Paper Digest: NeurIPS 2020 Highlights
Download NIPS-2020-Paper-Digests.pdf– Highlights of all 1,899 NeurIPS-2020 papers. Readers can choose to read all these highlights on our console as well, which allows users to filter out papers using keywords and find related papers, patents, etc. In addition, we identified a large number of papers that have published their code and data. Here is the (code/data download page).
The Conference on Neural Information Processing Systems (NIPS) is one of the top machine learning conferences in the world. In 2020, it is to be held online due to coivd-19 pandemic.
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.
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 2020 Highlights
| Paper | Author(s) | Code | |
|---|---|---|---|
| 1 | A Graph Similarity For Deep Learning Highlight: We adopt kernel distance and propose transform-sum-cat as an alternative to aggregate-transform to reflect the continuous similarity between the node neighborhoods in the neighborhood aggregation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Seongmin Ok; | |
| 2 | An Unsupervised Information-Theoretic Perceptual Quality Metric Highlight: We combine recent advances in information-theoretic objective functions with a computational architecture informed by the physiology of the human visual system and unsupervised training on pairs of video frames, yielding our Perceptual Information Metric (PIM). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sangnie Bhardwaj; Ian Fischer; Johannes Ball�; Troy Chinen; | |
| 3 | Self-Supervised MultiModal Versatile Networks Highlight: In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jean-Baptiste Alayrac; Adria Recasens; Rosalia Schneider; Relja Arandjelovic; Jason Ramapuram; Jeffrey De Fauw; Lucas Smaira; Sander Dieleman; Andrew Zisserman; | |
| 4 | Benchmarking Deep Inverse Models Over Time, And The Neural-Adjoint Method Highlight: We consider the task of solving generic inverse problems, where one wishes to determine the hidden parameters of a natural system that will give rise to a particular set of measurements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simiao Ren; Willie Padilla; Jordan Malof; | |
| 5 | Off-Policy Evaluation And Learning For External Validity Under A Covariate Shift Highlight: In this paper, we derive the efficiency bound of OPE under a covariate shift. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Masatoshi Uehara; Masahiro Kato; Shota Yasui; | |
| 6 | Neural Methods For Point-wise Dependency Estimation Highlight: In this work, instead of estimating the expected dependency, we focus on estimating point-wise dependency (PD), which quantitatively measures how likely two outcomes co-occur. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yao-Hung Hubert Tsai; Han Zhao; Makoto Yamada; Louis-Philippe Morency; Russ R. Salakhutdinov; | |
| 7 | Fast And Flexible Temporal Point Processes With Triangular Maps Highlight: By exploiting the recent developments in the field of normalizing flows, we design TriTPP – a new class of non-recurrent TPP models, where both sampling and likelihood computation can be done in parallel. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Oleksandr Shchur; Nicholas Gao; Marin Bilo�; Stephan G�nnemann; | |
| 8 | Backpropagating Linearly Improves Transferability Of Adversarial Examples Highlight: In this paper, we study the transferability of such examples, which lays the foundation of many black-box attacks on DNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yiwen Guo; Qizhang Li; Hao Chen; | code |
| 9 | PyGlove: Symbolic Programming For Automated Machine Learning Highlight: In this paper, we introduce a new way of programming AutoML based on symbolic programming. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daiyi Peng; Xuanyi Dong; Esteban Real; Mingxing Tan; Yifeng Lu; Gabriel Bender; Hanxiao Liu; Adam Kraft; Chen Liang; Quoc Le; | |
| 10 | Fourier Sparse Leverage Scores And Approximate Kernel Learning Highlight: We prove new explicit upper bounds on the leverage scores of Fourier sparse functions under both the Gaussian and Laplace measures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tamas Erdelyi; Cameron Musco; Christopher Musco; | |
| 11 | Improved Algorithms For Online Submodular Maximization Via First-order Regret Bounds Highlight: In this work, we give a general approach for improving regret bounds in online submodular maximization by exploiting “first-order” regret bounds for online linear optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicholas Harvey; Christopher Liaw; Tasuku Soma; | |
| 12 | Synbols: Probing Learning Algorithms With Synthetic Datasets Highlight: In this sense, we introduce Synbols — Synthetic Symbols — a tool for rapidly generating new datasets with a rich composition of latent features rendered in low resolution images. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexandre Lacoste; Pau Rodr�guez L�pez; Frederic Branchaud-Charron; Parmida Atighehchian; Massimo Caccia; Issam Hadj Laradji; Alexandre Drouin; Matthew Craddock; Laurent Charlin; David V�zquez; | |
| 13 | Adversarially Robust Streaming Algorithms Via Differential Privacy Highlight: We establish a connection between adversarial robustness of streaming algorithms and the notion of differential privacy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Avinatan Hasidim; Haim Kaplan; Yishay Mansour; Yossi Matias; Uri Stemmer; | |
| 14 | Trading Personalization For Accuracy: Data Debugging In Collaborative Filtering Highlight: In this paper, we propose a data debugging framework to identify overly personalized ratings whose existence degrades the performance of a given collaborative filtering model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Long Chen; Yuan Yao; Feng Xu; Miao Xu; Hanghang Tong; | |
| 15 | Cascaded Text Generation With Markov Transformers Highlight: This work proposes an autoregressive model with sub-linear parallel time generation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuntian Deng; Alexander Rush; | |
| 16 | Improving Local Identifiability In Probabilistic Box Embeddings Highlight: In this work we model the box parameters with min and max Gumbel distributions, which were chosen such that the space is still closed under the operation of intersection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shib Dasgupta; Michael Boratko; Dongxu Zhang; Luke Vilnis; Xiang Li; Andrew McCallum; | |
| 17 | Permute-and-Flip: A New Mechanism For Differentially Private Selection Highlight: In this work, we propose a new mechanism for this task based on a careful analysis of the privacy constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ryan McKenna; Daniel R. Sheldon; | |
| 18 | Deep Reconstruction Of Strange Attractors From Time Series Highlight: Inspired by classical analysis techniques for partial observations of chaotic attractors, we introduce a general embedding technique for univariate and multivariate time series, consisting of an autoencoder trained with a novel latent-space loss function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
William Gilpin; | |
| 19 | Reciprocal Adversarial Learning Via Characteristic Functions Highlight: We generalise this by comparing the distributions rather than their moments via a powerful tool, i.e., the characteristic function (CF), which uniquely and universally comprising all the information about a distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shengxi Li; Zeyang Yu; Min Xiang; Danilo Mandic; | |
| 20 | Statistical Guarantees Of Distributed Nearest Neighbor Classification Highlight: Through majority voting, the distributed nearest neighbor classifier achieves the same rate of convergence as its oracle version in terms of the regret, up to a multiplicative constant that depends solely on the data dimension. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiexin Duan; Xingye Qiao; Guang Cheng; | |
| 21 | Stein Self-Repulsive Dynamics: Benefits From Past Samples Highlight: We propose a new Stein self-repulsive dynamics for obtaining diversified samples from intractable un-normalized distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mao Ye; Tongzheng Ren; Qiang Liu; | |
| 22 | The Statistical Complexity Of Early-Stopped Mirror Descent Highlight: In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrained mirror descent algorithms applied to the unregularized empirical risk with the squared loss for linear models and kernel methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tomas Vaskevicius; Varun Kanade; Patrick Rebeschini; | |
| 23 | Algorithmic Recourse Under Imperfect Causal Knowledge: A Probabilistic Approach Highlight: To address this limitation, we propose two probabilistic approaches to select optimal actions that achieve recourse with high probability given limited causal knowledge (e.g., only the causal graph). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amir-Hossein Karimi; Julius von K�gelgen; Bernhard Sch�lkopf; Isabel Valera; | |
| 24 | Quantitative Propagation Of Chaos For SGD In Wide Neural Networks Highlight: In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neural networks, as the number or neurons (i.e., the size of the hidden layer) $N \to \plusinfty$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Valentin De Bortoli; Alain Durmus; Xavier Fontaine; Umut Simsekli; | |
| 25 | A Causal View On Robustness Of Neural Networks Highlight: We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cheng Zhang; Kun Zhang; Yingzhen Li; | |
| 26 | Minimax Classification With 0-1 Loss And Performance Guarantees Highlight: This paper presents minimax risk classifiers (MRCs) that do not rely on a choice of surrogate loss and family of rules. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Santiago Mazuelas; Andrea Zanoni; Aritz P�rez; | |
| 27 | How To Learn A Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization Highlight: In this paper, we propose MAGE, a model-based actor-critic algorithm, grounded in the theory of policy gradients, which explicitly learns the action-value gradient. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pierluca D'Oro; Wojciech Jaskowski; | |
| 28 | Coresets For Regressions With Panel Data Highlight: This paper introduces the problem of coresets for regression problems to panel data settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lingxiao Huang; K Sudhir; Nisheeth Vishnoi; | |
| 29 | Learning Composable Energy Surrogates For PDE Order Reduction Highlight: To address this, we leverage parametric modular structure to learn component-level surrogates, enabling cheaper high-fidelity simulation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Beatson; Jordan Ash; Geoffrey Roeder; Tianju Xue; Ryan P. Adams; | |
| 30 | Efficient Contextual Bandits With Continuous Actions Highlight: We create a computationally tractable learning algorithm for contextual bandits with continuous actions having unknown structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maryam Majzoubi; Chicheng Zhang; Rajan Chari; Akshay Krishnamurthy; John Langford; Aleksandrs Slivkins; | |
| 31 | Achieving Equalized Odds By Resampling Sensitive Attributes Highlight: We present a flexible framework for learning predictive models that approximately satisfy the equalized odds notion of fairness. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaniv Romano; Stephen Bates; Emmanuel Candes; | |
| 32 | Multi-Robot Collision Avoidance Under Uncertainty With Probabilistic Safety Barrier Certificates Highlight: This paper aims to propose a collision avoidance method that accounts for both measurement uncertainty and motion uncertainty. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenhao Luo; Wen Sun; Ashish Kapoor; | |
| 33 | Hard Shape-Constrained Kernel Machines Highlight: In this paper, we prove that hard affine shape constraints on function derivatives can be encoded in kernel machines which represent one of the most flexible and powerful tools in machine learning and statistics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pierre-Cyril Aubin-Frankowski; Zoltan Szabo; | |
| 34 | A Closer Look At The Training Strategy For Modern Meta-Learning Highlight: The support/query (S/Q) episodic training strategy has been widely used in modern meta-learning algorithms and is believed to improve their generalization ability to test environments. This paper conducts a theoretical investigation of this training strategy on generalization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
JIAXIN CHEN; Xiao-Ming Wu; Yanke Li; Qimai LI; Li-Ming Zhan; Fu-lai Chung; | |
| 35 | On The Value Of Out-of-Distribution Testing: An Example Of Goodhart's Law Highlight: We provide short- and long-term solutions to avoid these pitfalls and realize the benefits of OOD evaluation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Damien Teney; Ehsan Abbasnejad; Kushal Kafle; Robik Shrestha; Christopher Kanan; Anton van den Hengel; | |
| 36 | Generalised Bayesian Filtering Via Sequential Monte Carlo Highlight: We introduce a framework for inference in general state-space hidden Markov models (HMMs) under likelihood misspecification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ayman Boustati; Omer Deniz Akyildiz; Theodoros Damoulas; Adam Johansen; | |
| 37 | Deterministic Approximation For Submodular Maximization Over A Matroid In Nearly Linear Time Highlight: We study the problem of maximizing a non-monotone, non-negative submodular function subject to a matroid constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kai Han; zongmai Cao; Shuang Cui; Benwei Wu; | |
| 38 | Flows For Simultaneous Manifold Learning And Density Estimation Highlight: We introduce manifold-learning flows (?-flows), a new class of generative models that simultaneously learn the data manifold as well as a tractable probability density on that manifold. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Johann Brehmer; Kyle Cranmer; | |
| 39 | Simultaneous Preference And Metric Learning From Paired Comparisons Highlight: In this paper, we consider the problem of learning an ideal point representation of a user’s preferences when the distance metric is an unknown Mahalanobis metric. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Austin Xu; Mark Davenport; | |
| 40 | Efficient Variational Inference For Sparse Deep Learning With Theoretical Guarantee Highlight: In this paper, we train sparse deep neural networks with a fully Bayesian treatment under spike-and-slab priors, and develop a set of computationally efficient variational inferences via continuous relaxation of Bernoulli distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jincheng Bai; Qifan Song; Guang Cheng; | |
| 41 | Learning Manifold Implicitly Via Explicit Heat-Kernel Learning Highlight: In this paper, we propose the concept of implicit manifold learning, where manifold information is implicitly obtained by learning the associated heat kernel. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yufan Zhou; Changyou Chen; Jinhui Xu; | |
| 42 | Deep Relational Topic Modeling Via Graph Poisson Gamma Belief Network Highlight: To better utilize the document network, we first propose graph Poisson factor analysis (GPFA) that constructs a probabilistic model for interconnected documents and also provides closed-form Gibbs sampling update equations, moving beyond sophisticated approximate assumptions of existing RTMs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaojie Wang; Hao Zhang; Bo Chen; Dongsheng Wang; Zhengjue Wang; Mingyuan Zhou; | |
| 43 | One-bit Supervision For Image Classification Highlight: This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
hengtong hu; Lingxi Xie; Zewei Du; Richang Hong; Qi Tian; | |
| 44 | What Is Being Transferred In Transfer Learning? Highlight: In this paper, we provide new tools and analysis to address these fundamental questions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Behnam Neyshabur; Hanie Sedghi; Chiyuan Zhang; | |
| 45 | Submodular Maximization Through Barrier Functions Highlight: In this paper, we introduce a novel technique for constrained submodular maximization, inspired by barrier functions in continuous optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ashwinkumar Badanidiyuru; Amin Karbasi; Ehsan Kazemi; Jan Vondrak; | |
| 46 | Neural Networks With Recurrent Generative Feedback Highlight: The proposed framework, termed Convolutional Neural Networks with Feedback (CNN-F), introduces a generative feedback with latent variables to existing CNN architectures, where consistent predictions are made through alternating MAP inference under a Bayesian framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yujia Huang; James Gornet; Sihui Dai; Zhiding Yu; Tan Nguyen; Doris Tsao; Anima Anandkumar; | |
| 47 | Learning To Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction Highlight: Motivated by this challenge, we introduce a realistic problem of few-shot out-of-graph link prediction, where we not only predict the links between the seen and unseen nodes as in a conventional out-of-knowledge link prediction task but also between the unseen nodes, with only few edges per node. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jinheon Baek; Dong Bok Lee; Sung Ju Hwang; | |
