Yuchen Wu; Jakab Tardos; Mohammadhossein Bateni; Andr� Linhares; Filipe Miguel Goncalves de Almeida; Andrea Montanari; Ashkan Norouzi-Fard; | |
2067 | The Staircase Property: How Hierarchical Structure Can Guide Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper identifies a structural property of data distributions that enables deep neural networks to learn hierarchically. |
Emmanuel Abbe; Enric Boix Adsera; Matthew Brennan; Guy Bresler; Dheeraj Nagaraj; | |
2068 | MagNet: A Neural Network for Directed Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose MagNet, a GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian. |
Xitong Zhang; Yixuan He; Nathan Brugnone; Michael Perlmutter; Matthew Hirn; | |
2069 | Hardware-adaptive Efficient Latency Prediction for NAS Via Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce novel hardware embeddings to embed any devices considering them as black-box functions that output latencies, and meta-learn the hardware-adaptive latency predictor in a device-dependent manner, using the hardware embeddings. |
Hayeon Lee; Sewoong Lee; Song Chong; Sung Ju Hwang; | |
2070 | Topological Relational Learning on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose a novel topological neural framework of topological relational inference (TRI) which allows for integrating higher-order graph information to GNNs and for systematically learning a local graph structure. |
Yuzhou Chen; Baris Coskunuzer; Yulia Gel; | |
2071 | Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we argue that, under some distributional assumptions, classical learning-theoretic measures can sufficiently explain generalization for graph neural networks in the transductive setting. |
Pascal Esser; Leena Chennuru Vankadara; Debarghya Ghoshdastidar; | |
2072 | Federated Linear Contextual Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel federated linear contextual bandits model, where individual clients face different $K$-armed stochastic bandits coupled through common global parameters. |
Ruiquan Huang; Weiqiang Wu; Jing Yang; Cong Shen; | |
2073 | Least Square Calibration for Peer Reviews Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a flexible framework, namely \emph{least square calibration} (LSC), for selecting top candidates from peer ratings. |
Sijun Tan; Jibang Wu; Xiaohui Bei; Haifeng Xu; | |
2074 | Scaling Up Exact Neural Network Compression By ReLU Stability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. |
Thiago Serra; Xin Yu; Abhinav Kumar; Srikumar Ramalingam; | code |
2075 | Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work contributes a new approach to evaluating the biological and psychological validity of leading ANNs as models of human vision: by examining their similarities and differences in terms of their visual selectivity to the information contained in images. |
Thomas Langlois; Haicheng Zhao; Erin Grant; Ishita Dasgupta; Tom Griffiths; Nori Jacoby; | |
2076 | GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a conditional deep generative model that combines advances in graph neural networks. |
Longyuan Li; Jian Yao; Li Wenliang; Tong He; Tianjun Xiao; Junchi Yan; David Wipf; Zheng Zhang; | |
2077 | Instance-Dependent Partial Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature. |
Ning Xu; Congyu Qiao; Xin Geng; Min-Ling Zhang; | code |
2078 | Deep Learning with Label Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel algorithm, Randomized Response with Prior (RRWithPrior), which can provide more accurate results while maintaining the same level of privacy guaranteed by RR. |
Badih Ghazi; Noah Golowich; Ravi Kumar; Pasin Manurangsi; Chiyuan Zhang; | |
2079 | Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a semialgebraic representation for ReLU based monDEQs which allow to approximate the corresponding input output relation by semidefinite programs (SDP). |
Tong Chen; Jean B. Lasserre; Victor Magron; Edouard Pauwels; | |
2080 | The Role of Global Labels in Few-Shot Classification and How to Infer Them Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show why exploiting pre-training is theoretically advantageous for meta-learning, and in particular the critical role of global labels. |
Ruohan Wang; Massimiliano Pontil; Carlo Ciliberto; | |
2081 | NeuS: Learning Neural Implicit Surfaces By Volume Rendering for Multi-view Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. |
Peng Wang; Lingjie Liu; Yuan Liu; Christian Theobalt; Taku Komura; Wenping Wang; | |
2082 | Improved Guarantees for Offline Stochastic Matching Via New Ordered Contention Resolution Schemes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present new ordered contention resolution schemes yielding improved approximation guarantees for some of the foundational problems studied in this area. |
Brian Brubach; Nathaniel Grammel; Will Ma; Aravind Srinivasan; | |
2083 | UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, UFC-BERT, to unify any number of multi-modal controls. |
Zhu Zhang; Jianxin Ma; Chang Zhou; Rui Men; Zhikang Li; Ming Ding; Jie Tang; Jingren Zhou; Hongxia Yang; | |
2084 | Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the colloquially known phenomenon that trained agents often prefer actions at the boundaries of that space. |
Tim Seyde; Igor Gilitschenski; Wilko Schwarting; Bartolomeo Stellato; Martin Riedmiller; Markus Wulfmeier; Daniela Rus; | |
2085 | Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the limitation, we propose Latent Dynamics Mixture (LDM) that trains a reinforcement learning agent with imaginary tasks generated from mixtures of learned latent dynamics. |
Suyoung Lee; Sae-Young Chung; | |
2086 | Localization with Sampling-Argmax Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose sampling-argmax, a differentiable training method that imposes implicit constraints to the shape of the probability map by minimizing the expectation of the localization error. |
Jiefeng Li; Tong Chen; Ruiqi Shi; Yujing Lou; Yong-Lu Li; Cewu Lu; | code |
2087 | Improved Regularization and Robustness for Fine-tuning in Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a PAC-Bayes generalization bound that depends on the distance traveled in each layer during fine-tuning and the noise stability of the fine-tuned model. |
Dongyue Li; Hongyang Zhang; | |
2088 | BARTScore: Evaluating Generated Text As Text Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we conceptualize the evaluation of generated text as a text generation problem, modeled using pre-trained sequence-to-sequence models. |
Weizhe Yuan; Graham Neubig; Pengfei Liu; | code |
2089 | An Analysis of Ermakov-Zolotukhin Quadrature Using Kernels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how these two classes of quadrature are related, and we prove a tractable formula of the expected value of the squared worst-case integration error on the unit ball of an RKHS of the former quadrature. |
Ayoub Belhadji; | |
2090 | Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we prove that lookahead using SGD as its inner-loop optimizer can better balance the optimization error and generalization error to achieve smaller excess risk error than vanilla SGD on (strongly) convex problems and nonconvex problems with Polyak-{\L}ojasiewicz condition which has been observed/proved in neural networks. |
Pan Zhou; Hanshu Yan; Xiaotong Yuan; Jiashi Feng; Shuicheng Yan; | code |
2091 | Online Market Equilibrium with Application to Fair Division Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple, scalable and interpretable allocation and pricing dynamics termed as PACE. |
Yuan Gao; Christian Kroer; Alex Peysakhovich; | |
2092 | Dynamic Resolution Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we observe that the smallest resolution for accurately predicting the given image is different using the same neural network. |
Mingjian Zhu; Kai Han; Enhua Wu; Qiulin Zhang; Ying Nie; Zhenzhong Lan; Yunhe Wang; | |
2093 | Gauge Equivariant Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To enhance expressive ability, we adopt regular field of cyclic groups as feature fields in intermediate layers, and propose a novel method to parallel transport the feature vectors in these fields. |
Lingshen He; Yiming Dong; Yisen Wang; Dacheng Tao; Zhouchen Lin; | |
2094 | Unsupervised Object-Based Transition Models For 3D Partially Observable Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over successive frames. |
Antonia Creswell; Rishabh Kabra; Chris Burgess; Murray Shanahan; | |
2095 | Robust Contrastive Learning Using Negative Samples with Diminished Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that by generating carefully designed negative samples, contrastive learning can learn more robust representations with less dependence on such features. |
Songwei Ge; Shlok Mishra; Chun-Liang Li; Haohan Wang; David Jacobs; | |
2096 | General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper considers the global geometry of general low-rank minimization problems via the Burer-Monterio factorization approach. |
Haixiang Zhang; Yingjie Bi; Javad Lavaei; | |
2097 | Flow Network Based Generative Models for Non-Iterative Diverse Candidate Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using insights from Temporal Difference learning, we propose GFlowNet, based on a view of the generative process as a flow network, making it possible to handle the tricky case where different trajectories can yield the same final state, e.g., there are many ways to sequentially add atoms to generate some molecular graph. |
Emmanuel Bengio; Moksh Jain; Maksym Korablyov; Doina Precup; Yoshua Bengio; | |
2098 | Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the policy finetuning problem in episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and horizon length $H$. |
Tengyang Xie; Nan Jiang; Huan Wang; Caiming Xiong; Yu Bai; | |
2099 | Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes an information bottleneck, and as a result, only a subset of the task-relevant information is passed on to the output. |
Jungbeom Lee; Jooyoung Choi; Jisoo Mok; Sungroh Yoon; | |
2100 | SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of SCO and explore the role of implicit regularization, batch size and multiple epochs for SGD. |
Ayush Sekhari; Karthik Sridharan; Satyen Kale; | |
2101 | AC-GC: Lossy Activation Compression with Guaranteed Convergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we build upon recent developments on Stochastic Gradient Descent convergence to prove an upper bound on the expected loss increase when training with compressed activation storage. |
R David Evans; Tor Aamodt; | |
2102 | Label Noise SGD Provably Prefers Flat Global Minimizers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by empirical studies that demonstrate that training with noisy labels improves generalization, we study the implicit regularization effect of SGD with label noise. |
Alex Damian; Tengyu Ma; Jason D. Lee; | |