| 48 | Exploiting Weakly Supervised Visual Patterns To Learn From Partial Annotations Highlight: Instead, in this paper, we exploit relationships among images and labels to derive more supervisory signal from the un-annotated labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaustav Kundu; Joseph Tighe; | |
| 49 | Improving Inference For Neural Image Compression Highlight: We consider the problem of lossy image compression with deep latent variable models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yibo Yang; Robert Bamler; Stephan Mandt; | |
| 50 | Neuron Merging: Compensating For Pruned Neurons Highlight: In this work, we propose a novel concept of neuron merging applicable to both fully connected layers and convolution layers, which compensates for the information loss due to the pruned neurons/filters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Woojeong Kim; Suhyun Kim; Mincheol Park; Geunseok Jeon; | code |
| 51 | FixMatch: Simplifying Semi-Supervised Learning With Consistency And Confidence Highlight: In this paper we propose FixMatch, an algorithm that is a significant simplification of existing SSL methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kihyuk Sohn; David Berthelot; Nicholas Carlini; Zizhao Zhang; Han Zhang; Colin A. Raffel; Ekin Dogus Cubuk; Alexey Kurakin; Chun-Liang Li; | code |
| 52 | Reinforcement Learning With Combinatorial Actions: An Application To Vehicle Routing Highlight: We develop a framework for value-function-based deep reinforcement learning with a combinatorial action space, in which the action selection problem is explicitly formulated as a mixed-integer optimization problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arthur Delarue; Ross Anderson; Christian Tjandraatmadja; | |
| 53 | Towards Playing Full MOBA Games With Deep Reinforcement Learning Highlight: In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Deheng Ye; Guibin Chen; Wen Zhang; Sheng Chen; Bo Yuan; Bo Liu; Jia Chen; Zhao Liu; Fuhao Qiu; Hongsheng Yu; Yinyuting Yin; Bei Shi; Liang Wang; Tengfei Shi; Qiang Fu; Wei Yang; Lanxiao Huang; Wei Liu; | |
| 54 | Rankmax: An Adaptive Projection Alternative To The Softmax Function Highlight: In this work, we propose a method that adapts this parameter to individual training examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weiwei Kong; Walid Krichene; Nicolas Mayoraz; Steffen Rendle; Li Zhang; | |
| 55 | Online Agnostic Boosting Via Regret Minimization Highlight: In this work we provide the first agnostic online boosting algorithm; that is, given a weak learner with only marginally-better-than-trivial regret guarantees, our algorithm boosts it to a strong learner with sublinear regret. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nataly Brukhim; Xinyi Chen; Elad Hazan; Shay Moran; | |
| 56 | Causal Intervention For Weakly-Supervised Semantic Segmentation Highlight: We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dong Zhang; Hanwang Zhang; Jinhui Tang; Xian-Sheng Hua; Qianru Sun; | |
| 57 | Belief Propagation Neural Networks Highlight: To bridge this gap, we introduce belief propagation neural networks (BPNNs), a class of parameterized operators that operate on factor graphs and generalize Belief Propagation (BP). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Kuck; Shuvam Chakraborty; Hao Tang; Rachel Luo; Jiaming Song; Ashish Sabharwal; Stefano Ermon; | |
| 58 | Over-parameterized Adversarial Training: An Analysis Overcoming The Curse Of Dimensionality Highlight: Our work proves convergence to low robust training loss for \emph{polynomial} width instead of exponential, under natural assumptions and with ReLU activations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yi Zhang; Orestis Plevrakis; Simon S. Du; Xingguo Li; Zhao Song; Sanjeev Arora; | |
| 59 | Post-training Iterative Hierarchical Data Augmentation For Deep Networks Highlight: In this paper, we propose a new iterative hierarchical data augmentation (IHDA) method to fine-tune trained deep neural networks to improve their generalization performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adil Khan; Khadija Fraz; | |
| 60 | Debugging Tests For Model Explanations Highlight: We investigate whether post-hoc model explanations are effective for diagnosing model errors–model debugging. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julius Adebayo; Michael Muelly; Ilaria Liccardi; Been Kim; | |
| 61 | Robust Compressed Sensing Using Generative Models Highlight: In this paper we propose an algorithm inspired by the Median-of-Means (MOM). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ajil Jalal; Liu Liu; Alexandros G. Dimakis; Constantine Caramanis; | |
| 62 | Fairness Without Demographics Through Adversarially Reweighted Learning Highlight: In this work we address this problem by proposing Adversarially Reweighted Learning (ARL). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Preethi Lahoti; Alex Beutel; Jilin Chen; Kang Lee; Flavien Prost; Nithum Thain; Xuezhi Wang; Ed Chi; | |
| 63 | Stochastic Latent Actor-Critic: Deep Reinforcement Learning With A Latent Variable Model Highlight: In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Lee; Anusha Nagabandi; Pieter Abbeel; Sergey Levine; | |
| 64 | Ridge Rider: Finding Diverse Solutions By Following Eigenvectors Of The Hessian Highlight: In this paper, we present a different approach. Rather than following the gradient, which corresponds to a locally greedy direction, we instead follow the eigenvectors of the Hessian. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jack Parker-Holder; Luke Metz; Cinjon Resnick; Hengyuan Hu; Adam Lerer; Alistair Letcher; Alexander Peysakhovich; Aldo Pacchiano; Jakob Foerster; | |
| 65 | The Route To Chaos In Routing Games: When Is Price Of Anarchy Too Optimistic? Highlight: We study MWU using the actual game costs without applying cost normalization to $[0,1]$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thiparat Chotibut; Fryderyk Falniowski; Michal Misiurewicz; Georgios Piliouras; | |
| 66 | Online Algorithm For Unsupervised Sequential Selection With Contextual Information Highlight: In this paper, we study Contextual Unsupervised Sequential Selection (USS), a new variant of the stochastic contextual bandits problem where the loss of an arm cannot be inferred from the observed feedback. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arun Verma; Manjesh Kumar Hanawal; Csaba Szepesvari; Venkatesh Saligrama; | |
| 67 | Adapting Neural Architectures Between Domains Highlight: This paper aims to improve the generalization of neural architectures via domain adaptation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yanxi Li; zhaohui yang; Yunhe Wang; Chang Xu; | |
| 68 | What Went Wrong And When?\\ Instance-wise Feature Importance For Time-series Black-box Models Highlight: We propose FIT, a framework that evaluates the importance of observations for a multivariate time-series black-box model by quantifying the shift in the predictive distribution over time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sana Tonekaboni; Shalmali Joshi; Kieran Campbell; David K. Duvenaud; Anna Goldenberg; | |
| 69 | Towards Better Generalization Of Adaptive Gradient Methods Highlight: To close this gap, we propose \textit{\textbf{S}table \textbf{A}daptive \textbf{G}radient \textbf{D}escent} (\textsc{SAGD}) for nonconvex optimization which leverages differential privacy to boost the generalization performance of adaptive gradient methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingxue Zhou; Belhal Karimi; Jinxing Yu; Zhiqiang Xu; Ping Li; | |
| 70 | Learning Guidance Rewards With Trajectory-space Smoothing Highlight: This paper is in the same vein — starting with a surrogate RL objective that involves smoothing in the trajectory-space, we arrive at a new algorithm for learning guidance rewards. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tanmay Gangwani; Yuan Zhou; Jian Peng; | |
| 71 | Variance Reduction Via Accelerated Dual Averaging For Finite-Sum Optimization Highlight: In this paper, we introduce a simplified and unified method for finite-sum convex optimization, named \emph{Variance Reduction via Accelerated Dual Averaging (VRADA)}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaobing Song; Yong Jiang; Yi Ma; | |
| 72 | Tree! I Am No Tree! I Am A Low Dimensional Hyperbolic Embedding Highlight: In this paper, we explore a new method for learning hyperbolic representations by taking a metric-first approach. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rishi Sonthalia; Anna Gilbert; | |
| 73 | Deep Structural Causal Models For Tractable Counterfactual Inference Highlight: We formulate a general framework for building structural causal models (SCMs) with deep learning components. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nick Pawlowski; Daniel Coelho de Castro; Ben Glocker; | |
| 74 | Convolutional Generation Of Textured 3D Meshes Highlight: A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dario Pavllo; Graham Spinks; Thomas Hofmann; Marie-Francine Moens; Aurelien Lucchi; | |
| 75 | A Statistical Framework For Low-bitwidth Training Of Deep Neural Networks Highlight: In this paper, we address this problem by presenting a statistical framework for analyzing FQT algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianfei Chen; Yu Gai; Zhewei Yao; Michael W. Mahoney; Joseph E. Gonzalez; | |
| 76 | Better Set Representations For Relational Reasoning Highlight: To resolve this limitation, we propose a simple and general network module called Set Refiner Network (SRN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qian Huang; Horace He; Abhay Singh; Yan Zhang; Ser Nam Lim; Austin R. Benson; | |
| 77 | AutoSync: Learning To Synchronize For Data-Parallel Distributed Deep Learning Highlight: In this paper, we develop a model- and resource-dependent representation for synchronization, which unifies multiple synchronization aspects ranging from architecture, message partitioning, placement scheme, to communication topology. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hao Zhang; Yuan Li; Zhijie Deng; Xiaodan Liang; Lawrence Carin; Eric Xing; | |
| 78 | A Combinatorial Perspective On Transfer Learning Highlight: In this work we study how the learning of modular solutions can allow for effective generalization to both unseen and potentially differently distributed data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianan Wang; Eren Sezener; David Budden; Marcus Hutter; Joel Veness; | |
| 79 | Hardness Of Learning Neural Networks With Natural Weights Highlight: We prove negative results in this regard, and show that for depth-$2$ networks, and many “natural" weights distributions such as the normal and the uniform distribution, most networks are hard to learn. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amit Daniely; Gal Vardi; | |
| 80 | Higher-Order Spectral Clustering Of Directed Graphs Highlight: Based on the Hermitian matrix representation of digraphs, we present a nearly-linear time algorithm for digraph clustering, and further show that our proposed algorithm can be implemented in sublinear time under reasonable assumptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Valdimar Steinar Ericsson Laenen; He Sun; | |
| 81 | Primal-Dual Mesh Convolutional Neural Networks Highlight: We propose a method that combines the advantages of both types of approaches, while addressing their limitations: we extend a primal-dual framework drawn from the graph-neural-network literature to triangle meshes, and define convolutions on two types of graphs constructed from an input mesh. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Francesco Milano; Antonio Loquercio; Antoni Rosinol; Davide Scaramuzza; Luca Carlone; | |
| 82 | The Advantage Of Conditional Meta-Learning For Biased Regularization And Fine Tuning Highlight: We address this limitation by conditional meta-learning, inferring a conditioning function mapping task’s side information into a meta-parameter vector that is appropriate for that task at hand. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Giulia Denevi; Massimiliano Pontil; Carlo Ciliberto; | |
| 83 | Watch Out! Motion Is Blurring The Vision Of Your Deep Neural Networks Highlight: We propose a novel adversarial attack method that can generate visually natural motion-blurred adversarial examples, named motion-based adversarial blur attack (ABBA). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qing Guo; Felix Juefei-Xu; Xiaofei Xie; Lei Ma; Jian Wang; Bing Yu; Wei Feng; Yang Liu; | code |
| 84 | Sinkhorn Barycenter Via Functional Gradient Descent Highlight: In this paper, we consider the problem of computing the barycenter of a set of probability distributions under the Sinkhorn divergence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zebang Shen; Zhenfu Wang; Alejandro Ribeiro; Hamed Hassani; | |
| 85 | Coresets For Near-Convex Functions Highlight: We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Morad Tukan; Alaa Maalouf; Dan Feldman; | |
| 86 | Bayesian Deep Ensembles Via The Neural Tangent Kernel Highlight: We introduce a simple modification to standard deep ensembles training, through addition of a computationally-tractable, randomised and untrainable function to each ensemble member, that enables a posterior interpretation in the infinite width limit. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bobby He; Balaji Lakshminarayanan; Yee Whye Teh; | |
| 87 | Improved Schemes For Episodic Memory-based Lifelong Learning Highlight: In this paper, we provide the first unified view of episodic memory based approaches from an optimization’s perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunhui Guo; Mingrui Liu; Tianbao Yang; Tajana Rosing; | |
| 88 | Adaptive Sampling For Stochastic Risk-Averse Learning Highlight: We propose an adaptive sampling algorithm for stochastically optimizing the {\em Conditional Value-at-Risk (CVaR)} of a loss distribution, which measures its performance on the $\alpha$ fraction of most difficult examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sebastian Curi; Kfir Y. Levy; Stefanie Jegelka; Andreas Krause; | |
| 89 | Deep Wiener Deconvolution: Wiener Meets Deep Learning For Image Deblurring Highlight: We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiangxin Dong; Stefan Roth; Bernt Schiele; | |
| 90 | Discovering Reinforcement Learning Algorithms Highlight: This paper introduces a new meta-learning approach that discovers an entire update rule which includes both what to predict’ (e.g. value functions) and how to learn from it’ (e.g. bootstrapping) by interacting with a set of environments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junhyuk Oh; Matteo Hessel; Wojciech M. Czarnecki; Zhongwen Xu; Hado P. van Hasselt; Satinder Singh; David Silver; | |
| 91 | Taming Discrete Integration Via The Boon Of Dimensionality Highlight: The key contribution of this work addresses this scalability challenge via an efficient reduction of discrete integration to model counting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeffrey Dudek; Dror Fried; Kuldeep S Meel; | |
| 92 | Blind Video Temporal Consistency Via Deep Video Prior Highlight: To address this issue, we present a novel and general approach for blind video temporal consistency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chenyang Lei; Yazhou Xing; Qifeng Chen; | |
| 93 | Simplify And Robustify Negative Sampling For Implicit Collaborative Filtering Highlight: In this paper, we ?rst provide a novel understanding of negative instances by empirically observing that only a few instances are potentially important for model learning, and false negatives tend to have stable predictions over many training iterations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jingtao Ding; Yuhan Quan; Quanming Yao; Yong Li; Depeng Jin; | code |
| 94 | Model Selection For Production System Via Automated Online Experiments Highlight: We propose an automated online experimentation mechanism that can efficiently perform model selection from a large pool of models with a small number of online experiments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhenwen Dai; Praveen Chandar; Ghazal Fazelnia; Benjamin Carterette; Mounia Lalmas; | |
| 95 | On The Almost Sure Convergence Of Stochastic Gradient Descent In Non-Convex Problems Highlight: In this paper, we analyze the trajectories of stochastic gradient descent (SGD) with the aim of understanding their convergence properties in non-convex problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Panayotis Mertikopoulos; Nadav Hallak; Ali Kavis; Volkan Cevher; | |
| 96 | Automatic Perturbation Analysis For Scalable Certified Robustness And Beyond Highlight: In this paper, we develop an automatic framework to enable perturbation analysis on any neural network structures, by generalizing existing LiRPA algorithms such as CROWN to operate on general computational graphs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaidi Xu; Zhouxing Shi; Huan Zhang; Yihan Wang; Kai-Wei Chang; Minlie Huang; Bhavya Kailkhura; Xue Lin; Cho-Jui Hsieh; | code |
| 97 | Adaptation Properties Allow Identification Of Optimized Neural Codes Highlight: Here we solve an inverse problem: characterizing the objective and constraint functions that efficient codes appear to be optimal for, on the basis of how they adapt to different stimulus distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luke Rast; Jan Drugowitsch; | |
| 98 | Global Convergence And Variance Reduction For A Class Of Nonconvex-Nonconcave Minimax Problems Highlight: In this work, we show that for a subclass of nonconvex-nonconcave objectives satisfying a so-called two-sided Polyak-{\L}ojasiewicz inequality, the alternating gradient descent ascent (AGDA) algorithm converges globally at a linear rate and the stochastic AGDA achieves a sublinear rate. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junchi Yang; Negar Kiyavash; Niao He; | |
| 99 | Model-Based Multi-Agent RL In Zero-Sum Markov Games With Near-Optimal Sample Complexity Highlight: In this paper, we aim to address the fundamental open question about the sample complexity of model-based MARL. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaiqing Zhang; Sham Kakade; Tamer Basar; Lin Yang; | |
| 100 | Conservative Q-Learning For Offline Reinforcement Learning Highlight: In this paper, we propose conservative Q-learning (CQL), which aims to address these limitations by learning a conservative Q-function such that the expected value of a policy under this Q-function lower-bounds its true value. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aviral Kumar; Aurick Zhou; George Tucker; Sergey Levine; | |
| 101 | Online Influence Maximization Under Linear Threshold Model Highlight: In this paper, we address OIM in the linear threshold (LT) model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuai Li; Fang Kong; Kejie Tang; Qizhi Li; Wei Chen; | |
| 102 | Ensembling Geophysical Models With Bayesian Neural Networks Highlight: We develop a novel data-driven ensembling strategy for combining geophysical models using Bayesian Neural Networks, which infers spatiotemporally varying model weights and bias while accounting for heteroscedastic uncertainties in the observations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ushnish Sengupta; Matt Amos; Scott Hosking; Carl Edward Rasmussen; Matthew Juniper; Paul Young; | |
| 103 | Delving Into The Cyclic Mechanism In Semi-supervised Video Object Segmentation Highlight: In this paper, we take attempt to incorporate the cyclic mechanism with the vision task of semi-supervised video object segmentation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuxi Li; Ning Xu; Jinlong Peng; John See; Weiyao Lin; | |
| 104 | Asymmetric Shapley Values: Incorporating Causal Knowledge Into Model-agnostic Explainability Highlight: We introduce a less restrictive framework, Asymmetric Shapley values (ASVs), which are rigorously founded on a set of axioms, applicable to any AI system, and can flexibly incorporate any causal structure known to be respected by the data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christopher Frye; Colin Rowat; Ilya Feige; | |
| 105 | Understanding Deep Architecture With Reasoning Layer Highlight: In this paper, we take an initial step toward an understanding of such hybrid deep architectures by showing that properties of the algorithm layers, such as convergence, stability and sensitivity, are intimately related to the approximation and generalization abilities of the end-to-end model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xinshi Chen; Yufei Zhang; Christoph Reisinger; Le Song; | |
| 106 | Planning In Markov Decision Processes With Gap-Dependent Sample Complexity Highlight: We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anders Jonsson; Emilie Kaufmann; Pierre Menard; Omar Darwiche Domingues; Edouard Leurent; Michal Valko; | |
| 107 | Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration Highlight: We show that using \emph{pessimistic value estimates} in the low-data regions in Bellman optimality and evaluation back-up can yield more adaptive and stronger guarantees when the concentrability assumption does not hold. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yao Liu; Adith Swaminathan; Alekh Agarwal; Emma Brunskill; | |
| 108 | Detection As Regression: Certified Object Detection With Median Smoothing Highlight: This work is motivated by recent progress on certified classification by randomized smoothing. We start by presenting a reduction from object detection to a regression problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ping-yeh Chiang; Michael Curry; Ahmed Abdelkader; Aounon Kumar; John Dickerson; Tom Goldstein; | |
| 109 | Contextual Reserve Price Optimization In Auctions Via Mixed Integer Programming Highlight: We study the problem of learning a linear model to set the reserve price in an auction, given contextual information, in order to maximize expected revenue from the seller side. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joey Huchette; Haihao Lu; Hossein Esfandiari; Vahab Mirrokni; | |
| 110 | ExpandNets: Linear Over-parameterization To Train Compact Convolutional Networks Highlight: We introduce an approach to training a given compact network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuxuan Guo; Jose M. Alvarez; Mathieu Salzmann; | |
| 111 | FleXOR: Trainable Fractional Quantization Highlight: In this paper, we propose an encryption algorithm/architecture to compress quantized weights so as to achieve fractional numbers of bits per weight. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dongsoo Lee; Se Jung Kwon; Byeongwook Kim; Yongkweon Jeon; Baeseong Park; Jeongin Yun; | |
| 112 | The Implications Of Local Correlation On Learning Some Deep Functions Highlight: We introduce a property of distributions, denoted “local correlation”, which requires that small patches of the input image and of intermediate layers of the target function are correlated to the target label. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eran Malach; Shai Shalev-Shwartz; | |
| 113 | Learning To Search Efficiently For Causally Near-optimal Treatments Highlight: We formalize this problem as learning a policy for finding a near-optimal treatment in a minimum number of trials using a causal inference framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Samuel H�kansson; Viktor Lindblom; Omer Gottesman; Fredrik D. Johansson; | |
| 114 | A Game Theoretic Analysis Of Additive Adversarial Attacks And Defenses Highlight: In this paper, we propose a game-theoretic framework for studying attacks and defenses which exist in equilibrium. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ambar Pal; Rene Vidal; | |
| 115 | Posterior Network: Uncertainty Estimation Without OOD Samples Via Density-Based Pseudo-Counts Highlight: In this work we propose the Posterior Network (PostNet), which uses Normalizing Flows to predict an individual closed-form posterior distribution over predicted probabilites for any input sample. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bertrand Charpentier; Daniel Z�gner; Stephan G�nnemann; | |
| 116 | Recurrent Quantum Neural Networks Highlight: In this work we construct the first quantum recurrent neural network (QRNN) with demonstrable performance on non-trivial tasks such as sequence learning and integer digit classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Johannes Bausch; | |
| 117 | No-Regret Learning And Mixed Nash Equilibria: They Do Not Mix Highlight: In this paper, we study the dynamics of follow the regularized leader (FTRL), arguably the most well-studied class of no-regret dynamics, and we establish a sweeping negative result showing that the notion of mixed Nash equilibrium is antithetical to no-regret learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emmanouil-Vasileios Vlatakis-Gkaragkounis; Lampros Flokas; Thanasis Lianeas; Panayotis Mertikopoulos; Georgios Piliouras; | |
| 118 | A Unifying View Of Optimism In Episodic Reinforcement Learning Highlight: In this paper we provide a general framework for designing, analyzing and implementing such algorithms in the episodic reinforcement learning problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gergely Neu; Ciara Pike-Burke; | |
| 119 | Continuous Submodular Maximization: Beyond DR-Submodularity Highlight: In this paper, we propose the first continuous optimization algorithms that achieve a constant factor approximation guarantee for the problem of monotone continuous submodular maximization subject to a linear constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Moran Feldman; Amin Karbasi; | |
| 120 | An Asymptotically Optimal Primal-Dual Incremental Algorithm For Contextual Linear Bandits Highlight: In this paper, we follow recent approaches of deriving asymptotically optimal algorithms from problem-dependent regret lower bounds and we introduce a novel algorithm improving over the state-of-the-art along multiple dimensions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrea Tirinzoni; Matteo Pirotta; Marcello Restelli; Alessandro Lazaric; | |
| 121 | Assessing SATNet's Ability To Solve The Symbol Grounding Problem Highlight: In this paper, we clarify SATNet’s capabilities by showing that in the absence of intermediate labels that identify individual Sudoku digit images with their logical representations, SATNet completely fails at visual Sudoku (0% test accuracy). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Oscar Chang; Lampros Flokas; Hod Lipson; Michael Spranger; | |
| 122 | A Bayesian Nonparametrics View Into Deep Representations Highlight: We investigate neural network representations from a probabilistic perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michal Jamroz; Marcin Kurdziel; Mateusz Opala; | |
| 123 | On The Similarity Between The Laplace And Neural Tangent Kernels Highlight: Here we show that NTK for fully connected networks with ReLU activation is closely related to the standard Laplace kernel. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amnon Geifman; Abhay Yadav; Yoni Kasten; Meirav Galun; David Jacobs; Basri Ronen; | |
| 124 | A Causal View Of Compositional Zero-shot Recognition Highlight: Here we describe an approach for compositional generalization that builds on causal ideas. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuval Atzmon; Felix Kreuk; Uri Shalit; Gal Chechik; | |
| 125 | HiPPO: Recurrent Memory With Optimal Polynomial Projections Highlight: We introduce a general framework (HiPPO) for the online compression of continuous signals and discrete time series by projection onto polynomial bases. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Albert Gu; Tri Dao; Stefano Ermon; Atri Rudra; Christopher R�; | |
| 126 | Auto Learning Attention Highlight: In this paper, we devise an Auto Learning Attention (AutoLA) method, which is the first attempt on automatic attention design. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benteng Ma; Jing Zhang; Yong Xia; Dacheng Tao; | |
| 127 | CASTLE: Regularization Via Auxiliary Causal Graph Discovery Highlight: We introduce Causal Structure Learning (CASTLE) regularization and propose to regularize a neural network by jointly learning the causal relationships between variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Trent Kyono; Yao Zhang; Mihaela van der Schaar; | |
| 128 | Long-Tailed Classification By Keeping The Good And Removing The Bad Momentum Causal Effect Highlight: In this paper, we establish a causal inference framework, which not only unravels the whys of previous methods, but also derives a new principled solution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaihua Tang; Jianqiang Huang; Hanwang Zhang; | |
| 129 | Explainable Voting Highlight: We prove, however, that outcomes of the important Borda rule can be explained using O(m^2) steps, where m is the number of alternatives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dominik Peters; Ariel D. Procaccia; Alexandros Psomas; Zixin Zhou; | |
| 130 | Deep Archimedean Copulas Highlight: In this paper, we introduce ACNet, a novel differentiable neural network architecture that enforces structural properties and enables one to learn an important class of copulas–Archimedean Copulas. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chun Kai Ling; Fei Fang; J. Zico Kolter; | |
| 131 | Re-Examining Linear Embeddings For High-Dimensional Bayesian Optimization Highlight: In this paper, we identify several crucial issues and misconceptions about the use of linear embeddings for BO. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ben Letham; Roberto Calandra; Akshara Rai; Eytan Bakshy; | |
| 132 | UnModNet: Learning To Unwrap A Modulo Image For High Dynamic Range Imaging Highlight: In this paper, we reformulate the modulo image unwrapping problem into a series of binary labeling problems and propose a modulo edge-aware model, named as UnModNet, to iteratively estimate the binary rollover masks of the modulo image for unwrapping. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chu Zhou; Hang Zhao; Jin Han; Chang Xu; Chao Xu; Tiejun Huang; Boxin Shi; | |
| 133 | Thunder: A Fast Coordinate Selection Solver For Sparse Learning Highlight: In this paper, we propose a novel active incremental approach to further improve the efficiency of the solvers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shaogang Ren; Weijie Zhao; Ping Li; | |
| 134 | Neural Networks Fail To Learn Periodic Functions And How To Fix It Highlight: As a fix of this problem, we propose a new activation, namely, $x + \sin^2(x)$, which achieves the desired periodic inductive bias to learn a periodic function while maintaining a favorable optimization property of the $\relu$-based activations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Liu Ziyin; Tilman Hartwig; Masahito Ueda; | |
| 135 | Distribution Matching For Crowd Counting Highlight: In this paper, we show that imposing Gaussians to annotations hurts generalization performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Boyu Wang; Huidong Liu; Dimitris Samaras; Minh Hoai Nguyen; | code |
| 136 | Correspondence Learning Via Linearly-invariant Embedding Highlight: In this paper, we propose a fully differentiable pipeline for estimating accurate dense correspondences between 3D point clouds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Riccardo Marin; Marie-Julie Rakotosaona; Simone Melzi; Maks Ovsjanikov; | |
| 137 | Learning To Dispatch For Job Shop Scheduling Via Deep Reinforcement Learning Highlight: In this paper, we propose to automatically learn PDRs via an end-to-end deep reinforcement learning agent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cong Zhang; Wen Song; Zhiguang Cao; Jie Zhang; Puay Siew Tan; Xu Chi; | |
| 138 | On Adaptive Attacks To Adversarial Example Defenses Highlight: While prior evaluation papers focused mainly on the end result—showing that a defense was ineffective—this paper focuses on laying out the methodology and the approach necessary to perform an adaptive attack. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Florian Tramer; Nicholas Carlini; Wieland Brendel; Aleksander Madry; | |
| 139 | Sinkhorn Natural Gradient For Generative Models Highlight: In this regard, we propose a novel Sinkhorn Natural Gradient (SiNG) algorithm which acts as a steepest descent method on the probability space endowed with the Sinkhorn divergence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zebang Shen; Zhenfu Wang; Alejandro Ribeiro; Hamed Hassani; | |
| 140 | Online Sinkhorn: Optimal Transport Distances From Sample Streams Highlight: This paper introduces a new online estimator of entropy-regularized OT distances between two such arbitrary distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arthur Mensch; Gabriel Peyr�; | |
| 141 | Ultrahyperbolic Representation Learning Highlight: In this paper, we propose a representation living on a pseudo-Riemannian manifold of constant nonzero curvature. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marc Law; Jos Stam; | |
| 142 | Locally-Adaptive Nonparametric Online Learning Highlight: We fill this gap by introducing efficient online algorithms (based on a single versatile master algorithm) each adapting to one of the following regularities: (i) local Lipschitzness of the competitor function, (ii) local metric dimension of the instance sequence, (iii) local performance of the predictor across different regions of the instance space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilja Kuzborskij; Nicol� Cesa-Bianchi; | |
| 143 | Compositional Generalization Via Neural-Symbolic Stack Machines Highlight: To tackle this issue, we propose the Neural-Symbolic Stack Machine (NeSS). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xinyun Chen; Chen Liang; Adams Wei Yu; Dawn Song; Denny Zhou; | |
| 144 | Graphon Neural Networks And The Transferability Of Graph Neural Networks Highlight: In this paper we introduce graphon NNs as limit objects of GNNs and prove a bound on the difference between the output of a GNN and its limit graphon-NN. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luana Ruiz; Luiz Chamon; Alejandro Ribeiro; | |