2103 | Can We Have It All? On The Trade-off Between Spatial and Adversarial Robustness of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we prove a quantitative trade-off between spatial and adversarial robustness in a simple statistical setting. |
Sandesh Kamath; Amit Deshpande; Subrahmanyam Kambhampati Venkata; Vineeth N Balasubramanian; | |
2104 | Universal Off-Policy Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take the first steps towards a ‘universal off-policy estimator’ (UnO)—one that provides off-policy estimates and high-confidence bounds for any parameter of the return distribution. |
Yash Chandak; Scott Niekum; Bruno da Silva; Erik Learned-Miller; Emma Brunskill; Philip S. Thomas; | |
2105 | A Non-commutative Extension of Lee-Seung's Algorithm for Positive Semidefinite Factorizations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe a non-commutative extension of Lee-Seung’s algorithm, which we call the Matrix Multiplicative Update (MMU) algorithm, for computing PSD factorizations. |
Yong Sheng Soh; Antonios Varvitsiotis; | |
2106 | Efficiently Identifying Task Groupings for Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we suggest an approach to select which tasks should train together in multi-task learning models. |
Chris Fifty; Ehsan Amid; Zhe Zhao; Tianhe Yu; Rohan Anil; Chelsea Finn; | |
2107 | Instance-Conditioned GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. |
Arantxa Casanova; Marlene Careil; Jakob Verbeek; Michal Drozdzal; Adriana Romero; | code |
2108 | DeepSITH: Efficient Learning Via Decomposition of What and When Across Time Scales Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces DeepSITH, a deep network comprisingbiologically-inspired Scale-Invariant Temporal History (SITH) modules inseries with dense connections between layers. |
Brandon Jacques; Zoran Tiganj; Marc Howard; Per Sederberg; | |
2109 | A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to conduct multi-label active learning (ML-AL) through a novel integrated Gaussian Process-Bayesian Bernoulli Mixture model (GP-B$^2$M) to accurately quantify a data sample’s overall contribution to a correlated label space and choose the most informative samples for cost-effective annotation. |
Weishi Shi; Dayou Yu; Qi Yu; | |
2110 | Differentially Private Empirical Risk Minimization Under The Fairness Lens Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper builds on these important observations and sheds light on the causes of the disparate impacts arising in the problem of differentially private empirical risk minimization. |
Cuong Tran; My Dinh; Ferdinando Fioretto; | |
2111 | A Unified View of CGANs with and Without Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that classifiers can be properly leveraged to improve cGANs. |
Si-An Chen; Chun-Liang Li; Hsuan-Tien Lin; | code |
2112 | Online and Offline Reinforcement Learning By Planning with A Learned Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Combining Reanalyse with the MuZero algorithm, we introduce MuZero Unplugged, a single unified algorithm for any data budget, including Offline RL. |
Julian Schrittwieser; Thomas Hubert; Amol Mandhane; Mohammadamin Barekatain; Ioannis Antonoglou; David Silver; | |
2113 | Stochastic Multi-Armed Bandits with Control Variates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies a new variant of the stochastic multi-armed bandits problem where auxiliary information about the arm rewards is available in the form of control variates. |
Arun Verma; Manjesh Kumar Hanawal; | |
2114 | Near-Optimal No-Regret Learning in General Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that Optimistic Hedge — a common variant of multiplicative-weights-updates with recency bias — attains ${\rm poly}(\log T)$ regret in multi-player general-sum games. |
Constantinos Daskalakis; Maxwell Fishelson; Noah Golowich; | |
2115 | Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Particularly, we argue that the existing augmentation pipeline for generating multiple positive views naturally introduces out-of-distribution (OOD) samples that undermine the learning of the downstream tasks. |
Yu Wang; Jingyang Lin; Jingjing Zou; Yingwei Pan; Ting Yao; Tao Mei; | code |
2116 | Improving Anytime Prediction with Parallel Cascaded Networks and A Temporal-Difference Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a temporal-difference training loss that achieves a strictly superior speed-accuracy profile over standard losses and enables the cascaded architecture to outperform state-of-the-art anytime-prediction methods. |
Michael Iuzzolino; Michael C. Mozer; Samy Bengio; | |
2117 | Identifiable Generative Models for Missing Not at Random Data Imputation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we fill in this gap by systematically analyzing the identifiability of generative models under MNAR. |
Chao Ma; Cheng Zhang; | |
2118 | DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two embeddings of the input coordinates, which lead to (approximate) spatial invariance of the NTK and of the filter. |
Benjamin Dupuis; Arthur Jacot; | |
2119 | Baleen: Robust Multi-Hop Reasoning at Scale Via Condensed Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tame the search space, we propose condensed retrieval, a pipeline that summarizes the retrieved passages after each hop into a single compact context. |
Omar Khattab; Christopher Potts; Matei Zaharia; | |
2120 | Local Hyper-Flow Diffusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the first local diffusion method that achieves edge-size-independent Cheeger-type guarantee for the problem of local hypergraph clustering while applying to a rich class of higher-order relations that covers a number of previously studied special cases. |
Kimon Fountoulakis; Pan Li; Shenghao Yang; | |
2121 | Permuton-induced Chinese Restaurant Process Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes the permuton-induced Chinese restaurant process (PCRP), a stochastic process on rectangular partitioning of a matrix. |
Masahiro Nakano; Yasuhiro Fujiwara; Akisato Kimura; Takeshi Yamada; naonori ueda; | |
2122 | Faster Algorithms and Constant Lower Bounds for The Worst-Case Expected Error Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we design provably efficient algorithms for approximating the optimal semilinear estimator based on online convex optimization. |
Jonah Brown-Cohen; | |
2123 | On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop novel upper-bounds for the target general loss which appeal us to define two kinds of domain-invariant representations. |
Trung Phung; Trung Le; Tung-Long Vuong; Toan Tran; Anh Tran; Hung Bui; Dinh Phung; | |
2124 | You Never Cluster Alone Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation that encodes the context of each data group. |
Yuming Shen; Ziyi Shen; Menghan Wang; Jie Qin; Philip Torr; Ling Shao; | |
2125 | Dynamic COVID Risk Assessment Accounting for Community Virus Exposure from A Spatial-temporal Transmission Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To study the impact of socioeconomic factors on COVID transmission, we first propose a spatial-temporal model to examine the socioeconomic heterogeneity and spatial correlation of COVID-19 transmission at the community level. Second, to assess the individual risk of severe COVID-19 outcomes after a positive diagnosis, we propose a dynamic, varying-coefficient model that integrates individual-level risk factors from electronic health records (EHRs) with community-level risk factors. |
Yuan Chen; Wenbo Fei; Qinxia Wang; Donglin Zeng; Yuanjia Wang; | |
2126 | Dueling Bandits with Adversarial Sleeping Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the problem of sleeping dueling bandits with stochastic preferences and adversarial availabilities (DB-SPAA). |
Aadirupa Saha; Pierre Gaillard; | |
2127 | Beware of The Simulated DAG! Causal Discovery Benchmarks May Be Easy to Game Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce varsortability as a measure of the agreement between the order of increasing marginal variance and the causal order. |
Alexander Reisach; Christof Seiler; Sebastian Weichwald; | code |
2128 | Automated Dynamic Mechanism Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study Bayesian automated mechanism design in unstructured dynamic environments, where a principal repeatedly interacts with an agent, and takes actions based on the strategic agent’s report of the current state of the world. |
Hanrui Zhang; Vincent Conitzer; | |
2129 | A Generative Nonparametric Bayesian Model for Whole Genomes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article we propose a new generative sequence model, the Bayesian embedded autoregressive (BEAR) model, which uses a parametric autoregressive model to specify a conjugate prior over a nonparametric Bayesian Markov model. |
Alan Amin; Eli Weinstein; Debora Marks; | |
2130 | Robust Predictable Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We take advantage of these properties to propose a method (RPC) for learning simple policies. |
Ben Eysenbach; Russ R. Salakhutdinov; Sergey Levine; | |
2131 | Unsupervised Speech Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. |
Alexei Baevski; Wei-Ning Hsu; Alexis CONNEAU; Michael Auli; | |
2132 | Robustness Between The Worst and Average Case Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that a sliding scale between these two extremes provides a valuable additional metric by which to gauge robustness. |
Leslie Rice; Anna Bair; Huan Zhang; J. Zico Kolter; | code |
2133 | Online Learning and Control of Complex Dynamical Systems from Sensory Input Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel method for learning an embedding of the state space with linear dynamics from sensory data. |
Oumayma Bounou; Jean Ponce; Justin Carpentier; | |
2134 | Self-Supervised Bug Detection and Repair Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards addressing this, we present BugLab, an approach for self-supervised learning of bug detection and repair. |
Miltiadis Allamanis; Henry Jackson-Flux; Marc Brockschmidt; | |
2135 | Faster Neural Network Training with Approximate Tensor Operations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel technique for faster deep neural network training which systematically applies sample-based approximation to the constituent tensor operations, i.e., matrix multiplications and convolutions. |
Menachem Adelman; Kfir Levy; Ido Hakimi; Mark Silberstein; | |
2136 | Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider a submodular optimization based approach for learning rule sets. |
Fan Yang; Kai He; Linxiao Yang; Hongxia Du; Jingbang Yang; Bo Yang; Liang Sun; | |
2137 | Spatial-Temporal Super-Resolution of Satellite Imagery Via Conditional Pixel Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new conditional pixel synthesis model that uses abundant, low-cost, low-resolution imagery to generate accurate high-resolution imagery at locations and times in which it is unavailable. |
Yutong He; Dingjie Wang; Nicholas Lai; William Zhang; Chenlin Meng; Marshall Burke; David Lobell; Stefano Ermon; | |
2138 | On Memorization in Probabilistic Deep Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend a recently proposed measure of memorization for supervised learning (Feldman, 2019) to the unsupervised density estimation problem and adapt it to be more computationally efficient. |
Gerrit van den Burg; Chris Williams; | |
2139 | You Are The Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this withholding of information, in this paper, I introduce the Isotonic Mechanism, a simple and efficient approach to improving on the imprecise raw scores by leveraging certain information that the owner is incentivized to provide. |
Weijie Su; | |
2140 | Garment4D: Garment Reconstruction from Point Cloud Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To circumvent the problems caused by 2D images, we propose a principled framework, Garment4D, that uses 3D point cloud sequences of dressed humans for garment reconstruction. |
Fangzhou Hong; Liang Pan; Zhongang Cai; Ziwei Liu; | code |
2141 | Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the algorithmic role of entropy regularization in single-agent reinforcement learning and game theory, we develop provably efficient extragradient methods to find the quantal response equilibrium (QRE)—which are solutions to zero-sum two-player matrix games with entropy regularization—at a linear rate. |
Shicong Cen; Yuting Wei; Yuejie Chi; | |
2142 | Shift-Robust GNNs: Overcoming The Limitations of Localized Graph Training Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present a method, Shift-Robust GNN (SR-GNN), designed to account for distributional differences between biased training data and the graph’s true inference distribution. |
Qi Zhu; Natalia Ponomareva; Jiawei Han; Bryan Perozzi; | |
2143 | RIM: Reliable Influence-based Active Learning on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to unify active learning (AL) and message passing towards minimizing labeling costs, e.g., making use of few and unreliable labels that can be obtained cheaply. |
Wentao Zhang; Yexin Wang; Zhenbang You; Meng Cao; Ping Huang; Jiulong Shan; Zhi Yang; Bin CUI; | |
2144 | Dynamical Wasserstein Barycenters for Time-series Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a dynamical Wasserstein barycentric (DWB) model that estimates the system state over time as well as the data-generating distributions of pure states in an unsupervised manner. |
Kevin Cheng; Shuchin Aeron; Michael C. Hughes; Eric Miller; | |
2145 | RelaySum for Decentralized Deep Learning on Heterogeneous Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we introduce the RelaySum mechanism for information propagation in decentralized learning. |
Thijs Vogels; Lie He; Anastasiia Koloskova; Sai Praneeth Karimireddy; Tao Lin; Sebastian U. Stich; Martin Jaggi; | |
2146 | Transformers Generalize DeepSets and Can Be Extended to Graphs & Hypergraphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). |
Jinwoo Kim; Saeyoon Oh; Seunghoon Hong; | code |
2147 | No Regrets for Learning The Prior in Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose AdaTS, a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with. |
Soumya Basu; Branislav Kveton; Manzil Zaheer; Csaba Szepesvari; | |
2148 | Encoding Robustness to Image Style Via Adversarial Feature Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training. By fine-tuning neural networks on adversarial feature distributions, we observe improved robustness of networks to various unseen distributional shifts, including style variations and image corruptions. |
Manli Shu; Zuxuan Wu; Micah Goldblum; Tom Goldstein; | code |
2149 | Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the “continuized” Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. |
Mathieu Even; Rapha�l Berthier; Francis Bach; Nicolas Flammarion; Hadrien Hendrikx; Pierre Gaillard; Laurent Massouli�; Adrien Taylor; | |
2150 | Natural Continual Learning: Success Is A Journey, Not (just) A Destination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Natural Continual Learning (NCL), a new method that unifies weight regularization and projected gradient descent. |
Ta-Chu Kao; Kristopher Jensen; Gido van de Ven; Alberto Bernacchia; Guillaume Hennequin; | |
2151 | Individual Privacy Accounting Via A R�nyi Filter Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we give a method for tighter privacy loss accounting based on the value of a personalized privacy loss estimate for each individual in each analysis. |
Vitaly Feldman; Tijana Zrnic; | |
2152 | Post-Training Quantization for Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an effective post-training quantization algorithm for reducing the memory storage and computational costs of vision transformers. |
Zhenhua Liu; Yunhe Wang; Kai Han; Wei Zhang; Siwei Ma; Wen Gao; | code |
2153 | Unsupervised Part Discovery with Contrastive Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an unsupervised approach to object part discovery and segmentation and make three contributions. |
Subhabrata Choudhury; Iro Laina; Christian Rupprecht; Andrea Vedaldi; | code |
2154 | ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit and dive deeper into PointNet++, one of the most influential yet under-explored networks, and develop faster and more accurate variants of the model. |
Guocheng Qian; Hasan Hammoud; Guohao Li; Ali Thabet; Bernard Ghanem; | |
2155 | An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we study the extent to which the seminal domain adaptation theory of Ben-David et al. (2007) explains the performance of ERMs. |
Ramakrishna Vedantam; David Lopez-Paz; David J. Schwab; | |
2156 | Fair Sequential Selection Using Supervised Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss whether the fairness notions (e.g., equal opportunity, statistical parity, etc.) that are commonly used in classification problems are suitable for the sequential selection problems. |
Mohammad Mahdi Khalili; Xueru Zhang; Mahed Abroshan; | |
2157 | Towards Sample-efficient Overparameterized Meta-learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While the prior literature focuses on the classical supervised setting, this paper aims to demystify overparameterization for meta-learning. |
Yue Sun; Adhyyan Narang; Ibrahim Gulluk; Samet Oymak; Maryam Fazel; | |
2158 | ScaleCert: Scalable Certified Defense Against Adversarial Patches with Sparse Superficial Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the certified defense methodology that achieves high provable robustness for high-resolution images and largely improves the practicality for real adoption of the certified defense. |
Husheng Han; Kaidi Xu; Xing Hu; Xiaobing Chen; Ling LIANG; Zidong Du; Qi Guo; Yanzhi Wang; Yunji Chen; | |
2159 | Towards Mental Time Travel: A Hierarchical Memory for Reinforcement Learning Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we propose a Hierarchical Chunk Attention Memory (HCAM), that helps agents to remember the past in detail. |
Andrew Lampinen; Stephanie Chan; Andrea Banino; Felix Hill; | |
2160 | Beyond Tikhonov: Faster Learning with Self-concordant Losses, Via Iterative Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we go a step further and show that fast and optimal rates can be achieved for GSC by using the iterated Tikhonov regularization scheme, which is intrinsically related to the proximal point method in optimization, and overcomes the limitation of the classical Tikhonov regularization. |
Gaspard Beugnot; Julien Mairal; Alessandro Rudi; | |
2161 | Variational Bayesian Reinforcement Learning with Regret Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the exploration-exploitation trade-off in reinforcement learning and show that an agent endowed with an exponential epistemic-risk-seeking utility function explores efficiently, as measured by regret. |
Brendan O'Donoghue; | |
2162 | Logarithmic Regret from Sublinear Hints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the question of whether an algorithm really requires a hint at _every_ time step. |
Aditya Bhaskara; Ashok Cutkosky; Ravi Kumar; Manish Purohit; | |
2163 | Independent Mechanism Analysis, A New Concept? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate an alternative path and consider instead including assumptions reflecting the principle of independent causal mechanisms exploited in the field of causality. |
Luigi Gresele; Julius von K�gelgen; Vincent Stimper; Bernhard Sch�lkopf; Michel Besserve; | |
2164 | Momentum Centering and Asynchronous Update for Adaptive Gradient Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose ACProp (Asynchronous-centering-Prop), an adaptive optimizer which combines centering of second momentum and asynchronous update (e.g. for $t$-th update, denominator uses information up to step $t-1$, while numerator uses gradient at $t$-th step). |
Juntang Zhuang; Yifan Ding; Tommy Tang; Nicha Dvornek; Sekhar C. Tatikonda; James Duncan; | code |
2165 | Robustness Via Uncertainty-aware Cycle Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose a novel probabilistic method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by generalized Gaussian distribution, capable of modelling heavy-tailed distributions. |
Uddeshya Upadhyay; Yanbei Chen; Zeynep Akata; | code |
2166 | CBP: Backpropagation with Constraint on Weight Precision Using A Pseudo-Lagrange Multiplier Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose the constrained backpropagation (CBP) algorithm based on the pseudo-Lagrange multiplier method to obtain the optimal set of weights that satisfy a given set of constraints. |
Guhyun Kim; Doo Seok Jeong; | code |
2167 | On The Sample Complexity of Privately Learning Axis-Aligned Rectangles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel algorithm that reduces the sample complexity to only $\tilde{O}\left\{d{\cdot}\left(\log^*|X|\right)^{1.5}\right\}$, attaining a dimensionality optimal dependency without requiring the sample complexity to grow with $\log|X|$. |
Menachem Sadigurschi; Uri Stemmer; | |
2168 | Implicit Sparse Regularization: The Impact of Depth and Early Stopping Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the implicit bias of gradient descent for sparse regression. |
Jiangyuan Li; Thanh Nguyen; Chinmay Hegde; Ka Wai Wong; | |
2169 | Efficient Generalization with Distributionally Robust Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a new stochastic gradient descent algorithm to ef?ciently solve this DRL formulation. |
Soumyadip Ghosh; Mark Squillante; Ebisa Wollega; | |
2170 | No-regret Online Learning Over Riemannian Manifolds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study Riemannian online gradient descent (R-OGD) on Hadamard manifolds for both geodesically convex and strongly geodesically convex loss functions, and Riemannian bandit algorithm (R-BAN) on Hadamard homogeneous manifolds for geodesically convex functions. |