| 145 | Unreasonable Effectiveness Of Greedy Algorithms In Multi-Armed Bandit With Many Arms Highlight: We study the structure of regret-minimizing policies in the {\em many-armed} Bayesian multi-armed bandit problem: in particular, with $k$ the number of arms and $T$ the time horizon, we consider the case where $k \geq \sqrt{T}$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mohsen Bayati; Nima Hamidi; Ramesh Johari; Khashayar Khosravi; | |
| 146 | Gamma-Models: Generative Temporal Difference Learning For Infinite-Horizon Prediction Highlight: We introduce the gamma-model, a predictive model of environment dynamics with an infinite, probabilistic horizon. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Janner; Igor Mordatch; Sergey Levine; | |
| 147 | Deep Transformers With Latent Depth Highlight: We present a probabilistic framework to automatically learn which layer(s) to use by learning the posterior distributions of layer selection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xian Li; Asa Cooper Stickland; Yuqing Tang; Xiang Kong; | |
| 148 | Neural Mesh Flow: 3D Manifold Mesh Generation Via Diffeomorphic Flows Highlight: In this work, we propose NeuralMeshFlow (NMF) to generate two-manifold meshes for genus-0 shapes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kunal Gupta; Manmohan Chandraker; | |
| 149 | Statistical Control For Spatio-temporal MEG/EEG Source Imaging With Desparsified Mutli-task Lasso Highlight: To deal with this, we adapt the desparsified Lasso estimator —an estimator tailored for high dimensional linear model that asymptotically follows a Gaussian distribution under sparsity and moderate feature correlation assumptions— to temporal data corrupted with autocorrelated noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jerome-Alexis Chevalier; Joseph Salmon; Alexandre Gramfort; Bertrand Thirion; | |
| 150 | A Scalable MIP-based Method For Learning Optimal Multivariate Decision Trees Highlight: In this paper, we propose a novel MIP formulation, based on 1-norm support vector machine model, to train a binary oblique ODT for classification problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haoran Zhu; Pavankumar Murali; Dzung Phan; Lam Nguyen; Jayant Kalagnanam; | |
| 151 | Efficient Exact Verification Of Binarized Neural Networks Highlight: We present a new system, EEV, for efficient and exact verification of BNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kai Jia; Martin Rinard; | |
| 152 | Ultra-Low Precision 4-bit Training Of Deep Neural Networks Highlight: In this paper, we propose a number of novel techniques and numerical representation formats that enable, for the very first time, the precision of training systems to be aggressively scaled from 8-bits to 4-bits. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiao Sun; Naigang Wang; Chia-Yu Chen; Jiamin Ni; Ankur Agrawal; Xiaodong Cui; Swagath Venkataramani; Kaoutar El Maghraoui; Vijayalakshmi (Viji) Srinivasan; Kailash Gopalakrishnan; | |
| 153 | Bridging The Gap Between Sample-based And One-shot Neural Architecture Search With BONAS Highlight: In this work, we propose BONAS (Bayesian Optimized Neural Architecture Search), a sample-based NAS framework which is accelerated using weight-sharing to evaluate multiple related architectures simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Han Shi; Renjie Pi; Hang Xu; Zhenguo Li; James Kwok; Tong Zhang; | |
| 154 | On Numerosity Of Deep Neural Networks Highlight: Recently, a provocative claim was published that number sense spontaneously emerges in a deep neural network trained merely for visual object recognition. This has, if true, far reaching significance to the fields of machine learning and cognitive science alike. In this paper, we prove the above claim to be unfortunately incorrect. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xi Zhang; Xiaolin Wu; | |
| 155 | Outlier Robust Mean Estimation With Subgaussian Rates Via Stability Highlight: We study the problem of outlier robust high-dimensional mean estimation under a bounded covariance assumption, and more broadly under bounded low-degree moment assumptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilias Diakonikolas; Daniel M. Kane; Ankit Pensia; | |
| 156 | Self-Supervised Relationship Probing Highlight: In this work, we introduce a self-supervised method that implicitly learns the visual relationships without relying on any ground-truth visual relationship annotations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiuxiang Gu; Jason Kuen; Shafiq Joty; Jianfei Cai; Vlad Morariu; Handong Zhao; Tong Sun; | |
| 157 | Information Theoretic Counterfactual Learning From Missing-Not-At-Random Feedback Highlight: To circumvent the use of RCTs, we build an information theoretic counterfactual variational information bottleneck (CVIB), as an alternative for debiasing learning without RCTs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zifeng Wang; Xi Chen; Rui Wen; Shao-Lun Huang; Ercan Kuruoglu; Yefeng Zheng; | |
| 158 | Prophet Attention: Predicting Attention With Future Attention Highlight: In this paper, we propose the Prophet Attention, similar to the form of self-supervision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fenglin Liu; Xuancheng Ren; Xian Wu; Shen Ge; Wei Fan; Yuexian Zou; Xu Sun; | |
| 159 | Language Models Are Few-Shot Learners Highlight: Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tom Brown; Benjamin Mann; Nick Ryder; Melanie Subbiah; Jared D Kaplan; Prafulla Dhariwal; Arvind Neelakantan; Pranav Shyam; Girish Sastry; Amanda Askell; Sandhini Agarwal; Ariel Herbert-Voss; Gretchen Krueger; Tom Henighan; Rewon Child; Aditya Ramesh; Daniel Ziegler; Jeffrey Wu; Clemens Winter; Chris Hesse; Mark Chen; Eric Sigler; Mateusz Litwin; Scott Gray; Benjamin Chess; Jack Clark; Christopher Berner; Sam McCandlish; Alec Radford; Ilya Sutskever; Dario Amodei; | |
| 160 | Margins Are Insufficient For Explaining Gradient Boosting Highlight: In this work, we first demonstrate that the k’th margin bound is inadequate in explaining the performance of state-of-the-art gradient boosters. We then explain the short comings of the k’th margin bound and prove a stronger and more refined margin-based generalization bound that indeed succeeds in explaining the performance of modern gradient boosters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Allan Gr�nlund; Lior Kamma; Kasper Green Larsen; | |
| 161 | Fourier-transform-based Attribution Priors Improve The Interpretability And Stability Of Deep Learning Models For Genomics Highlight: To address these shortcomings, we propose a novel attribution prior, where the Fourier transform of input-level attribution scores are computed at training-time, and high-frequency components of the Fourier spectrum are penalized. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Tseng; Avanti Shrikumar; Anshul Kundaje; | |
| 162 | MomentumRNN: Integrating Momentum Into Recurrent Neural Networks Highlight: We theoretically prove and numerically demonstrate that MomentumRNNs alleviate the vanishing gradient issue in training RNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tan Nguyen; Richard Baraniuk; Andrea Bertozzi; Stanley Osher; Bao Wang; | |
| 163 | Marginal Utility For Planning In Continuous Or Large Discrete Action Spaces Highlight: In this paper we explore explicitly learning a candidate action generator by optimizing a novel objective, marginal utility. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zaheen Ahmad; Levi Lelis; Michael Bowling; | |
| 164 | Projected Stein Variational Gradient Descent Highlight: In this work, we propose a {projected Stein variational gradient descent} (pSVGD) method to overcome this challenge by exploiting the fundamental property of intrinsic low dimensionality of the data informed subspace stemming from ill-posedness of such problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peng Chen; Omar Ghattas; | |
| 165 | Minimax Lower Bounds For Transfer Learning With Linear And One-hidden Layer Neural Networks Highlight: In this paper we develop a statistical minimax framework to characterize the fundamental limits of transfer learning in the context of regression with linear and one-hidden layer neural network models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mohammadreza Mousavi Kalan; Zalan Fabian; Salman Avestimehr; Mahdi Soltanolkotabi; | |
| 166 | SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks Highlight: We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point-clouds, which is equivariant under continuous 3D roto-translations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fabian Fuchs; Daniel Worrall; Volker Fischer; Max Welling; | |
| 167 | On The Equivalence Of Molecular Graph Convolution And Molecular Wave Function With Poor Basis Set Highlight: In this study, we demonstrate that the linear combination of atomic orbitals (LCAO), an approximation introduced by Pauling and Lennard-Jones in the 1920s, corresponds to graph convolutional networks (GCNs) for molecules. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Masashi Tsubaki; Teruyasu Mizoguchi; | |
| 168 | The Power Of Predictions In Online Control Highlight: We study the impact of predictions in online Linear Quadratic Regulator control with both stochastic and adversarial disturbances in the dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chenkai Yu; Guanya Shi; Soon-Jo Chung; Yisong Yue; Adam Wierman; | |
| 169 | Learning Affordance Landscapes For Interaction Exploration In 3D Environments Highlight: We introduce a reinforcement learning approach for exploration for interaction, whereby an embodied agent autonomously discovers the affordance landscape of a new unmapped 3D environment (such as an unfamiliar kitchen). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tushar Nagarajan; Kristen Grauman; | code |
| 170 | Cooperative Multi-player Bandit Optimization Highlight: We design a distributed learning algorithm that overcomes the informational bias players have towards maximizing the rewards of nearby players they got more information about. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilai Bistritz; Nicholas Bambos; | |
| 171 | Tight First- And Second-Order Regret Bounds For Adversarial Linear Bandits Highlight: We propose novel algorithms with first- and second-order regret bounds for adversarial linear bandits. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shinji Ito; Shuichi Hirahara; Tasuku Soma; Yuichi Yoshida; | |
| 172 | Just Pick A Sign: Optimizing Deep Multitask Models With Gradient Sign Dropout Highlight: We present Gradient Sign Dropout (GradDrop), a probabilistic masking procedure which samples gradients at an activation layer based on their level of consistency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhao Chen; Jiquan Ngiam; Yanping Huang; Thang Luong; Henrik Kretzschmar; Yuning Chai; Dragomir Anguelov; | |
| 173 | A Loss Function For Generative Neural Networks Based On Watson�s Perceptual Model Highlight: We propose such a loss function based on Watson’s perceptual model, which computes a weighted distance in frequency space and accounts for luminance and contrast masking. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Steffen Czolbe; Oswin Krause; Ingemar Cox; Christian Igel; | |
| 174 | Dynamic Fusion Of Eye Movement Data And Verbal Narrations In Knowledge-rich Domains Highlight: We propose to jointly analyze experts’ eye movements and verbal narrations to discover important and interpretable knowledge patterns to better understand their decision-making processes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ervine Zheng; Qi Yu; Rui Li; Pengcheng Shi; Anne Haake; | |
| 175 | Scalable Multi-Agent Reinforcement Learning For Networked Systems With Average Reward Highlight: In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guannan Qu; Yiheng Lin; Adam Wierman; Na Li; | |
| 176 | Optimizing Neural Networks Via Koopman Operator Theory Highlight: Koopman operator theory, a powerful framework for discovering the underlying dynamics of nonlinear dynamical systems, was recently shown to be intimately connected with neural network training. In this work, we take the first steps in making use of this connection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Akshunna Dogra; William Redman; | |
| 177 | SVGD As A Kernelized Wasserstein Gradient Flow Of The Chi-squared Divergence Highlight: We introduce a new perspective on SVGD that instead views SVGD as the kernelized gradient flow of the chi-squared divergence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sinho Chewi; Thibaut Le Gouic; Chen Lu; Tyler Maunu; Philippe Rigollet; | |
| 178 | Adversarial Robustness Of Supervised Sparse Coding Highlight: In this work, we strike a better balance by considering a model that involves learning a representation while at the same time giving a precise generalization bound and a robustness certificate. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeremias Sulam; Ramchandran Muthukumar; Raman Arora; | |
| 179 | Differentiable Meta-Learning Of Bandit Policies Highlight: In this work, we learn such policies for an unknown distribution P using samples from P. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Craig Boutilier; Chih-wei Hsu; Branislav Kveton; Martin Mladenov; Csaba Szepesvari; Manzil Zaheer; | |
| 180 | Biologically Inspired Mechanisms For Adversarial Robustness Highlight: In this work, we investigate the role of two biologically plausible mechanisms in adversarial robustness. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Manish Vuyyuru Reddy; Andrzej Banburski; Nishka Pant; Tomaso Poggio; | |
| 181 | Statistical-Query Lower Bounds Via Functional Gradients Highlight: For the specific problem of ReLU regression (equivalently, agnostically learning a ReLU), we show that any statistical-query algorithm with tolerance $n^{-(1/\epsilon)^b}$ must use at least $2^{n^c} \epsilon$ queries for some constants $b, c > 0$, where $n$ is the dimension and $\epsilon$ is the accuracy parameter. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Surbhi Goel; Aravind Gollakota; Adam Klivans; | |
| 182 | Near-Optimal Reinforcement Learning With Self-Play Highlight: This paper closes this gap for the first time: we propose an optimistic variant of the Nash Q-learning algorithm with sample complexity \tlO(SAB), and a new Nash V-learning algorithm with sample complexity \tlO(S(A+B)). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu Bai; Chi Jin; Tiancheng Yu; | |
| 183 | Network Diffusions Via Neural Mean-Field Dynamics Highlight: We propose a novel learning framework based on neural mean-field dynamics for inference and estimation problems of diffusion on networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shushan He; Hongyuan Zha; Xiaojing Ye; | |
| 184 | Self-Distillation As Instance-Specific Label Smoothing Highlight: With this in mind, we offer a new interpretation for teacher-student training as amortized MAP estimation, such that teacher predictions enable instance-specific regularization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhilu Zhang; Mert Sabuncu; | |
| 185 | Towards Problem-dependent Optimal Learning Rates Highlight: In this paper we propose a new framework based on a "uniform localized convergence" principle. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunbei Xu; Assaf Zeevi; | |
| 186 | Cross-lingual Retrieval For Iterative Self-Supervised Training Highlight: In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs mined using their own encoder outputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chau Tran; Yuqing Tang; Xian Li; Jiatao Gu; | |
| 187 | Rethinking Pooling In Graph Neural Networks Highlight: In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Diego Mesquita; Amauri Souza; Samuel Kaski; | |
| 188 | Pointer Graph Networks Highlight: Here we introduce Pointer Graph Networks (PGNs) which augment sets or graphs with additional inferred edges for improved model generalisation ability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Petar Velickovic; Lars Buesing; Matthew Overlan; Razvan Pascanu; Oriol Vinyals; Charles Blundell; | |
| 189 | Gradient Regularized V-Learning For Dynamic Treatment Regimes Highlight: In this paper, we introduce Gradient Regularized V-learning (GRV), a novel method for estimating the value function of a DTR. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yao Zhang; Mihaela van der Schaar; | |
| 190 | Faster Wasserstein Distance Estimation With The Sinkhorn Divergence Highlight: In this work, we propose instead to estimate it with the Sinkhorn divergence, which is also built on entropic regularization but includes debiasing terms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
L�na�c Chizat; Pierre Roussillon; Flavien L�ger; Fran�ois-Xavier Vialard; Gabriel Peyr�; | |
| 191 | Forethought And Hindsight In Credit Assignment Highlight: We address the problem of credit assignment in reinforcement learning and explore fundamental questions regarding the way in which an agent can best use additional computation to propagate new information, by planning with internal models of the world to improve its predictions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Veronica Chelu; Doina Precup; Hado P. van Hasselt; | |