Xi Wang; Zhipeng Tu; Yiguang Hong; Yingyi Wu; Guodong Shi; | |
2171 | Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present HIerarchical reinforcement learning Guided by Landmarks (HIGL), a novel framework for training a high-level policy with a reduced action space guided by landmarks, i.e., promising states to explore. |
Junsu Kim; Younggyo Seo; Jinwoo Shin; | |
2172 | Minimax Regret for Stochastic Shortest Path Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we show that the minimax regret for this setting is $\widetilde O(\sqrt{ (B_\star^2 + B_\star) |S| |A| K})$ where $B_\star$ is a bound on the expected cost of the optimal policy from any state, $S$ is the state space, and $A$ is the action space. |
Alon Cohen; Yonathan Efroni; Yishay Mansour; Aviv Rosenberg; | |
2173 | Parametrized Quantum Policies for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a hybrid quantum-classical reinforcement learning model using very few qubits, which we show can be effectively trained to solve several standard benchmarking environments. |
Sofiene Jerbi; Casper Gyurik; Simon Marshall; Hans Briegel; Vedran Dunjko; | |
2174 | On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, we show that KL-regularized reinforcement learning with behavioral policies derived from expert demonstrations suffers from previously unrecognized pathological behavior that can lead to slow, unstable, and suboptimal online training. |
Tim G. J. Rudner; Cong Lu; Michael Osborne; Yarin Gal; Yee Teh; | |
2175 | Conditional Generation Using Polynomial Expansions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a general framework, called CoPE, that enables a polynomial expansion of two input variables and captures their auto- and cross-correlations. |
Grigorios Chrysos; Markos Georgopoulos; Yannis Panagakis; | code |
2176 | Efficient Constrained Sampling Via The Mirror-Langevin Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. |
Kwangjun Ahn; Sinho Chewi; | |
2177 | Adaptive Online Packing-guided Search for POMDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this, we take one step further and propose an online planning algorithm, Adaptive Online Packing-guided Search (AdaOPS), to better approximate beliefs with adaptive particle filter technique and balance estimation bias and variance by fusing similar observation branches. |
Chenyang Wu; Guoyu Yang; Zongzhang Zhang; Yang Yu; Dong Li; Wulong Liu; Jianye Hao; | |
2178 | Turing Completeness of Bounded-Precision Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To remove this assumption, we propose a dynamically growing memory module made of neurons of fixed precision. |
Stephen Chung; Hava Siegelmann; | |
2179 | End-to-end Multi-modal Video Temporal Grounding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from most existing methods that only consider RGB images as visual features, we propose a multi-modal framework to extract complementary information from videos. |
Yi-Wen Chen; Yi-Hsuan Tsai; Ming-Hsuan Yang; | |
2180 | How Powerful Are Performance Predictors in Neural Architecture Search? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we give the first large-scale study of performance predictors by analyzing 31 techniques ranging from learning curve extrapolation, to weight-sharing, to supervised learning, to zero-cost proxies. |
Colin White; Arber Zela; Robin Ru; Yang Liu; Frank Hutter; | |
2181 | Stylized Dialogue Generation with Multi-Pass Dual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the above difficulties, we propose multi-pass dual learning (MPDL), which leverages the duality among the context, response of style S1 and response of style S_0. |
Jinpeng Li; Yingce Xia; Rui Yan; Hongda Sun; Dongyan Zhao; Tie-Yan Liu; | |
2182 | Entropy-based Adaptive Hamiltonian Monte Carlo Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a gradient-based algorithm that allows for the adaptation of the mass matrix by encouraging the leapfrog integrator to have high acceptance rates while also exploring all dimensions jointly. |
Marcel Hirt; Michalis Titsias; Petros Dellaportas; | |
2183 | Continual World: A Robotic Benchmark For Continual Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our benchmark aims to provide a meaningful and computationally inexpensive challenge for the community and thus help better understand the performance of existing and future solutions. |
Maciej Wolczyk; Michal Zajac; Razvan Pascanu; Lukasz Kucinski; Piotr Milos; | code |
2184 | Towards Best-of-All-Worlds Online Learning with Feedback Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: One of our key technical contributions is in establishing the convexity of this regularizer and controlling its inverse Hessian, despite its complex product structure. |
Liad Erez; Tomer Koren; | |
2185 | ViTAE: Vision Transformer Advanced By Exploring Intrinsic Inductive Bias Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. |
Yufei Xu; Qiming ZHANG; Jing Zhang; Dacheng Tao; | code |
2186 | Open Rule Induction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we propose the open rule induction problem, which aims to induce open rules utilizing the knowledge in LMs. |
Wanyun Cui; Xingran Chen; | |
2187 | Post-Contextual-Bandit Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Contextual Adaptive Doubly Robust (CADR) estimator, a novel estimator for policy value that is asymptotically normal under contextual adaptive data collection. |
Aurelien Bibaut; Maria Dimakopoulou; Nathan Kallus; Antoine Chambaz; Mark van der Laan; | |
2188 | Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we revisit the role of discriminator in GAN compression and design a novel generator-discriminator cooperative compression scheme for GAN compression, termed GCC. |
Shaojie Li; Jie Wu; Xuefeng Xiao; Fei Chao; Xudong Mao; Rongrong Ji; | |
2189 | Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of offline policy evaluation~(OPE) with Markov decision processes~(MDPs), where the goal is to estimate the utility of given decision-making policies based on static datasets. |
Kohei Miyaguchi; | |
2190 | Topographic VAEs Learn Equivariant Capsules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we seek to bridge the concepts of topographic organization and equivariance in neural networks. |
Thomas Keller; Max Welling; | |
2191 | MobILE: Model-Based Imitation Learning From Observation Alone Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a provably efficient model-based framework MobILE to solve the ILFO problem. |
Rahul Kidambi; Jonathan Chang; Wen Sun; | code |
2192 | Few-Round Learning for Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim at designing an initial model based on which an arbitrary group of clients can obtain a global model for its own purpose, within only a few rounds of FL. |
Younghyun Park; Dong-Jun Han; Do-Yeon Kim; Jun Seo; Jaekyun Moon; | |
2193 | On Path Integration of Grid Cells: Group Representation and Isotropic Scaling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct theoretical analysis of a general representation model of path integration by grid cells, where the 2D self-position is encoded as a higher dimensional vector, and the 2D self-motion is represented by a general transformation of the vector. |
Ruiqi Gao; Jianwen Xie; Xue-Xin Wei; Song-Chun Zhu; Ying Nian Wu; | code |
2194 | Online Convex Optimization with Continuous Switching Constraint Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To control the switching cost, we introduce the problem of online convex optimization with continuous switching constraint, where the goal is to achieve a small regret given a budget on the \emph{overall} switching cost. |
Guanghui Wang; Yuanyu Wan; Tianbao Yang; Lijun Zhang; | |
2195 | Why Do Better Loss Functions Lead to Less Transferable Features? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies how the choice of training objective affects the transferability of the hidden representations of convolutional neural networks trained on ImageNet. |
Simon Kornblith; Ting Chen; Honglak Lee; Mohammad Norouzi; | |
2196 | Breaking The Centralized Barrier for Cross-device Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a general algorithmic framework, Mime, which i) mitigates client drift and ii) adapts arbitrary centralized optimization algorithms such as momentum and Adam to the cross-device federated learning setting. |
Sai Praneeth Karimireddy; Martin Jaggi; Satyen Kale; Mehryar Mohri; Sashank Reddi; Sebastian U. Stich; Ananda Theertha Suresh; | |
2197 | Adversarially Robust Learning for Security-constrained Optimal Power Flow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we combine innovations from these areas to tackle the problem of N-k security-constrained optimal power flow (SCOPF). |
Priya Donti; Aayushya Agarwal; Neeraj Vijay Bedmutha; Larry Pileggi; J. Zico Kolter; | |
2198 | Learning A Single Neuron with Bias Using Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We theoretically study the fundamental problem of learning a single neuron with a bias term ($\mathbf{x}\mapsto \sigma(\langle\mathbf{w},\mathbf{x}\rangle + b)$) in the realizable setting with the ReLU activation, using gradient descent. |
Gal Vardi; Gilad Yehudai; Ohad Shamir; | |
2199 | Making A (Counterfactual) Difference One Rationale at A Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate whether counterfactual data augmentation (CDA), without human assistance, can improve the performance of the selector by lowering the mutual information between spurious signals and the document label. |
Mitchell Plyler; Michael Green; Min Chi; | |
2200 | 3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Siamese voxel-to-BEV tracker, which can significantly improve the tracking performance in sparse 3D point clouds. |
Le Hui; Lingpeng Wang; Mingmei Cheng; Jin Xie; Jian Yang; | |
2201 | Stateful Strategic Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While prior work has focused on the short-term strategic interactions between a decision-making institution (modeled as a principal) and individual decision-subjects (modeled as agents), we investigate interactions spanning multiple time-steps. |
Keegan Harris; Hoda Heidari; Steven Z. Wu; | |
2202 | Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce a general-purpose deep learning architecture that takes as input the entire dataset instead of processing one datapoint at a time. |
Jannik Kossen; Neil Band; Clare Lyle; Aidan N. Gomez; Thomas Rainforth; Yarin Gal; | |
2203 | Your Head Is There to Move You Around: Goal-driven Models of The Primate Dorsal Pathway Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We hypothesized that the properties of dorsal stream neurons could be explained by a simple learning objective: the need for an organism to orient itself during self-motion. |
Patrick Mineault; Shahab Bakhtiari; Blake Richards; Christopher Pack; | |
2204 | Achieving Rotational Invariance with Bessel-Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a new type of convolutional layer that takes advantage of Bessel functions, well known in physics, to build Bessel-CNNs (B-CNNs) that are invariant to all the continuous set of possible rotation angles by design. |
Valentin Delchevalerie; Adrien Bibal; Beno�t Fr�nay; Alexandre Mayer; | |
2205 | Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Assuming free access to a source environment, we propose an unsupervised domain adaptation method to identify and acquire skills across dynamics. |
Jinxin Liu; Hao Shen; Donglin Wang; Yachen Kang; Qiangxing Tian; | |
2206 | GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models. |
Junhan Yang; Zheng Liu; Shitao Xiao; Chaozhuo Li; Defu Lian; Sanjay Agrawal; Amit Singh; Guangzhong Sun; Xing Xie; | code |
2207 | A Universal Law of Robustness Via Isoperimetry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A puzzling phenomenon in the current practice of deep learning is that models are trained with many more parameters than what this classical theory would suggest. We propose a theoretical explanation for this phenomenon. |
Sebastien Bubeck; Mark Sellke; | |
2208 | On Contrastive Representations of Stochastic Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose a unifying framework for learning contrastive representations of stochastic processes (CReSP) that does away with exact reconstruction. |
Emile Mathieu; Adam Foster; Yee Teh; | |
2209 | A Domain-Shrinking Based Bayesian Optimization Algorithm with Order-Optimal Regret Performance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a Gaussian process-based algorithm and establish its order-optimal regret performance (up to a poly-logarithmic factor). |
Sudeep Salgia; Sattar Vakili; Qing Zhao; | |
2210 | Scalars Are Universal: Equivariant Machine Learning, Structured Like Classical Physics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we show that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincaré groups, at any dimensionality $d$. |
Soledad Villar; David Hogg; Kate Storey-Fisher; Weichi Yao; Ben Blum-Smith; | |
2211 | Unsupervised Object-Level Representation Learning from Scene Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we introduce Object-level Representation Learning (ORL), a new self-supervised learning framework towards scene images. |
Jiahao Xie; Xiaohang Zhan; Ziwei Liu; Yew Ong; Chen Change Loy; | |
2212 | Do Transformers Really Perform Badly for Graph Representation? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model. |
Chengxuan Ying; Tianle Cai; Shengjie Luo; Shuxin Zheng; Guolin Ke; Di He; Yanming Shen; Tie-Yan Liu; | code |
2213 | Powerpropagation: A Sparsity Inducing Weight Reparameterisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inthis work, we introduce Powerpropagation, a new weight-parameterisation for neural networks that leads to inherently sparse models. |
Jonathan Schwarz; Siddhant Jayakumar; Razvan Pascanu; Peter Latham; Yee Teh; | |
2214 | Stronger NAS with Weaker Predictors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper reflects on a simple yet crucial question: if our final goal is to find the best architecture, do we really need to model the whole space well? |
Junru Wu; Xiyang Dai; Dongdong Chen; Yinpeng Chen; Mengchen Liu; Ye Yu; Zhangyang Wang; Zicheng Liu; Mei Chen; Lu Yuan; | code |
2215 | Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we introduce a simple and efficient “Convolutional Normalization” (ConvNorm) method that can fully exploit the convolutional structure in the Fourier domain and serve as a simple plug-and-play module to be conveniently incorporated into any ConvNets. |
Sheng Liu; Xiao Li; Yuexiang Zhai; Chong You; Zhihui Zhu; Carlos Fernandez-Granda; Qing Qu; | code |
2216 | Nearly-Tight and Oblivious Algorithms for Explainable Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of explainable clustering in the setting first formalized by Dasgupta, Frost, Moshkovitz, and Rashtchian (ICML 2020). |
Buddhima Gamlath; Xinrui Jia; Adam Polak; Ola Svensson; | |
2217 | Deep Networks Provably Classify Data on Curves Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study a model problem with such structure—a binary classification task that uses a deep fully-connected neural network to classify data drawn from two disjoint smooth curves on the unit sphere. |
Tingran Wang; Sam Buchanan; Dar Gilboa; John Wright; | |
2218 | COMBO: Conservative Offline Model-Based Policy Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that trains a value function using both the offline dataset and data generated using rollouts under the model while also additionally regularizing the value function on out-of-support state-action tuples generated via model rollouts. |
Tianhe Yu; Aviral Kumar; Rafael Rafailov; Aravind Rajeswaran; Sergey Levine; Chelsea Finn; | |
2219 | Time-series Generation By Contrastive Imitation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy, where the reinforcement signal is provided by a global (but stepwise-decomposable) energy model trained by contrastive estimation. |
Daniel Jarrett; Ioana Bica; Mihaela van der Schaar; | |
2220 | Differentially Private Sampling from Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We initiate an investigation of private sampling from distributions. |
Sofya Raskhodnikova; Satchit Sivakumar; Adam Smith; Marika Swanberg; | |
2221 | On The Expected Complexity of Maxout Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that this phenomenon also occurs in networks with maxout (multi-argument) activation functions and when considering the decision boundaries in classification tasks. |
Hanna Tseran; Guido F. Montufar; | |
2222 | Cross-view Geo-localization with Layer-to-Layer Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address the problem of cross-view geo-localization, which estimates the geospatial location of a street view image by matching it with a database of geo-tagged aerial images. |
Hongji Yang; Xiufan Lu; Yingying Zhu; | |
2223 | TAAC: Temporally Abstract Actor-Critic for Continuous Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present temporally abstract actor-critic (TAAC), a simple but effective off-policy RL algorithm that incorporates closed-loop temporal abstraction into the actor-critic framework. |
Haonan Yu; Wei Xu; Haichao Zhang; | code |
2224 | Learning Robust Hierarchical Patterns of Human Brain Across Many FMRI Studies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to reduce site-specific variance in the estimation of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data via a simple yet effective matrix factorization while preserving biologically relevant variations. |
Dushyant Sahoo; Christos Davatzikos; | |
2225 | Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study gradient descent-ascent learning dynamics with timescale separation in unconstrained continuous action zero-sum games where the minimizing player faces a nonconvex optimization problem and the maximizing player optimizes a Polyak-Lojasiewicz (PL) or strongly-concave (SC) objective. |
Tanner Fiez; Lillian Ratliff; Eric Mazumdar; Evan Faulkner; Adhyyan Narang; | |
2226 | Bandit Quickest Changepoint Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We derive an information-theoretic lower bound on the detection delay for a general class of finitely parameterized probability distributions. |
Aditya Gopalan; Braghadeesh Lakshminarayanan; Venkatesh Saligrama; | |
2227 | Can Multi-label Classification Networks Know What They Don’t Know? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose JointEnergy, a simple and effective method, which estimates the OOD indicator scores by aggregating label-wise energy scores from multiple labels. |
Haoran Wang; Weitang Liu; Alex Bocchieri; Sharon Li; | |
2228 | Balanced Chamfer Distance As A Comprehensive Metric for Point Cloud Completion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these problems, we propose a new similarity measure named Density-aware Chamfer Distance (DCD). |
Tong Wu; Liang Pan; Junzhe Zhang; Tai WANG; Ziwei Liu; Dahua Lin; | code |
2229 | Optimality of Zeroth Order Gradient Ascent for Nonlinear Bandit Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work considers a large family of bandit problems where the unknown underlying reward function is non-concave, including the low-rank generalized linear bandit problems and two-layer neural network with polynomial activation bandit problem. |
Baihe Huang; Kaixuan Huang; Sham Kakade; Jason D. Lee; Qi Lei; Runzhe Wang; Jiaqi Yang; | |
2230 | On Optimal Interpolation in Linear Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we ask the question of what is the optimal way to interpolate in linear regression using functions that are linear in the response variable (as the case for the Bayes optimal estimator in ridge regression) and depend on the data, the population covariance of the data, the signal-to-noise ratio and the covariance of the prior for the signal, but do not depend on the value of the signal itself nor the noise vector in the training data. |
Eduard Oravkin; Patrick Rebeschini; | |
2231 | Differentiable Optimization of Generalized Nondecomposable Functions Using Linear Programs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework which makes it feasible to directly train deep neural networks with respect to popular families of task-specific non-decomposable performance measures such as AUC, multi-class AUC, $F$-measure and others. |
Zihang Meng; Lopamudra Mukherjee; Yichao Wu; Vikas Singh; Sathya Narayanan Ravi; | |
2232 | Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning. |
Jianhao Wang; Zhizhou Ren; Beining Han; Jianing Ye; Chongjie Zhang; | |
2233 | Margin-Independent Online Multiclass Learning Via Convex Geometry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of multi-class classification, where a stream of adversarially chosen queries arrive and must be assigned a label online. |
Guru Guruganesh; Allen Liu; Jon Schneider; Joshua Wang; | |
2234 | STEP: Out-of-Distribution Detection in The Presence of Limited In-Distribution Labeled Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study a setting called semi-supervised OOD detection. |
Zhi Zhou; Lan-Zhe Guo; Zhanzhan Cheng; Yu-Feng Li; Shiliang Pu; | |
2235 | Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively throughinteractions with a server from whom we need privacy. |
Antonious Girgis; Deepesh Data; Suhas Diggavi; | |
2236 | Gradient-based Editing of Memory Examples for Online Task-free Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose Gradient based Memory EDiting (GMED), a framework for editing stored examples in continuous input space via gradient updates, in order to create more "challenging" examples for replay. |
Xisen Jin; Arka Sadhu; Junyi Du; Xiang Ren; | |