| 192 | Robust Recursive Partitioning For Heterogeneous Treatment Effects With Uncertainty Quantification Highlight: This paper develops a new method for subgroup analysis, R2P, that addresses all these weaknesses. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hyun-Suk Lee; Yao Zhang; William Zame; Cong Shen; Jang-Won Lee; Mihaela van der Schaar; | |
| 193 | Rescuing Neural Spike Train Models From Bad MLE Highlight: To alleviate this, we propose to directly minimize the divergence between neural recorded and model generated spike trains using spike train kernels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Diego Arribas; Yuan Zhao; Il Memming Park; | |
| 194 | Lower Bounds And Optimal Algorithms For Personalized Federated Learning Highlight: In this work, we consider the optimization formulation of personalized federated learning recently introduced by Hanzely & Richtarik (2020) which was shown to give an alternative explanation to the workings of local SGD methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Filip Hanzely; Slavom�r Hanzely; Samuel Horv�th; Peter Richtarik; | |
| 195 | Black-Box Certification With Randomized Smoothing: A Functional Optimization Based Framework Highlight: We propose a general framework of adversarial certification with non-Gaussian noise and for more general types of attacks, from a unified \functional optimization perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dinghuai Zhang; Mao Ye; Chengyue Gong; Zhanxing Zhu; Qiang Liu; | |
| 196 | Deep Imitation Learning For Bimanual Robotic Manipulation Highlight: We present a deep imitation learning framework for robotic bimanual manipulation in a continuous state-action space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fan Xie; Alexander Chowdhury; M. Clara De Paolis Kaluza; Linfeng Zhao; Lawson Wong; Rose Yu; | code |
| 197 | Stationary Activations For Uncertainty Calibration In Deep Learning Highlight: We introduce a new family of non-linear neural network activation functions that mimic the properties induced by the widely-used Mat\’ern family of kernels in Gaussian process (GP) models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lassi Meronen; Christabella Irwanto; Arno Solin; | |
| 198 | Ensemble Distillation For Robust Model Fusion In Federated Learning Highlight: In this work we investigate more powerful and more flexible aggregation schemes for FL. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tao Lin; Lingjing Kong; Sebastian U. Stich; Martin Jaggi; | |
| 199 | Falcon: Fast Spectral Inference On Encrypted Data Highlight: In this paper, we propose a fast, frequency-domain deep neural network called Falcon, for fast inferences on encrypted data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qian Lou; Wen-jie Lu; Cheng Hong; Lei Jiang; | |
| 200 | On Power Laws In Deep Ensembles Highlight: In this work, we focus on a classification problem and investigate the behavior of both non-calibrated and calibrated negative log-likelihood (CNLL) of a deep ensemble as a function of the ensemble size and the member network size. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ekaterina Lobacheva; Nadezhda Chirkova; Maxim Kodryan; Dmitry P. Vetrov; | |
| 201 | Practical Quasi-Newton Methods For Training Deep Neural Networks Highlight: We consider the development of practical stochastic quasi-Newton, and in particular Kronecker-factored block diagonal BFGS and L-BFGS methods, for training deep neural networks (DNNs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Donald Goldfarb; Yi Ren; Achraf Bahamou; | |
| 202 | Approximation Based Variance Reduction For Reparameterization Gradients Highlight: In this work we present a control variate that is applicable for any reparameterizable distribution with known mean and covariance, e.g. Gaussians with any covariance structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tomas Geffner; Justin Domke; | |
| 203 | Inference Stage Optimization For Cross-scenario 3D Human Pose Estimation Highlight: In this work, we propose a novel framework, Inference Stage Optimization (ISO), for improving the generalizability of 3D pose models when source and target data come from different pose distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianfeng Zhang; Xuecheng Nie; Jiashi Feng; | |
| 204 | Consistent Feature Selection For Analytic Deep Neural Networks Highlight: In this work, we investigate the problem of feature selection for analytic deep networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vu C. Dinh; Lam S. Ho; | |
| 205 | Glance And Focus: A Dynamic Approach To Reducing Spatial Redundancy In Image Classification Highlight: Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yulin Wang; Kangchen Lv; Rui Huang; Shiji Song; Le Yang; Gao Huang; | code |
| 206 | Information Maximization For Few-Shot Learning Highlight: We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Malik Boudiaf; Imtiaz Ziko; J�r�me Rony; Jose Dolz; Pablo Piantanida; Ismail Ben Ayed; | |
| 207 | Inverse Reinforcement Learning From A Gradient-based Learner Highlight: In this paper, we propose a new algorithm for this setting, in which the goal is to recover the reward function being optimized by an agent, given a sequence of policies produced during learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Giorgia Ramponi; Gianluca Drappo; Marcello Restelli; | |
| 208 | Bayesian Multi-type Mean Field Multi-agent Imitation Learning Highlight: In this paper, we proposed Bayesian multi-type mean field multi-agent imitation learning (BM3IL). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fan Yang; Alina Vereshchaka; Changyou Chen; Wen Dong; | |
| 209 | Bayesian Robust Optimization For Imitation Learning Highlight: To provide a bridge between these two extremes, we propose Bayesian Robust Optimization for Imitation Learning (BROIL). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniel Brown; Scott Niekum; Marek Petrik; | |
| 210 | Multiview Neural Surface Reconstruction By Disentangling Geometry And Appearance Highlight: In this work we address the challenging problem of multiview 3D surface reconstruction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lior Yariv; Yoni Kasten; Dror Moran; Meirav Galun; Matan Atzmon; Basri Ronen; Yaron Lipman; | |
| 211 | Riemannian Continuous Normalizing Flows Highlight: To overcome this problem, we introduce Riemannian continuous normalizing flows, a model which admits the parametrization of flexible probability measures on smooth manifolds by defining flows as the solution to ordinary differential equations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emile Mathieu; Maximilian Nickel; | |
| 212 | Attention-Gated Brain Propagation: How The Brain Can Implement Reward-based Error Backpropagation Highlight: We demonstrate a biologically plausible reinforcement learning scheme for deep networks with an arbitrary number of layers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Isabella Pozzi; Sander Bohte; Pieter Roelfsema; | |
| 213 | Asymptotic Guarantees For Generative Modeling Based On The Smooth Wasserstein Distance Highlight: In this work, we conduct a thorough statistical study of the minimum smooth Wasserstein estimators (MSWEs), first proving the estimator’s measurability and asymptotic consistency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziv Goldfeld; Kristjan Greenewald; Kengo Kato; | |
| 214 | Online Robust Regression Via SGD On The L1 Loss Highlight: In contrast, we show in this work that stochastic gradient descent on the l1 loss converges to the true parameter vector at a $\tilde{O}( 1 / (1 – \eta)^2 n )$ rate which is independent of the values of the contaminated measurements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Scott Pesme; Nicolas Flammarion; | |
| 215 | PRANK: Motion Prediction Based On RANKing Highlight: In this paper, we introduce the PRANK method, which satisfies these requirements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuriy Biktairov; Maxim Stebelev; Irina Rudenko; Oleh Shliazhko; Boris Yangel; | |
| 216 | Fighting Copycat Agents In Behavioral Cloning From Observation Histories Highlight: To combat this "copycat problem", we propose an adversarial approach to learn a feature representation that removes excess information about the previous expert action nuisance correlate, while retaining the information necessary to predict the next action. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chuan Wen; Jierui Lin; Trevor Darrell; Dinesh Jayaraman; Yang Gao; | |
| 217 | Tight Nonparametric Convergence Rates For Stochastic Gradient Descent Under The Noiseless Linear Model Highlight: We analyze the convergence of single-pass, fixed step-size stochastic gradient descent on the least-square risk under this model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rapha�l Berthier; Francis Bach; Pierre Gaillard; | |
| 218 | Structured Prediction For Conditional Meta-Learning Highlight: In this work, we propose a new perspective on conditional meta-learning via structured prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruohan Wang; Yiannis Demiris; Carlo Ciliberto; | |
| 219 | Optimal Lottery Tickets Via Subset Sum: Logarithmic Over-Parameterization Is Sufficient Highlight: In this work, we close the gap and offer an exponential improvement to the over-parameterization requirement for the existence of lottery tickets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ankit Pensia; Shashank Rajput; Alliot Nagle; Harit Vishwakarma; Dimitris Papailiopoulos; | |
| 220 | The Hateful Memes Challenge: Detecting Hate Speech In Multimodal Memes Highlight: This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Douwe Kiela; Hamed Firooz; Aravind Mohan; Vedanuj Goswami; Amanpreet Singh; Pratik Ringshia; Davide Testuggine; | |
| 221 | Stochasticity Of Deterministic Gradient Descent: Large Learning Rate For Multiscale Objective Function Highlight: This article suggests that deterministic Gradient Descent, which does not use any stochastic gradient approximation, can still exhibit stochastic behaviors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lingkai Kong; Molei Tao; | |
| 222 | Identifying Learning Rules From Neural Network Observables Highlight: It is an open question as to what specific experimental measurements would need to be made to determine whether any given learning rule is operative in a real biological system. In this work, we take a "virtual experimental" approach to this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aran Nayebi; Sanjana Srivastava; Surya Ganguli; Daniel L. Yamins; | |
| 223 | Optimal Approximation – Smoothness Tradeoffs For Soft-Max Functions Highlight: Our goal is to identify the optimal approximation-smoothness tradeoffs for different measures of approximation and smoothness. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alessandro Epasto; Mohammad Mahdian; Vahab Mirrokni; Emmanouil Zampetakis; | |
| 224 | Weakly-Supervised Reinforcement Learning For Controllable Behavior Highlight: In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lisa Lee; Ben Eysenbach; Russ R. Salakhutdinov; Shixiang (Shane) Gu; Chelsea Finn; | |
| 225 | Improving Policy-Constrained Kidney Exchange Via Pre-Screening Highlight: We propose both a greedy heuristic and a Monte Carlo tree search, which outperforms previous approaches, using experiments on both synthetic data and real kidney exchange data from the United Network for Organ Sharing. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Duncan McElfresh; Michael Curry; Tuomas Sandholm; John Dickerson; | |
| 226 | Learning Abstract Structure For Drawing By Efficient Motor Program Induction Highlight: We show that people spontaneously learn abstract drawing procedures that support generalization, and propose a model of how learners can discover these reusable drawing procedures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lucas Tian; Kevin Ellis; Marta Kryven; Josh Tenenbaum; | |
| 227 | Why Do Deep Residual Networks Generalize Better Than Deep Feedforward Networks? — A Neural Tangent Kernel Perspective Highlight: This paper studies this fundamental problem in deep learning from a so-called neural tangent kernel” perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaixuan Huang; Yuqing Wang; Molei Tao; Tuo Zhao; | |
| 228 | Dual Instrumental Variable Regression Highlight: We present a novel algorithm for non-linear instrumental variable (IV) regression, DualIV, which simplifies traditional two-stage methods via a dual formulation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Krikamol Muandet; Arash Mehrjou; Si Kai Lee; Anant Raj; | |
| 229 | Stochastic Gradient Descent In Correlated Settings: A Study On Gaussian Processes Highlight: In this paper, we focus on the Gaussian process (GP) and take a step forward towards breaking the barrier by proving minibatch SGD converges to a critical point of the full loss function, and recovers model hyperparameters with rate $O(\frac{1}{K})$ up to a statistical error term depending on the minibatch size. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hao Chen; Lili Zheng; Raed AL Kontar; Garvesh Raskutti; | |
| 230 | Interventional Few-Shot Learning Highlight: Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhongqi Yue; Hanwang Zhang; Qianru Sun; Xian-Sheng Hua; | code |
| 231 | Minimax Value Interval For Off-Policy Evaluation And Policy Optimization Highlight: We study minimax methods for off-policy evaluation (OPE) using value functions and marginalized importance weights. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nan Jiang; Jiawei Huang; | |
| 232 | Biased Stochastic First-Order Methods For Conditional Stochastic Optimization And Applications In Meta Learning Highlight: For this special setting, we propose an accelerated algorithm called biased SpiderBoost (BSpiderBoost) that matches the lower bound complexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yifan Hu; Siqi Zhang; Xin Chen; Niao He; | |
| 233 | ShiftAddNet: A Hardware-Inspired Deep Network Highlight: This paper presented ShiftAddNet, whose main inspiration is drawn from a common practice in energy-efficient hardware implementation, that is, multiplication can be instead performed with additions and logical bit-shifts. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haoran You; Xiaohan Chen; Yongan Zhang; Chaojian Li; Sicheng Li; Zihao Liu; Zhangyang Wang; Yingyan Lin; | code |
| 234 | Network-to-Network Translation With Conditional Invertible Neural Networks Highlight: Therefore, we seek a model that can relate between different existing representations and propose to solve this task with a conditionally invertible network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Robin Rombach; Patrick Esser; Bjorn Ommer; | |
| 235 | Intra-Processing Methods For Debiasing Neural Networks Highlight: In this work, we initiate the study of a new paradigm in debiasing research, intra-processing, which sits between in-processing and post-processing methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yash Savani; Colin White; Naveen Sundar Govindarajulu; | code |
| 236 | Finding Second-Order Stationary Points Efficiently In Smooth Nonconvex Linearly Constrained Optimization Problems Highlight: This paper proposes two efficient algorithms for computing approximate second-order stationary points (SOSPs) of problems with generic smooth non-convex objective functions and generic linear constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Songtao Lu; Meisam Razaviyayn; Bo Yang; Kejun Huang; Mingyi Hong; | |
| 237 | Model-based Policy Optimization With Unsupervised Model Adaptation Highlight: In this paper, we investigate how to bridge the gap between real and simulated data due to inaccurate model estimation for better policy optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jian Shen; Han Zhao; Weinan Zhang; Yong Yu; | |
| 238 | Implicit Regularization And Convergence For Weight Normalization Highlight: Here, we study the weight normalization (WN) method \cite{salimans2016weight} and a variant called reparametrized projected gradient descent (rPGD) for overparametrized least squares regression and some more general loss functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaoxia Wu; Edgar Dobriban; Tongzheng Ren; Shanshan Wu; Zhiyuan Li; Suriya Gunasekar; Rachel Ward; Qiang Liu; | |
| 239 | Geometric All-way Boolean Tensor Decomposition Highlight: In this work, we presented a computationally efficient BTD algorithm, namely Geometric Expansion for all-order Tensor Factorization (GETF), that sequentially identifies the rank-1 basis components for a tensor from a geometric perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Changlin Wan; Wennan Chang; Tong Zhao; Sha Cao; Chi Zhang; | |
| 240 | Modular Meta-Learning With Shrinkage Highlight: Here, we propose a meta-learning approach that obviates the need for this often sub-optimal hand-selection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yutian Chen; Abram L. Friesen; Feryal Behbahani; Arnaud Doucet; David Budden; Matthew Hoffman; Nando de Freitas; | |
| 241 | A/B Testing In Dense Large-Scale Networks: Design And Inference Highlight: In this paper, we present a novel strategy for accurately estimating the causal effects of a class of treatments in a dense large-scale network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Preetam Nandy; Kinjal Basu; Shaunak Chatterjee; Ye Tu; | |
| 242 | What Neural Networks Memorize And Why: Discovering The Long Tail Via Influence Estimation Highlight: In this work we design experiments to test the key ideas in this theory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vitaly Feldman; Chiyuan Zhang; | |
| 243 | Partially View-aligned Clustering Highlight: In this paper, we study one challenging issue in multi-view data clustering. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhenyu Huang; Peng Hu; Joey Tianyi Zhou; Jiancheng Lv; Xi Peng; | |
| 244 | Partial Optimal Tranport With Applications On Positive-Unlabeled Learning Highlight: In this paper, we address the partial Wasserstein and Gromov-Wasserstein problems and propose exact algorithms to solve them. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Laetitia Chapel; Mokhtar Z. Alaya / Laboratoire LITIS; Universit� de Rouen Normandie; Gilles Gasso; | |
| 245 | Toward The Fundamental Limits Of Imitation Learning Highlight: In this paper, we focus on understanding the minimax statistical limits of IL in episodic Markov Decision Processes (MDPs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nived Rajaraman; Lin Yang; Jiantao Jiao; Kannan Ramchandran; | |
| 246 | Logarithmic Pruning Is All You Need Highlight: In this work, we remove the most limiting assumptions of this previous work while providing significantly tighter bounds: the overparameterized network only needs a logarithmic factor (in all variables but depth) number of neurons per weight of the target subnetwork. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Laurent Orseau; Marcus Hutter; Omar Rivasplata; | |
| 247 | Hold Me Tight! Influence Of Discriminative Features On Deep Network Boundaries Highlight: In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates dataset features to the distance of samples to the decision boundary. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guillermo Ortiz-Jimenez; Apostolos Modas; Seyed-Mohsen Moosavi-Dezfooli; Pascal Frossard; | |
| 248 | Learning From Mixtures Of Private And Public Populations Highlight: Inspired by the above example, we consider a model in which the population $\cD$ is a mixture of two possibly distinct sub-populations: a private sub-population $\Dprv$ of private and sensitive data, and a public sub-population $\Dpub$ of data with no privacy concerns. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Raef Bassily; Shay Moran; Anupama Nandi; | |
| 249 | Adversarial Weight Perturbation Helps Robust Generalization Highlight: In this paper, we investigate the weight loss landscape from a new perspective, and identify a clear correlation between the flatness of weight loss landscape and robust generalization gap. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dongxian Wu; Shu-Tao Xia; Yisen Wang; | |
| 250 | Stateful Posted Pricing With Vanishing Regret Via Dynamic Deterministic Markov Decision Processes Highlight: In this paper, a rather general online problem called \emph{dynamic resource allocation with capacity constraints (DRACC)} is introduced and studied in the realm of posted price mechanisms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuval Emek; Ron Lavi; Rad Niazadeh; Yangguang Shi; | |
| 251 | Adversarial Self-Supervised Contrastive Learning Highlight: In this paper, we propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minseon Kim; Jihoon Tack; Sung Ju Hwang; | |
| 252 | Normalizing Kalman Filters For Multivariate Time Series Analysis Highlight: To this extent, we present a novel approach reconciling classical state space models with deep learning methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emmanuel de B�zenac; Syama Sundar Rangapuram; Konstantinos Benidis; Michael Bohlke-Schneider; Richard Kurle; Lorenzo Stella; Hilaf Hasson; Patrick Gallinari; Tim Januschowski; | |
| 253 | Learning To Summarize With Human Feedback Highlight: In this work, we show that it is possible to significantly improve summary quality by training a model to optimize for human preferences. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nisan Stiennon; Long Ouyang; Jeffrey Wu; Daniel Ziegler; Ryan Lowe; Chelsea Voss; Alec Radford; Dario Amodei; Paul F. Christiano; | |
| 254 | Fourier Spectrum Discrepancies In Deep Network Generated Images Highlight: In this paper, we present an analysis of the high-frequency Fourier modes of real and deep network generated images and show that deep network generated images share an observable, systematic shortcoming in replicating the attributes of these high-frequency modes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tarik Dzanic; Karan Shah; Freddie Witherden; | |
| 255 | Lamina-specific Neuronal Properties Promote Robust, Stable Signal Propagation In Feedforward Networks Highlight: Specifically, we found that signal transformations, made by each layer of neurons on an input-driven spike signal, demodulate signal distortions introduced by preceding layers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dongqi Han; Erik De Schutter; Sungho Hong; | |
| 256 | Learning Dynamic Belief Graphs To Generalize On Text-Based Games Highlight: In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ashutosh Adhikari; Xingdi Yuan; Marc-Alexandre C�t�; Mikul� Zelinka; Marc-Antoine Rondeau; Romain Laroche; Pascal Poupart; Jian Tang; Adam Trischler; Will Hamilton; | |
| 257 | Triple Descent And The Two Kinds Of Overfitting: Where & Why Do They Appear? Highlight: In this paper, we show that despite their apparent similarity, these two scenarios are inherently different. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
St�phane d'Ascoli; Levent Sagun; Giulio Biroli; | |
| 258 | Multimodal Graph Networks For Compositional Generalization In Visual Question Answering Highlight: In this paper, we propose to tackle this challenge by employing neural factor graphs to induce a tighter coupling between concepts in different modalities (e.g. images and text). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Raeid Saqur; Karthik Narasimhan; | |
| 259 | Learning Graph Structure With A Finite-State Automaton Layer Highlight: In this work, we study the problem of learning to derive abstract relations from the intrinsic graph structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniel Johnson; Hugo Larochelle; Daniel Tarlow; | |
| 260 | A Universal Approximation Theorem Of Deep Neural Networks For Expressing Probability Distributions Highlight: This paper studies the universal approximation property of deep neural networks for representing probability distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yulong Lu; Jianfeng Lu; | |
| 261 | Unsupervised Object-centric Video Generation And Decomposition In 3D Highlight: We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Paul Henderson; Christoph H. Lampert; | |
| 262 | Domain Generalization For Medical Imaging Classification With Linear-Dependency Regularization Highlight: In this paper, we introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haoliang Li; Yufei Wang; Renjie Wan; Shiqi Wang; Tie-Qiang Li; Alex Kot; | |
| 263 | Multi-label Classification: Do Hamming Loss And Subset Accuracy Really Conflict With Each Other? Highlight: This paper provides an attempt to fill up this gap by analyzing the learning guarantees of the corresponding learning algorithms on both SA and HL measures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guoqiang Wu; Jun Zhu; | |
| 264 | A Novel Automated Curriculum Strategy To Solve Hard Sokoban Planning Instances Highlight: We present a novel {\em automated} curriculum approach that dynamically selects from a pool of unlabeled training instances of varying task complexity guided by our {\em difficulty quantum momentum} strategy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dieqiao Feng; Carla P. Gomes; Bart Selman; | |
| 265 | Causal Analysis Of Covid-19 Spread In Germany Highlight: In this work, we study the causal relations among German regions in terms of the spread of Covid-19 since the beginning of the pandemic, taking into account the restriction policies that were applied by the different federal states. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Atalanti Mastakouri; Bernhard Sch�lkopf; | |
| 266 | Locally Private Non-asymptotic Testing Of Discrete Distributions Is Faster Using Interactive Mechanisms Highlight: We find separation rates for testing multinomial or more general discrete distributions under the constraint of alpha-local differential privacy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thomas Berrett; Cristina Butucea; | |
| 267 | Adaptive Gradient Quantization For Data-Parallel SGD Highlight: We empirically observe that the statistics of gradients of deep models change during the training. Motivated by this observation, we introduce two adaptive quantization schemes, ALQ and AMQ. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fartash Faghri; Iman Tabrizian; Ilia Markov; Dan Alistarh; Daniel M. Roy; Ali Ramezani-Kebrya; | |
| 268 | Finite Continuum-Armed Bandits Highlight: Focusing on a nonparametric setting, where the mean reward is an unknown function of a one-dimensional covariate, we propose an optimal strategy for this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Solenne Gaucher; | |
| 269 | Removing Bias In Multi-modal Classifiers: Regularization By Maximizing Functional Entropies Highlight: To alleviate this shortcoming, we propose a novel regularization term based on the functional entropy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Itai Gat; Idan Schwartz; Alexander Schwing; Tamir Hazan; | |
| 270 | Compact Task Representations As A Normative Model For Higher-order Brain Activity Highlight: More specifically, we focus on MDPs whose state is based on action-observation histories, and we show how to compress the state space such that unnecessary redundancy is eliminated, while task-relevant information is preserved. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Severin Berger; Christian K. Machens; | |
| 271 | Robust-Adaptive Control Of Linear Systems: Beyond Quadratic Costs Highlight: We consider the problem of robust and adaptive model predictive control (MPC) of a linear system, with unknown parameters that are learned along the way (adaptive), in a critical setting where failures must be prevented (robust). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edouard Leurent; Odalric-Ambrym Maillard; Denis Efimov; | |
| 272 | Co-exposure Maximization In Online Social Networks Highlight: In this paper, we study the problem of allocating seed users to opposing campaigns: by drawing on the equal-time rule of political campaigning on traditional media, our goal is to allocate seed users to campaigners with the aim to maximize the expected number of users who are co-exposed to both campaigns. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sijing Tu; Cigdem Aslay; Aristides Gionis; | |
| 273 | UCLID-Net: Single View Reconstruction In Object Space Highlight: In this paper, we show that building a geometry preserving 3-dimensional latent space helps the network concurrently learn global shape regularities and local reasoning in the object coordinate space and, as a result, boosts performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benoit Guillard; Edoardo Remelli; Pascal Fua; | |
| 274 | Reinforcement Learning For Control With Multiple Frequencies Highlight: In this paper, we formalize the problem of multiple control frequencies in RL and provide its efficient solution method. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jongmin Lee; ByungJun Lee; Kee-Eung Kim; | |
| 275 | Complex Dynamics In Simple Neural Networks: Understanding Gradient Flow In Phase Retrieval Highlight: Here we focus on gradient flow dynamics for phase retrieval from random measurements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stefano Sarao Mannelli; Giulio Biroli; Chiara Cammarota; Florent Krzakala; Pierfrancesco Urbani; Lenka Zdeborov�; | |
| 276 | Neural Message Passing For Multi-Relational Ordered And Recursive Hypergraphs Highlight: In this work, we first unify exisiting MPNNs on different structures into G-MPNN (Generalised MPNN) framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Naganand Yadati; | |
| 277 | A Unified View Of Label Shift Estimation Highlight: In this paper, we present a unified view of the two methods and the first theoretical characterization of MLLS. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Saurabh Garg; Yifan Wu; Sivaraman Balakrishnan; Zachary Lipton; | |
| 278 | Optimal Private Median Estimation Under Minimal Distributional Assumptions Highlight: We study the fundamental task of estimating the median of an underlying distribution from a finite number of samples, under pure differential privacy constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christos Tzamos; Emmanouil-Vasileios Vlatakis-Gkaragkounis; Ilias Zadik; | |
| 279 | Breaking The Communication-Privacy-Accuracy Trilemma Highlight: In this paper, we develop novel encoding and decoding mechanisms that simultaneously achieve optimal privacy and communication efficiency in various canonical settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei-Ning Chen; Peter Kairouz; Ayfer Ozgur; | |
| 280 | Audeo: Audio Generation For A Silent Performance Video Highlight: Our main aim in this work is to explore the plausibility of such a transformation and to identify cues and components able to carry the association of sounds with visual events. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kun Su; Xiulong Liu; Eli Shlizerman; | |
| 281 | Ode To An ODE Highlight: We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Krzysztof M. Choromanski; Jared Quincy Davis; Valerii Likhosherstov; Xingyou Song; Jean-Jacques Slotine; Jacob Varley; Honglak Lee; Adrian Weller; Vikas Sindhwani; | |
| 282 | Self-Distillation Amplifies Regularization In Hilbert Space Highlight: This work provides the first theoretical analysis of self-distillation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hossein Mobahi; Mehrdad Farajtabar; Peter Bartlett; | |
| 283 | Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators Highlight: Without a universality, there could be a well-behaved invertible transformation that the CF-INN can never approximate, hence it would render the model class unreliable. We answer this question by showing a convenient criterion: a CF-INN is universal if its layers contain affine coupling and invertible linear functions as special cases. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Takeshi Teshima; Isao Ishikawa; Koichi Tojo; Kenta Oono; Masahiro Ikeda; Masashi Sugiyama; | |
| 284 | Community Detection Using Fast Low-cardinality Semidefinite Programming? Highlight: In this paper, we propose a new class of low-cardinality algorithm that generalizes the local update to maximize a semidefinite relaxation derived from max-k-cut. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Po-Wei Wang; J. Zico Kolter; | |
| 285 | Modeling Noisy Annotations For Crowd Counting Highlight: In this paper, we first model the annotation noise using a random variable with Gaussian distribution, and derive the pdf of the crowd density value for each spatial location in the image. We then approximate the joint distribution of the density values (i.e., the distribution of density maps) with a full covariance multivariate Gaussian density, and derive a low-rank approximate for tractable implementation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jia Wan; Antoni Chan; | |
| 286 | An Operator View Of Policy Gradient Methods Highlight: We cast policy gradient methods as the repeated application of two operators: a policy improvement operator $\mathcal{I}$, which maps any policy $\pi$ to a better one $\mathcal{I}\pi$, and a projection operator $\mathcal{P}$, which finds the best approximation of $\mathcal{I}\pi$ in the set of realizable policies. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dibya Ghosh; Marlos C. Machado; Nicolas Le Roux; | |
| 287 | Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations And Dataset Biases Highlight: Somewhat mysteriously the recent gains in performance come from training instance classification models, treating each image and it’s augmented versions as samples of a single class. In this work, we first present quantitative experiments to demystify these gains. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Senthil Purushwalkam Shiva Prakash; Abhinav Gupta; | |
| 288 | Online MAP Inference Of Determinantal Point Processes Highlight: In this paper, we provide an efficient approximation algorithm for finding the most likelihood configuration (MAP) of size $k$ for Determinantal Point Processes (DPP) in the online setting where the data points arrive in an arbitrary order and the algorithm cannot discard the selected elements from its local memory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aditya Bhaskara; Amin Karbasi; Silvio Lattanzi; Morteza Zadimoghaddam; | |
| 289 | Video Object Segmentation With Adaptive Feature Bank And Uncertain-Region Refinement Highlight: This paper presents a new matching-based framework for semi-supervised video object segmentation (VOS). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yongqing Liang; Xin Li; Navid Jafari; Jim Chen; | |