2237 | Tailoring: Encoding Inductive Biases By Optimizing Unsupervised Objectives at Prediction Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we address both problems: first, we take inspiration from transductive learning and note that after receiving an input but before making a prediction, we can fine-tune our networks on any unsupervised loss. We call this process tailoring, because we customize the model to each input to ensure our prediction satisfies the inductive bias. |
Ferran Alet; Maria Bauza; Kenji Kawaguchi; Nurullah Giray Kuru; Tom�s Lozano-P�rez; Leslie Kaelbling; | |
2238 | Implicit Bias of SGD for Diagonal Linear Networks: A Provable Benefit of Stochasticity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the dynamics of stochastic gradient descent over diagonal linear networks through its continuous time version, namely stochastic gradient flow. |
Scott Pesme; Loucas Pillaud-Vivien; Nicolas Flammarion; | |
2239 | Iterative Teacher-Aware Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a gradient optimization based teacher-aware learner who can incorporate teacher’s cooperative intention into the likelihood function and learn provably faster compared with the naive learning algorithms used in previous machine teaching works. |
Luyao Yuan; Dongruo Zhou; Junhong Shen; Jingdong Gao; Jeffrey Chen; Quanquan Gu; Ying Nian Wu; Song-Chun Zhu; | |
2240 | Clockwork Variational Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the Clockwork VAE (CW-VAE), a video prediction model that leverages a hierarchy of latent sequences, where higher levels tick at slower intervals. |
Vaibhav Saxena; Jimmy Ba; Danijar Hafner; | |
2241 | How Does It Sound? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore this problem and propose a novel system, called `RhythmicNet’, which takes as an input a video which includes human movements and generates a soundtrack for it. |
Kun Su; Xiulong Liu; Eli Shlizerman; | |
2242 | Stabilizing Dynamical Systems Via Policy Gradient Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a simple, model-free algorithm for stabilizing fully observed dynamical systems. |
Juan Perdomo; Jack Umenberger; Max Simchowitz; | |
2243 | Language Models Enable Zero-shot Prediction of The Effects of Mutations on Protein Function Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that using only zero-shot inference, without any supervision from experimental data or additional training, protein language models capture the functional effects of sequence variation, performing at state-of-the-art. |
Joshua Meier; Roshan Rao; Robert Verkuil; Jason Liu; Tom Sercu; Alex Rives; | |
2244 | Deep Reinforcement Learning at The Edge of The Statistical Precipice Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that reliable evaluation in the few run deep RL regime cannot ignore the uncertainty in results without running the risk of slowing down progress in the field. |
Rishabh Agarwal; Max Schwarzer; Pablo Samuel Castro; Aaron C. Courville; Marc Bellemare; | |
2245 | DRONE: Data-aware Low-rank Compression for Large NLP Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we observe that the learned representation of each layer lies in a low-dimensional space. |
Pei-Hung Chen; Hsiang-Fu Yu; Inderjit Dhillon; Cho-Jui Hsieh; | |
2246 | DSelect-k: Differentiable Selection in The Mixture of Experts with Applications to Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop DSelect-k: a continuously differentiable and sparse gate for MoE, based on a novel binary encoding formulation. |
Hussein Hazimeh; Zhe Zhao; Aakanksha Chowdhery; Maheswaran Sathiamoorthy; Yihua Chen; Rahul Mazumder; Lichan Hong; Ed Chi; | |
2247 | Mind The Gap: Assessing Temporal Generalization in Neural Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, given the compilation of ever-larger language modelling datasets, combined with the growing list of language-model-based NLP applications that require up-to-date factual knowledge about the world, we argue that now is the right time to rethink the static way in which we currently train and evaluate our language models, and develop adaptive language models that can remain up-to-date with respect to our ever-changing and non-stationary world. |
Angeliki Lazaridou; Adhi Kuncoro; Elena Gribovskaya; Devang Agrawal; Adam Liska; Tayfun Terzi; Mai Gimenez; Cyprien de Masson d'Autume; Tomas Kocisky; Sebastian Ruder; Dani Yogatama; Kris Cao; Susannah Young; Phil Blunsom; | |
2248 | Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, focusing our attention on stochastic gradient descent (SGD), our main contribution is to link compressibility to two recently established properties of SGD: (i) as the network size goes to infinity, the system can converge to a mean-field limit, where the network weights behave independently [DBDF?20], (ii) for a large step-size/batch-size ratio, the SGD iterates can converge to a heavy-tailed stationary distribution [HM20, G?Z21]. |
Melih Barsbey; Seyedmilad Sefidgaran; Murat A. Erdogdu; Ga�l Richard; Umut Simsekli; | |
2249 | Targeted Neural Dynamical Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce Targeted Neural Dynamical Modeling (TNDM), a nonlinear state-space model that jointly models the neural activity and external behavioural variables. |
Cole Hurwitz; Akash Srivastava; Kai Xu; Justin Jude; Matthew Perich; Lee Miller; Matthias Hennig; | |
2250 | Exploiting The Intrinsic Neighborhood Structure for Source-free Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. |
Shiqi Yang; yaxing wang; Joost van de Weijer; Luis Herranz; Shangling Jui; | code |
2251 | Learning with Noisy Correspondence for Cross-modal Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this new problem, we propose a novel method for learning with noisy correspondence, named Noisy Correspondence Rectifier (NCR). |
Zhenyu Huang; Guocheng Niu; Xiao Liu; Wenbiao Ding; Xinyan Xiao; Hua Wu; Xi Peng; | |
2252 | Offline Reinforcement Learning with Reverse Model-based Imagination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To encourage more conservatism, we propose a novel model-based offline RL framework, called Reverse Offline Model-based Imagination (ROMI). |
Jianhao Wang; Wenzhe Li; Haozhe Jiang; Guangxiang Zhu; Siyuan Li; Chongjie Zhang; | |
2253 | Parameter Prediction for Unseen Deep Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a large-scale dataset of diverse computational graphs of neural architectures – DeepNets-1M – and use it to explore parameter prediction on CIFAR-10 and ImageNet. |
Boris Knyazev; Michal Drozdzal; Graham W. Taylor; Adriana Romero; | |
2254 | FMMformer: Efficient and Flexible Transformer Via Decomposed Near-field and Far-field Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose FMMformers, a class of efficient and flexible transformers inspired by the celebrated fast multipole method (FMM) for accelerating interacting particle simulation. |
Tan Nguyen; Vai Suliafu; Stanley Osher; Long Chen; Bao Wang; | |
2255 | Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new framework — Square Root Principal Component Pursuit — for low-rank matrix recovery from observations corrupted with noise and outliers. |
Junhui Zhang; Jingkai Yan; John Wright; | |
2256 | Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm. |
Zhaocheng Zhu; Zuobai Zhang; Louis-Pascal Xhonneux; Jian Tang; | |
2257 | CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object. |
Leo Lebrat; Rodrigo Santa Cruz; Frederic de Gournay; Darren Fu; Pierrick Bourgeat; Jurgen Fripp; Clinton Fookes; Olivier Salvado; | |
2258 | Bridging The Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By relaxing this assumption, we develop two PAC-Bayesian bounds tailored for the few-shot learning setting and show that two existing meta-learning algorithms (MAML and Reptile) can be derived from our bounds, thereby bridging the gap between practice and PAC-Bayesian theories. |
Nan Ding; Xi Chen; Tomer Levinboim; Sebastian Goodman; Radu Soricut; | |
2259 | SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose SLOE, a fast and straightforward approach to estimate the signal strength in logistic regression. |
Steve Yadlowsky; Taedong Yun; Cory McLean; Alexander D'Amour; | |
2260 | ELLA: Exploration Through Learned Language Abstraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce ELLA: Exploration through Learned Language Abstraction, a reward shaping approach geared towards boosting sample efficiency in sparse reward environments by correlating high-level instructions with simpler low-level constituents. |
Suvir Mirchandani; Siddharth Karamcheti; Dorsa Sadigh; | |
2261 | Learning Distilled Collaboration Graph for Multi-Agent Perception Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote better performance-bandwidth trade-off for multi-agent perception, we propose a novel distilled collaboration graph (DiscoGraph) to model trainable, pose-aware, and adaptive collaboration among agents. |
Yiming Li; Shunli Ren; Pengxiang Wu; Siheng Chen; Chen Feng; Wenjun Zhang; | code |
2262 | Federated-EM with Heterogeneity Mitigation and Variance Reduction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces FedEM, which is the first extension of the EM algorithm to the federated learning context. |
Aymeric Dieuleveut; Gersende Fort; Eric Moulines; Genevi�ve Robin; | |
2263 | On The Role of Optimization in Double Descent: A Least Squares Study Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we add to the growing body of work in this space, providing a careful study of learning dynamics as a function of model size for the least squares scenario. |
Ilja Kuzborskij; Csaba Szepesvari; Omar Rivasplata; Amal Rannen-Triki; Razvan Pascanu; | |
2264 | Neural Architecture Dilation for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: From the neural architecture perspective, this paper aims to improve the adversarial robustness of the backbone CNNs that have a satisfactory accuracy. |
Yanxi Li; Zhaohui Yang; Yunhe Wang; Chang Xu; | |
2265 | Clustering Effect of Adversarial Robust Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we interpret adversarial robustness from the perspective of linear components, and find that there exist some statistical properties for comprehensively robust models. |
Yang Bai; Xin Yan; Yong Jiang; Shu-Tao Xia; Yisen Wang; | |
2266 | On The Cryptographic Hardness of Learning Single Periodic Neurons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show a simple reduction which demonstrates the cryptographic hardness of learning a single periodic neuron over isotropic Gaussian distributions in the presence of noise. |
Min Jae Song; Ilias Zadik; Joan Bruna; | |
2267 | PCA Initialization for Approximate Message Passing in Rotationally Invariant Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we combine the two methods, and propose to initialize AMP with PCA. |
Marco Mondelli; Ramji Venkataramanan; | |