| 290 | Inferring Learning Rules From Animal Decision-making Highlight: Whereas reinforcement learning often focuses on the design of algorithms that enable artificial agents to efficiently learn new tasks, here we develop a modeling framework to directly infer the empirical learning rules that animals use to acquire new behaviors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zoe Ashwood; Nicholas A. Roy; Ji Hyun Bak; Jonathan W. Pillow; | |
| 291 | Input-Aware Dynamic Backdoor Attack Highlight: In this work, we propose a novel backdoor attack technique in which the triggers vary from input to input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tuan Anh Nguyen; Anh Tran; | |
| 292 | How Hard Is To Distinguish Graphs With Graph Neural Networks? Highlight: This study derives hardness results for the classification variant of graph isomorphism in the message-passing model (MPNN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andreas Loukas; | |
| 293 | Minimax Regret Of Switching-Constrained Online Convex Optimization: No Phase Transition Highlight: In this paper, we show that $ T $-round switching-constrained OCO with fewer than $ K $ switches has a minimax regret of $ \Theta(\frac{T}{\sqrt{K}}) $. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lin Chen; Qian Yu; Hannah Lawrence; Amin Karbasi; | |
| 294 | Dual Manifold Adversarial Robustness: Defense Against Lp And Non-Lp Adversarial Attacks Highlight: To partially answer this question, we consider the scenario when the manifold information of the underlying data is available. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei-An Lin; Chun Pong Lau; Alexander Levine; Rama Chellappa; Soheil Feizi; | |
| 295 | Cross-Scale Internal Graph Neural Network For Image Super-Resolution Highlight: In this paper, we explore the cross-scale patch recurrence property of a natural image, i.e., similar patches tend to recur many times across different scales. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shangchen Zhou; Jiawei Zhang; Wangmeng Zuo; Chen Change Loy; | |
| 296 | Unsupervised Representation Learning By Invariance Propagation Highlight: In this paper, we propose Invariance Propagation to focus on learning representations invariant to category-level variations, which are provided by different instances from the same category. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Feng Wang; Huaping Liu; Di Guo; Sun Fuchun; | |
| 297 | Restoring Negative Information In Few-Shot Object Detection Highlight: In this paper, we restore the negative information in few-shot object detection by introducing a new negative- and positive-representative based metric learning framework and a new inference scheme with negative and positive representatives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yukuan Yang; Fangyun Wei; Miaojing Shi; Guoqi Li; | code |
| 298 | Do Adversarially Robust ImageNet Models Transfer Better? Highlight: In this work, we identify another such aspect: we find that adversarially robust models, while less accurate, often perform better than their standard-trained counterparts when used for transfer learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hadi Salman; Andrew Ilyas; Logan Engstrom; Ashish Kapoor; Aleksander Madry; | |
| 299 | Robust Correction Of Sampling Bias Using Cumulative Distribution Functions Highlight: We present a new method for handling covariate shift using the empirical cumulative distribution function estimates of the target distribution by a rigorous generalization of a recent idea proposed by Vapnik and Izmailov. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bijan Mazaheri; Siddharth Jain; Jehoshua Bruck; | |
| 300 | Personalized Federated Learning With Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach Highlight: In this paper, we study a personalized variant of the federated learning in which our goal is to find an initial shared model that current or new users can easily adapt to their local dataset by performing one or a few steps of gradient descent with respect to their own data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alireza Fallah; Aryan Mokhtari; Asuman Ozdaglar; | |
| 301 | Pixel-Level Cycle Association: A New Perspective For Domain Adaptive Semantic Segmentation Highlight: In this paper, we propose to build the pixel-level cycle association between source and target pixel pairs and contrastively strengthen their connections to diminish the domain gap and make the features more discriminative. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guoliang Kang; Yunchao Wei; Yi Yang; Yueting Zhuang; Alexander Hauptmann; | code |
| 302 | Classification With Valid And Adaptive Coverage Highlight: In this paper, we develop specialized versions of these techniques for categorical and unordered response labels that, in addition to providing marginal coverage, are also fully adaptive to complex data distributions, in the sense that they perform favorably in terms of approximate conditional coverage compared to alternative methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaniv Romano; Matteo Sesia; Emmanuel Candes; | |
| 303 | Learning Global Transparent Models Consistent With Local Contrastive Explanations Highlight: In this work, we explore the question: Can we produce a transparent global model that is simultaneously accurate and consistent with the local (contrastive) explanations of the black-box model? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tejaswini Pedapati; Avinash Balakrishnan; Karthikeyan Shanmugam; Amit Dhurandhar; | |
| 304 | Learning To Approximate A Bregman Divergence Highlight: In this paper, we focus on the problem of approximating an arbitrary Bregman divergence from supervision, and we provide a well-principled approach to analyzing such approximations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ali Siahkamari; XIDE XIA; Venkatesh Saligrama; David Casta��n; Brian Kulis; | |
| 305 | Diverse Image Captioning With Context-Object Split Latent Spaces Highlight: To this end, we introduce a novel factorization of the latent space, termed context-object split, to model diversity in contextual descriptions across images and texts within the dataset. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shweta Mahajan; Stefan Roth; | |
| 306 | Learning Disentangled Representations Of Videos With Missing Data Highlight: We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in the presence of missing data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Armand Comas; Chi Zhang; Zlatan Feric; Octavia Camps; Rose Yu; | code |
| 307 | Natural Graph Networks Highlight: Here we show that instead of equivariance, the more general concept of naturality is sufficient for a graph network to be well-defined, opening up a larger class of graph networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pim de Haan; Taco S. Cohen; Max Welling; | |
| 308 | Continual Learning With Node-Importance Based Adaptive Group Sparse Regularization Highlight: We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based penalties. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sangwon Jung; Hongjoon Ahn; Sungmin Cha; Taesup Moon; | |
| 309 | Towards Crowdsourced Training Of Large Neural Networks Using Decentralized Mixture-of-Experts Highlight: In this work, we propose Learning@home: a novel neural network training paradigm designed to handle large amounts of poorly connected participants. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maksim Riabinin; Anton Gusev; | |
| 310 | Bidirectional Convolutional Poisson Gamma Dynamical Systems Highlight: Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
wenchao chen; Chaojie Wang; Bo Chen; Yicheng Liu; Hao Zhang; Mingyuan Zhou; | |
| 311 | Deep Reinforcement And InfoMax Learning Highlight: To test that hypothesis, we introduce an objective based on Deep InfoMax (DIM) which trains the agent to predict the future by maximizing the mutual information between its internal representation of successive timesteps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bogdan Mazoure; Remi Tachet des Combes; Thang Long DOAN; Philip Bachman; R Devon Hjelm; | |
| 312 | On Ranking Via Sorting By Estimated Expected Utility Highlight: We provide an answer to this question in the form of a structural characterization of ranking losses for which a suitable regression is consistent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Clement Calauzenes; Nicolas Usunier; | |
| 313 | Distribution-free Binary Classification: Prediction Sets, Confidence Intervals And Calibration Highlight: We study three notions of uncertainty quantification—calibration, confidence intervals and prediction sets—for binary classification in the distribution-free setting, that is without making any distributional assumptions on the data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chirag Gupta; Aleksandr Podkopaev; Aaditya Ramdas; | |
| 314 | Closing The Dequantization Gap: PixelCNN As A Single-Layer Flow Highlight: In this paper, we introduce subset flows, a class of flows that can tractably transform finite volumes and thus allow exact computation of likelihoods for discrete data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Didrik Nielsen; Ole Winther; | |
| 315 | Sequence To Multi-Sequence Learning Via Conditional Chain Mapping For Mixture Signals Highlight: In this work, we focus on one-to-many sequence transduction problems, such as extracting multiple sequential sources from a mixture sequence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jing Shi; Xuankai Chang; Pengcheng Guo; Shinji Watanabe; Yusuke Fujita; Jiaming Xu; Bo Xu; Lei Xie; | |
| 316 | Variance Reduction For Random Coordinate Descent-Langevin Monte Carlo Highlight: We show by a counterexamplethat blindly applying RCD does not achieve the goal in the most general setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
ZHIYAN DING; Qin Li; | |
| 317 | Language As A Cognitive Tool To Imagine Goals In Curiosity Driven Exploration Highlight: We introduce IMAGINE, an intrinsically motivated deep reinforcement learning architecture that models this ability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
C�dric Colas; Tristan Karch; Nicolas Lair; Jean-Michel Dussoux; Cl�ment Moulin-Frier; Peter Dominey; Pierre-Yves Oudeyer; | |
| 318 | All Word Embeddings From One Embedding Highlight: In this study, to reduce the total number of parameters, the embeddings for all words are represented by transforming a shared embedding. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sho Takase; Sosuke Kobayashi; | |
| 319 | Primal Dual Interpretation Of The Proximal Stochastic Gradient Langevin Algorithm Highlight: We consider the task of sampling with respect to a log concave probability distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adil SALIM; Peter Richtarik; | |
| 320 | How To Characterize The Landscape Of Overparameterized Convolutional Neural Networks Highlight: Specifically, we consider the loss landscape of an overparameterized convolutional neural network (CNN) in the continuous limit, where the numbers of channels/hidden nodes in the hidden layers go to infinity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yihong Gu; Weizhong Zhang; Cong Fang; Jason D. Lee; Tong Zhang; | |
| 321 | On The Tightness Of Semidefinite Relaxations For Certifying Robustness To Adversarial Examples Highlight: In this paper, we describe a geometric technique that determines whether this SDP certificate is exact, meaning whether it provides both a lower-bound on the size of the smallest adversarial perturbation, as well as a globally optimal perturbation that attains the lower-bound. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Richard Zhang; | |
| 322 | Submodular Meta-Learning Highlight: In this paper, we introduce a discrete variant of the Meta-learning framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arman Adibi; Aryan Mokhtari; Hamed Hassani; | |
| 323 | Rethinking Pre-training And Self-training Highlight: Our study reveals the generality and flexibility of self-training with three additional insights: 1) stronger data augmentation and more labeled data further diminish the value of pre-training, 2) unlike pre-training, self-training is always helpful when using stronger data augmentation, in both low-data and high-data regimes, and 3) in the case that pre-training is helpful, self-training improves upon pre-training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Barret Zoph; Golnaz Ghiasi; Tsung-Yi Lin; Yin Cui; Hanxiao Liu; Ekin Dogus Cubuk; Quoc Le; | |
| 324 | Unsupervised Sound Separation Using Mixture Invariant Training Highlight: In this paper, we propose a completely unsupervised method, mixture invariant training (MixIT), that requires only single-channel acoustic mixtures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Scott Wisdom; Efthymios Tzinis; Hakan Erdogan; Ron Weiss; Kevin Wilson; John Hershey; | |
| 325 | Adaptive Discretization For Model-Based Reinforcement Learning Highlight: We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sean Sinclair; Tianyu Wang; Gauri Jain; Siddhartha Banerjee; Christina Yu; | |
| 326 | CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching Highlight: This paper proposes an end-to-end cross-modal retrieval network for binary source code matching, which achieves higher accuracy and requires less expert experience. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zeping Yu; Wenxin Zheng; Jiaqi Wang; Qiyi Tang; Sen Nie; Shi Wu; | |
| 327 | On Warm-Starting Neural Network Training Highlight: In this work, we take a closer look at this empirical phenomenon and try to understand when and how it occurs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jordan Ash; Ryan P. Adams; | |
| 328 | DAGs With No Fears: A Closer Look At Continuous Optimization For Learning Bayesian Networks Highlight: Informed by the KKT conditions, a local search post-processing algorithm is proposed and shown to substantially and universally improve the structural Hamming distance of all tested algorithms, typically by a factor of 2 or more. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dennis Wei; Tian Gao; yue yu; | |
| 329 | OOD-MAML: Meta-Learning For Few-Shot Out-of-Distribution Detection And Classification Highlight: We propose a few-shot learning method for detecting out-of-distribution (OOD) samples from classes that are unseen during training while classifying samples from seen classes using only a few labeled examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Taewon Jeong; Heeyoung Kim; | |
| 330 | An Imitation From Observation Approach To Transfer Learning With Dynamics Mismatch Highlight: In this paper, we show that one existing solution to this transfer problem– grounded action transformation –is closely related to the problem of imitation from observation (IfO): learning behaviors that mimic the observations of behavior demonstrations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siddharth Desai; Ishan Durugkar; Haresh Karnan; Garrett Warnell; Josiah Hanna; Peter Stone; | |
| 331 | Learning About Objects By Learning To Interact With Them Highlight: Taking inspiration from infants learning from their environment through play and interaction, we present a computational framework to discover objects and learn their physical properties along this paradigm of Learning from Interaction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Martin Lohmann; Jordi Salvador; Aniruddha Kembhavi; Roozbeh Mottaghi; | |
| 332 | Learning Discrete Distributions With Infinite Support Highlight: We present a novel approach to estimating discrete distributions with (potentially) infinite support in the total variation metric. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Doron Cohen; Aryeh Kontorovich; Geo?rey Wolfer; | |
| 333 | Dissecting Neural ODEs Highlight: In this work we “open the box”, further developing the continuous-depth formulation with the aim of clarifying the influence of several design choices on the underlying dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stefano Massaroli; Michael Poli; Jinkyoo Park; Atsushi Yamashita; edit Hajime Asama; | |
| 334 | Teaching A GAN What Not To Learn Highlight: In this paper, we approach the supervised GAN problem from a different perspective, one that is motivated by the philosophy of the famous Persian poet Rumi who said, "The art of knowing is knowing what to ignore." Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siddarth Asokan; Chandra Seelamantula; | |
| 335 | Counterfactual Data Augmentation Using Locally Factored Dynamics Highlight: We propose an approach to inferring these structures given an object-oriented state representation, as well as a novel algorithm for Counterfactual Data Augmentation (CoDA). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Silviu Pitis; Elliot Creager; Animesh Garg; | code |
| 336 | Rethinking Learnable Tree Filter For Generic Feature Transform Highlight: To relax the geometric constraint, we give the analysis by reformulating it as a Markov Random Field and introduce a learnable unary term. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lin Song; Yanwei Li; Zhengkai Jiang; Zeming Li; Xiangyu Zhang; Hongbin Sun; Jian Sun; Nanning Zheng; | code |