2268 | Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a dynamic barrier gradient descent algorithm which provides a unified solution of both constrained and lexicographic optimization. |
Chengyue Gong; Xingchao Liu; Qiang Liu; | |
2269 | Corruption Robust Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve this drawback, we propose a new algorithm which is provably correct without any assumptions on the presence of corruptions. |
Yifang Chen; Simon S. Du; Kevin G. Jamieson; | |
2270 | Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the metadata-based multi-task bandit problem, where the agent needs to solve a large number of related multi-armed bandit tasks and can leverage some task-specific features (i.e., metadata) to share knowledge across tasks. |
Runzhe Wan; Lin Ge; Rui Song; | |
2271 | Program Synthesis Guided Reinforcement Learning for Partially Observed Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new approach, model predictive program synthesis (MPPS), that uses program synthesis to automatically generate the guiding programs. |
Yichen Yang; Jeevana Priya Inala; Osbert Bastani; Yewen Pu; Armando Solar-Lezama; Martin Rinard; | |
2272 | Robust Allocations with Diversity Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of allocating divisible items among multiple agents, and consider the setting where any agent is allowed to introduce {\emph diversity constraints} on the items they are allocated. |
Zeyu Shen; Lodewijk Gelauff; Ashish Goel; Aleksandra Korolova; Kamesh Munagala; | |
2273 | Activation Sharing with Asymmetric Paths Solves Weight Transport Problem Without Bidirectional Connection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an Activation Sharing algorithm that removes the need for bidirectional connections between the two types of neurons. |
Sunghyeon Woo; Jeongwoo Park; Jiwoo Hong; Dongsuk Jeon; | |
2274 | BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above issues, we propose BlendGAN for arbitrary stylized face generation by leveraging a flexible blending strategy and a generic artistic dataset. |
Mingcong Liu; Qiang Li; Zekui Qin; Guoxin Zhang; Pengfei Wan; Wen Zheng; | |
2275 | Differentially Private Model Personalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide algorithms that exploit popular non-private approaches in this domain like the Almost-No-Inner-Loop (ANIL) method, and give strong user-level privacy guarantees for our general approach. |
Prateek Jain; John Rush; Adam Smith; Shuang Song; Abhradeep Guha Thakurta; | |
2276 | Rates of Estimation of Optimal Transport Maps Using Plug-in Estimators Via Barycentric Projections Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a comprehensive analysis of the rates of convergences for general plug-in estimators defined via barycentric projections. |
NABARUN DEB; Promit Ghosal; Bodhisattva Sen; | |
2277 | Robust Generalization Despite Distribution Shift Via Minimum Discriminating Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribution. |
Tobias Sutter; Andreas Krause; Daniel Kuhn; | |
2278 | Soft Calibration Objectives for Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose differentiable losses to improve calibration based on a soft (continuous) version of the binning operation underlying popular calibration-error estimators. |
Archit Karandikar; Nicholas Cain; Dustin Tran; Balaji Lakshminarayanan; Jonathon Shlens; Michael C. Mozer; Rebecca Roelofs; | |
2279 | Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach towards estimating epistemically uncertain neural ODEs, avoiding the numerical integration bottleneck. |
Lenart Treven; Philippe Wenk; Florian Dorfler; Andreas Krause; | |
2280 | Shaping Embodied Agent Behavior with Activity-context Priors from Egocentric Video Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an approach to discover activity-context priors from in-the-wild egocentric video captured with human worn cameras. |
Tushar Nagarajan; Kristen Grauman; | |
2281 | Adjusting for Autocorrelated Errors in Neural Networks for Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, in order to adjust for autocorrelated errors, we propose to learn the autocorrelation coefficient jointly with the model parameters. |
Fan-Keng Sun; Chris Lang; Duane Boning; | |
2282 | A Geometric Analysis of Neural Collapse with Unconstrained Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide the first global optimization landscape analysis of Neural Collapse — an intriguing empirical phenomenon that arises in the last-layer classifiers and features of neural networks during the terminal phase of training. |
Zhihui Zhu; Tianyu Ding; Jinxin Zhou; Xiao Li; Chong You; Jeremias Sulam; Qing Qu; | code |
2283 | NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in The Wild Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: But because the vast majority of real-world scenes are composed of well-defined surfaces, we introduce a {\em surface} analog of such implicit models called Neural Reflectance Surfaces (NeRS). |
Jason Zhang; Gengshan Yang; Shubham Tulsiani; Deva Ramanan; | |
2284 | Unleashing The Power of Contrastive Self-Supervised Visual Models Via Contrast-Regularized Fine-Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate whether applying contrastive learning to fine-tuning would bring further benefits, and analytically find that optimizing the contrastive loss benefits both discriminative representation learning and model optimization during fine-tuning. |
Yifan Zhang; Bryan Hooi; Dapeng Hu; Jian Liang; Jiashi Feng; | |
2285 | Discovery of Options Via Meta-Learned Subgoals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel meta-gradient approach for discovering useful options in multi-task RL environments. |
Vivek Veeriah; Tom Zahavy; Matteo Hessel; Zhongwen Xu; Junhyuk Oh; Iurii Kemaev; Hado P. van Hasselt; David Silver; Satinder Singh; | |
2286 | Near-Optimal Lower Bounds For Convex Optimization For All Orders of Smoothness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the complexity of optimizing highly smooth convex functions. |
Ankit Garg; Robin Kothari; Praneeth Netrapalli; Suhail Sherif; | |
2287 | Topology-Imbalance Learning for Semi-Supervised Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we first probe the previously unknown topology-imbalance issue, including its characteristics, causes, and threats to semisupervised node classification learning. We then provide a unified view to jointly analyzing the quantity- and topology- imbalance issues by considering the node influence shift phenomenon with the Label Propagation algorithm. |
Deli Chen; Yankai Lin; Guangxiang Zhao; Xuancheng Ren; Peng Li; Jie Zhou; Xu Sun; | |
2288 | Gradient Inversion with Generative Image Prior Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By exploiting a generative model pretrained on the data distribution, we demonstrate that data privacy can be easily breached. |
Jiwnoo Jeon; jaechang Kim; Kangwook Lee; Sewoong Oh; Jungseul Ok; | |
2289 | Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop $\beta$-CROWN, a new bound propagation based method that can fully encode neuron splits via optimizable parameters $\beta$ constructed from either primal or dual space. |
Shiqi Wang; Huan Zhang; Kaidi Xu; Xue Lin; Suman Jana; Cho-Jui Hsieh; J. Zico Kolter; | |
2290 | Autobahn: Automorphism-based Graph Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. |
Erik Thiede; Wenda Zhou; Risi Kondor; | |
2291 | Data Augmentation Can Improve Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. |
Sylvestre-Alvise Rebuffi; Sven Gowal; Dan Andrei Calian; Florian Stimberg; Olivia Wiles; Timothy A. Mann; | |
2292 | Deep Explicit Duration Switching Models for Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Recurrent Explicit Duration Switching Dynamical System (RED-SDS), a flexible model that is capable of identifying both state- and time-dependent switching dynamics. |
Abdul Fatir Ansari; Konstantinos Benidis; Richard Kurle; Ali Caner Turkmen; Harold Soh; Alexander J. Smola; Bernie Wang; Tim Januschowski; | |
2293 | Shared Independent Component Analysis for Multi-Subject Neuroimaging Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Shared Independent Component Analysis (ShICA) that models eachview as a linear transform of shared independent components contaminated by additive Gaussian noise. |
Hugo Richard; Pierre Ablin; Bertrand Thirion; Alexandre Gramfort; Aapo Hyvarinen; | |
2294 | Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the novel task of jointly reconstructing the 3D shape, texture, and motion of an object from a single motion-blurred image. |
Denys Rozumnyi; Martin R. Oswald; Vittorio Ferrari; Marc Pollefeys; | |
2295 | Batched Thompson Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike these algorithms, the batched Thompson sampling algorithm we propose is an anytime policy, i.e. it operates without the knowledge of the time horizon $T$, and as such it is the only anytime algorithm that achieves optimal regret with $O(\log\log(T))$ expected batch complexity. |
Cem Kalkanli; Ayfer Ozgur; | |
2296 | Delayed Gradient Averaging: Tolerate The Communication Latency for Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To over comethe problem, we propose \textbf{D}elayed \textbf{G}radient \textbf{A}veraging (DGA), which delays the averaging step to improve efficiency and allows local computation in parallel tocommunication. |
Ligeng Zhu; Hongzhou Lin; Yao Lu; Yujun Lin; Song Han; | |
2297 | Focal Attention for Long-Range Interactions in Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present focal attention, a new attention mechanism that incorporates both fine-grained local and coarse-grained global interactions. |
Jianwei Yang; Chunyuan Li; Pengchuan Zhang; Xiyang Dai; Bin Xiao; Lu Yuan; Jianfeng Gao; | |
2298 | Scalable and Stable Surrogates for Flexible Classifiers with Fairness Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze an easy-to-use and robust way of imposing fairness constraints when training, and through this framework prove that some prior fairness surrogates exhibit degeneracies for non-convex models. |
Henry Bendekgey; Erik Sudderth; | |
2299 | Residual Pathway Priors for Soft Equivariance Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Residual Pathway Priors (RPPs) as a method for converting hard architectural constraints into soft priors, guiding models towards structured solutions while retaining the ability to capture additional complexity. |
Marc Finzi; Gregory Benton; Andrew G. Wilson; | |
2300 | Optimal Algorithms for Stochastic Contextual Preference Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following this, we propose a matching upper bound algorithm justifying the tightness of our results. |
Aadirupa Saha; | |
2301 | Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides a non-asymptotic analysis of linear stochastic approximation (LSA) algorithms with fixed stepsize. |
Alain Durmus; Eric Moulines; Alexey Naumov; Sergey Samsonov; Kevin Scaman; Hoi-To Wai; | |
2302 | Learning Large Neighborhood Search Policy for Integer Programming Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a deep reinforcement learning (RL) method to learn large neighborhood search (LNS) policy for integer programming (IP). |
Yaoxin Wu; Wen Song; Zhiguang Cao; Jie Zhang; | |
2303 | Dynamic Trace Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a practical algorithm for solving this problem and prove that, in a natural setting, its complexity is quadratically better than the standard solution of repeatedly applying Hutchinson’s stochastic trace estimator. |
Prathamesh Dharangutte; Christopher Musco; | |
2304 | Provable Representation Learning for Imitation with Contrastive Fourier Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider using offline experience datasets — potentially far from the target distribution — to learn low-dimensional state representations that provably accelerate the sample-efficiency of downstream imitation learning. |
Ofir Nachum; Mengjiao Yang; | |
2305 | MICo: Improved Representations Via Sampling-based State Similarity for Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an effective means of shaping the learnt representations of deep reinforcement learning agents. |
Pablo Samuel Castro; Tyler Kastner; Prakash Panangaden; Mark Rowland; | |
2306 | Counterfactual Explanations in Sequential Decision Making Under Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we initiate the development of methods to find counterfactual explanations for decision making processes in which multiple, dependent actions are taken sequentially over time. |
Stratis Tsirtsis; Abir De; Manuel Rodriguez; | |
2307 | Streaming Linear System Identification with Reverse Experience Replay Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel streaming algorithm, SGD with Reverse Experience Replay (SGD-RER), that is inspired by the experience replay (ER) technique popular in the RL literature. |
Suhas Kowshik; Dheeraj Nagaraj; Prateek Jain; Praneeth Netrapalli; | |
2308 | SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup: it trains on convex combinations of samples along the direction of adversarial perturbation for each input. |
Jongheon Jeong; Sejun Park; Minkyu Kim; Heung-Chang Lee; Do-Guk Kim; Jinwoo Shin; | |
2309 | Action-guided 3D Human Motion Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on developing models to predict future human motion from past observed video frames. |
Jiangxin Sun; Zihang Lin; Xintong Han; Jian-Fang Hu; Jia Xu; Wei-Shi Zheng; | |
2310 | Meta-Learning The Search Distribution of Black-Box Random Search Based Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, as we demonstrate in this work, their efficiency in different query budget regimes depends on manual design and heuristic tuning of the underlying proposal distributions. We study how this issue can be addressed by adapting the proposal distribution online based on the information obtained during the attack. |
Maksym Yatsura; Jan Metzen; Matthias Hein; | |
2311 | Validating The Lottery Ticket Hypothesis with Inertial Manifold Theory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging dynamical systems theory and inertial manifold theory, this work theoretically verifies the validity of the LTH. |
Zeru Zhang; Jiayin Jin; Zijie Zhang; Yang Zhou; Xin Zhao; Jiaxiang Ren; Ji Liu; Lingfei Wu; Ruoming Jin; Dejing Dou; | |
2312 | Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct the first empirical study to quantify the impact of software implementation on the fairness and its variance of DL systems. |
Shangshu Qian; Hung Pham; Thibaud Lutellier; Zeou Hu; Jungwon Kim; Lin Tan; Yaoliang Yu; Jiahao Chen; Sameena Shah; | |
2313 | Rectangular Flows for Manifold Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we propose two methods to tractably calculate the gradient of this term with respect to the parameters of the model, relying on careful use of automatic differentiation and techniques from numerical linear algebra. |
Anthony L. Caterini; Gabriel Loaiza-Ganem; Geoff Pleiss; John P. Cunningham; | code |
2314 | On The Generative Utility of Cyclic Conditionals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the theory, we propose a novel generative modeling framework CyGen that only uses the two cyclic conditional models. |
Chang Liu; Haoyue Tang; Tao Qin; Jintao Wang; Tie-Yan Liu; | |
2315 | Structural Credit Assignment in Neural Networks Using Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we revisit this approach and investigate if we can leverage other reinforcement learning approaches to improve learning. |
Dhawal Gupta; Gabor Mihucz; Matthew Schlegel; James Kostas; Philip S. Thomas; Martha White; | |
2316 | A Near-Optimal Algorithm for Stochastic Bilevel Optimization Via Double-Momentum Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new algorithm — the \underline{S}ingle-timescale Do\underline{u}ble-momentum \underline{St}ochastic \underline{A}pprox\underline{i}matio\underline{n} (SUSTAIN) — for tackling stochastic unconstrained bilevel optimization problems. |
Prashant Khanduri; Siliang Zeng; Mingyi Hong; Hoi-To Wai; Zhaoran Wang; Zhuoran Yang; | |
2317 | Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose to use Jensen-Shannon divergence as a noise-robust loss function and show that it interestingly interpolate between CE and MAE with a controllable mixing parameter. |
Erik Englesson; Hossein Azizpour; | |
2318 | Continual Learning Via Local Module Composition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce local module composition (LMC), an approach to modular CL where each module is provided a local structural component that estimates a module’s relevance to the input. |
Oleksiy Ostapenko; Pau Rodriguez; Massimo Caccia; Laurent Charlin; | code |
2319 | Model-Based Episodic Memory Induces Dynamic Hybrid Controls Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new model-based episodic memory of trajectories addressing current limitations of episodic control. |
Hung Le; Thommen Karimpanal George; Majid Abdolshah; Truyen Tran; Svetha Venkatesh; | |
2320 | FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop two new algorithms, called, FedDR and asyncFedDR, for solving a fundamental nonconvex composite optimization problem in federated learning. |
Quoc Tran Dinh; Nhan Pham; Dzung Phan; Lam Nguyen; | |
2321 | Adversarial Examples Make Strong Poisons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. |
Liam Fowl; Micah Goldblum; Ping-yeh Chiang; Jonas Geiping; Wojciech Czaja; Tom Goldstein; | |
2322 | Coresets for Decision Trees of Signals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide the first algorithm that outputs such a $(k,\varepsilon)$-coreset for \emph{every} such matrix $D$. |
Ibrahim Jubran; Ernesto Evgeniy Sanches Shayda; Ilan Newman; Dan Feldman; | |
2323 | Local Plasticity Rules Can Learn Deep Representations Using Self-supervised Contrastive Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a learning rule that takes inspiration from neuroscience and recent advances in self-supervised deep learning. |
Bernd Illing; Jean Ventura; Guillaume Bellec; Wulfram Gerstner; | |
2324 | MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose MobTCast, a Transformer-based context-aware network for mobility prediction. |
Hao Xue; Flora Salim; Yongli Ren; Nuria Oliver; | |
2325 | Early Convolutions Help Transformers See Better Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and training schedule length. In comparison, modern convolutional neural networks are easier to optimize. Why is this the case? In this work, we conjecture that the issue lies with the patchify stem of ViT models, which is implemented by a stride-p p×p convolution (p = 16 by default) applied to the input image. |
Tete Xiao; Piotr Dollar; Mannat Singh; Eric Mintun; Trevor Darrell; Ross Girshick; | |
2326 | Error Compensated Distributed SGD Can Be Accelerated Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we focus on developing efficient distributed methods that can work for any compressor satisfying a certain contraction property, which includes both unbiased (after appropriate scaling) and biased compressors such as RandK and TopK. |
Xun Qian; Peter Richtarik; Tong Zhang; | |
2327 | InfoGCL: Information-Aware Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to fill this gap by studying how graph information is transformed and transferred during the contrastive learning process, and proposing an information-aware graph contrastive learning framework called InfoGCL. |
Dongkuan Xu; Wei Cheng; Dongsheng Luo; Haifeng Chen; Xiang Zhang; | |
2328 | Meta-Learning for Relative Density-Ratio Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a meta-learning method for relative DRE, which estimates the relative density-ratio from a few instances by using knowledge in related datasets. |
Atsutoshi Kumagai; Tomoharu Iwata; Yasuhiro Fujiwara; | |
2329 | Overcoming The Curse of Dimensionality with Laplacian Regularization in Semi-supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design a new class of algorithms overcoming this issue, unveiling a large body of spectral filtering methods. |
Vivien Cabannes; Loucas Pillaud-Vivien; Francis Bach; Alessandro Rudi; | |
2330 | Unlabeled Principal Component Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce robust principal component analysis from a data matrix in which the entries of its columns have been corrupted by permutations, termed Unlabeled Principal Component Analysis (UPCA). |
Yunzhen Yao; Liangzu Peng; Manolis Tsakiris; | |
2331 | Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce causal, Bayesian acquisition functions grounded in information theory that bias data acquisition towards regions with overlapping support to maximize sample efficiency for learning personalized treatment effects. |
Andrew Jesson; Panagiotis Tigas; Joost van Amersfoort; Andreas Kirsch; Uri Shalit; Yarin Gal; | |
2332 | Scalable Rule-Based Representation Learning for Interpretable Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To obtain both good scalability and interpretability, we propose a new classifier, named Rule-based Representation Learner (RRL), that automatically learns interpretable non-fuzzy rules for data representation and classification. |
Zhuo Wang; Wei Zhang; Ning Liu; Jianyong Wang; | code |
2333 | Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the use of unlabeled in-the-wild data to bridge the non co-occurrence caused by the missing base classes during the training of additional novel classes. |
NA DONG; Yongqiang Zhang; Mingli Ding; Gim Hee Lee; | |
2334 | A Regression Approach to Learning-Augmented Online Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce this approach in this paper, and explore it in the context of a general online search framework that captures classic problems like (generalized) ski rental, bin packing, minimum makespan scheduling, etc. |
Keerti Anand; Rong Ge; Amit Kumar; Debmalya Panigrahi; |