| 337 | Self-Supervised Relational Reasoning For Representation Learning Highlight: In this work, we propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Massimiliano Patacchiola; Amos J. Storkey; | |
| 338 | Sufficient Dimension Reduction For Classification Using Principal Optimal Transport Direction Highlight: To address this issue, we propose a novel estimation method of sufficient dimension reduction subspace (SDR subspace) using optimal transport. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cheng Meng; Jun Yu; Jingyi Zhang; Ping Ma; Wenxuan Zhong; | |
| 339 | Fast Epigraphical Projection-based Incremental Algorithms For Wasserstein Distributionally Robust Support Vector Machine Highlight: In this paper, we focus on a family of Wasserstein distributionally robust support vector machine (DRSVM) problems and propose two novel epigraphical projection-based incremental algorithms to solve them. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiajin Li; Caihua Chen; Anthony Man-Cho So; | |
| 340 | Differentially Private Clustering: Tight Approximation Ratios Highlight: For several basic clustering problems, including Euclidean DensestBall, 1-Cluster, k-means, and k-median, we give efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Badih Ghazi; Ravi Kumar; Pasin Manurangsi; | |
| 341 | On The Power Of Louvain In The Stochastic Block Model Highlight: We provide valuable tools for the analysis of Louvain, but also for many other combinatorial algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vincent Cohen-Addad; Adrian Kosowski; Frederik Mallmann-Trenn; David Saulpic; | |
| 342 | Fairness With Overlapping Groups; A Probabilistic Perspective Highlight: In algorithmically fair prediction problems, a standard goal is to ensure the equality of fairness metrics across multiple overlapping groups simultaneously. We reconsider this standard fair classification problem using a probabilistic population analysis, which, in turn, reveals the Bayes-optimal classifier. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Forest Yang; Mouhamadou Cisse; Oluwasanmi O. Koyejo; | |
| 343 | AttendLight: Universal Attention-Based Reinforcement Learning Model For Traffic Signal Control Highlight: We propose AttendLight, an end-to-end Reinforcement Learning (RL) algorithm for the problem of traffic signal control. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Afshin Oroojlooy; Mohammadreza Nazari; Davood Hajinezhad; Jorge Silva; | |
| 344 | Searching For Low-Bit Weights In Quantized Neural Networks Highlight: Thus, we present to regard the discrete weights in an arbitrary quantized neural network as searchable variables, and utilize a differential method to search them accurately. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
zhaohui yang; Yunhe Wang; Kai Han; Chunjing XU; Chao Xu; Dacheng Tao; Chang Xu; | |
| 345 | Adaptive Reduced Rank Regression Highlight: To complement the upper bound, we introduce new techniques for establishing lower bounds on the performance of any algorithm for this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qiong Wu; Felix MF Wong; Yanhua Li; Zhenming Liu; Varun Kanade; | |
| 346 | From Predictions To Decisions: Using Lookahead Regularization Highlight: For this, we introduce look-ahead regularization which, by anticipating user actions, encourages predictive models to also induce actions that improve outcomes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nir Rosenfeld; Anna Hilgard; Sai Srivatsa Ravindranath; David C. Parkes; | |
| 347 | Sequential Bayesian Experimental Design With Variable Cost Structure Highlight: We propose and demonstrate an algorithm that accounts for these variable costs in the refinement decision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sue Zheng; David Hayden; Jason Pacheco; John W. Fisher III; | |
| 348 | Predictive Inference Is Free With The Jackknife+-after-bootstrap Highlight: In this paper, we propose the jackknife+-after-bootstrap (J+aB), a procedure for constructing a predictive interval, which uses only the available bootstrapped samples and their corresponding fitted models, and is therefore "free" in terms of the cost of model fitting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Byol Kim; Chen Xu; Rina Foygel Barber; | |
| 349 | Counterfactual Predictions Under Runtime Confounding Highlight: We propose a doubly-robust procedure for learning counterfactual prediction models in this setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amanda Coston; Edward Kennedy; Alexandra Chouldechova; | |
| 350 | Learning Loss For Test-Time Augmentation Highlight: This paper proposes a novel instance-level test- time augmentation that efficiently selects suitable transformations for a test input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ildoo Kim; Younghoon Kim; Sungwoong Kim; | |
| 351 | Balanced Meta-Softmax For Long-Tailed Visual Recognition Highlight: In this paper, we show that the Softmax function, though used in most classification tasks, gives a biased gradient estimation under the long-tailed setup. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ren Jiawei; Cunjun Yu; shunan sheng; Xiao Ma; Haiyu Zhao; Shuai Yi; hongsheng Li; | |
| 352 | Efficient Exploration Of Reward Functions In Inverse Reinforcement Learning Via Bayesian Optimization Highlight: This paper presents an IRL framework called Bayesian optimization-IRL (BO-IRL) which identifies multiple solutions that are consistent with the expert demonstrations by efficiently exploring the reward function space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sreejith Balakrishnan; Quoc Phong Nguyen; Bryan Kian Hsiang Low; Harold Soh; | |
| 353 | MDP Homomorphic Networks: Group Symmetries In Reinforcement Learning Highlight: This paper introduces MDP homomorphic networks for deep reinforcement learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Elise van der Pol; Daniel Worrall; Herke van Hoof; Frans Oliehoek; Max Welling; | |
| 354 | How Can I Explain This To You? An Empirical Study Of Deep Neural Network Explanation Methods Highlight: We performed a cross-analysis Amazon Mechanical Turk study comparing the popular state-of-the-art explanation methods to empirically determine which are better in explaining model decisions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeya Vikranth Jeyakumar; Joseph Noor; Yu-Hsi Cheng; Luis Garcia; Mani Srivastava; | |
| 355 | On The Error Resistance Of Hinge-Loss Minimization Highlight: In this work, we identify a set of conditions on the data under which such surrogate loss minimization algorithms provably learn the correct classifier. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kunal Talwar; | |
| 356 | Munchausen Reinforcement Learning Highlight: Our core contribution stands in a very simple idea: adding the scaled log-policy to the immediate reward. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nino Vieillard; Olivier Pietquin; Matthieu Geist; | |
| 357 | Object Goal Navigation Using Goal-Oriented Semantic Exploration Highlight: We propose a modular system called, `Goal-Oriented Semantic Exploration’ which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Devendra Singh Chaplot; Dhiraj Prakashchand Gandhi; Abhinav Gupta; Russ R. Salakhutdinov; | |
| 358 | Efficient Semidefinite-programming-based Inference For Binary And Multi-class MRFs Highlight: In this paper, we propose an efficient method for computing the partition function or MAP estimate in a pairwise MRF by instead exploiting a recently proposed coordinate-descent-based fast semidefinite solver. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chirag Pabbaraju; Po-Wei Wang; J. Zico Kolter; | |
| 359 | Funnel-Transformer: Filtering Out Sequential Redundancy For Efficient Language Processing Highlight: With this intuition, we propose Funnel-Transformer which gradually compresses the sequence of hidden states to a shorter one and hence reduces the computation cost. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zihang Dai; Guokun Lai; Yiming Yang; Quoc Le; | |
| 360 | Semantic Visual Navigation By Watching YouTube Videos Highlight: This paper learns and leverages such semantic cues for navigating to objects of interest in novel environments, by simply watching YouTube videos. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matthew Chang; Arjun Gupta; Saurabh Gupta; | |
| 361 | Heavy-tailed Representations, Text Polarity Classification & Data Augmentation Highlight: In this paper, we develop a novel method to learn a heavy-tailed embedding with desirable regularity properties regarding the distributional tails, which allows to analyze the points far away from the distribution bulk using the framework of multivariate extreme value theory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hamid JALALZAI; Pierre Colombo; Chlo� Clavel; Eric Gaussier; Giovanna Varni; Emmanuel Vignon; Anne Sabourin; | |
| 362 | SuperLoss: A Generic Loss For Robust Curriculum Learning Highlight: We propose instead a simple and generic method that can be applied to a variety of losses and tasks without any change in the learning procedure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thibault Castells; Philippe Weinzaepfel; Jerome Revaud; | |
| 363 | CogMol: Target-Specific And Selective Drug Design For COVID-19 Using Deep Generative Models Highlight: In this study, we propose an end-to-end framework, named CogMol (Controlled Generation of Molecules), for designing new drug-like small molecules targeting novel viral proteins with high affinity and off-target selectivity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vijil Chenthamarakshan; Payel Das; Samuel Hoffman; Hendrik Strobelt; Inkit Padhi; Kar Wai Lim; Ben Hoover; Matteo Manica; Jannis Born; Teodoro Laino; Aleksandra Mojsilovic; | |
| 364 | Memory Based Trajectory-conditioned Policies For Learning From Sparse Rewards Highlight: In this work, instead of focusing on good experiences with limited diversity, we propose to learn a trajectory-conditioned policy to follow and expand diverse past trajectories from a memory buffer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yijie Guo; Jongwook Choi; Marcin Moczulski; Shengyu Feng; Samy Bengio; Mohammad Norouzi; Honglak Lee; | |
| 365 | Liberty Or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations Highlight: We challenge the longstanding assumption that the mean-field approximation for variational inference in Bayesian neural networks is severely restrictive, and show this is not the case in deep networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sebastian Farquhar; Lewis Smith; Yarin Gal; | |
| 366 | Improving Sample Complexity Bounds For (Natural) Actor-Critic Algorithms Highlight: In contrast, this paper characterizes the convergence rate and sample complexity of AC and NAC under Markovian sampling, with mini-batch data for each iteration, and with actor having general policy class approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tengyu Xu; Zhe Wang; Yingbin Liang; | |
| 367 | Learning Differential Equations That Are Easy To Solve Highlight: We propose a remedy that encourages learned dynamics to be easier to solve. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jacob Kelly; Jesse Bettencourt; Matthew J. Johnson; David K. Duvenaud; | |
| 368 | Stability Of Stochastic Gradient Descent On Nonsmooth Convex Losses Highlight: Specifically, we provide sharp upper and lower bounds for several forms of SGD and full-batch GD on arbitrary Lipschitz nonsmooth convex losses. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Raef Bassily; Vitaly Feldman; Cristobal Guzman; Kunal Talwar; | |
| 369 | Influence-Augmented Online Planning For Complex Environments Highlight: In this work, we propose influence-augmented online planning, a principled method to transform a factored simulator of the entire environment into a local simulator that samples only the state variables that are most relevant to the observation and reward of the planning agent and captures the incoming influence from the rest of the environment using machine learning methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jinke He; Miguel Suau de Castro; Frans Oliehoek; | |
| 370 | PAC-Bayes Learning Bounds For Sample-Dependent Priors Highlight: We present a series of new PAC-Bayes learning guarantees for randomized algorithms with sample-dependent priors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pranjal Awasthi; Satyen Kale; Stefani Karp; Mehryar Mohri; | |
| 371 | Reward-rational (implicit) Choice: A Unifying Formalism For Reward Learning Highlight: Our key observation is that different types of behavior can be interpreted in a single unifying formalism – as a reward-rational choice that the human is making, often implicitly. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hong Jun Jeon; Smitha Milli; Anca Dragan; | |
| 372 | Probabilistic Time Series Forecasting With Shape And Temporal Diversity Highlight: In this paper, we address this problem for non-stationary time series, which is very challenging yet crucially important. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vincent LE GUEN; Nicolas THOME; | |
| 373 | Low Distortion Block-Resampling With Spatially Stochastic Networks Highlight: We formalize and attack the problem of generating new images from old ones that are as diverse as possible, only allowing them to change without restrictions in certain parts of the image while remaining globally consistent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sarah Hong; Martin Arjovsky; Darryl Barnhart; Ian Thompson; | |
| 374 | Continual Deep Learning By Functional Regularisation Of Memorable Past Highlight: In this paper, we fix this issue by using a new functional-regularisation approach that utilises a few memorable past examples crucial to avoid forgetting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pingbo Pan; Siddharth Swaroop; Alexander Immer; Runa Eschenhagen; Richard Turner; Mohammad Emtiyaz E. Khan; | |
| 375 | Distance Encoding: Design Provably More Powerful Neural Networks For Graph Representation Learning Highlight: Here we propose and mathematically analyze a general class of structure-related features, termed Distance Encoding (DE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pan Li; Yanbang Wang; Hongwei Wang; Jure Leskovec; | |
| 376 | Fast Fourier Convolution Highlight: In this work, we propose a novel convolutional operator dubbed as fast Fourier convolution (FFC), which has the main hallmarks of non-local receptive fields and cross-scale fusion within the convolutional unit. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lu Chi; Borui Jiang; Yadong Mu; | |
| 377 | Unsupervised Learning Of Dense Visual Representations Highlight: In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pedro O. O. Pinheiro; Amjad Almahairi; Ryan Benmalek; Florian Golemo; Aaron C. Courville; | |
| 378 | Higher-Order Certification For Randomized Smoothing Highlight: In this work, we propose a framework to improve the certified safety region for these smoothed classifiers without changing the underlying smoothing scheme. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeet Mohapatra; Ching-Yun Ko; Tsui-Wei Weng; Pin-Yu Chen; Sijia Liu; Luca Daniel; | |
| 379 | Learning Structured Distributions From Untrusted Batches: Faster And Simpler Highlight: In this paper, we find an appealing way to synthesize the techniques of [JO19] and [CLM19] to give the best of both worlds: an algorithm which runs in polynomial time and can exploit structure in the underlying distribution to achieve sublinear sample complexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sitan Chen; Jerry Li; Ankur Moitra; | |
| 380 | Hierarchical Quantized Autoencoders Highlight: This leads us to introduce a novel objective for training hierarchical VQ-VAEs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Will Williams; Sam Ringer; Tom Ash; David MacLeod; Jamie Dougherty; John Hughes; | |
| 381 | Diversity Can Be Transferred: Output Diversification For White- And Black-box Attacks Highlight: To improve the efficiency of these attacks, we propose Output Diversified Sampling (ODS), a novel sampling strategy that attempts to maximize diversity in the target model’s outputs among the generated samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yusuke Tashiro; Yang Song; Stefano Ermon; | |
| 382 | POLY-HOOT: Monte-Carlo Planning In Continuous Space MDPs With Non-Asymptotic Analysis Highlight: In this paper, we consider Monte-Carlo planning in an environment with continuous state-action spaces, a much less understood problem with important applications in control and robotics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weichao Mao; Kaiqing Zhang; Qiaomin Xie; Tamer Basar; | |
| 383 | AvE: Assistance Via Empowerment Highlight: We propose a new paradigm for assistance by instead increasing the human’s ability to control their environment, and formalize this approach by augmenting reinforcement learning with human empowerment. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuqing Du; Stas Tiomkin; Emre Kiciman; Daniel Polani; Pieter Abbeel; Anca Dragan; | |
| 384 | Variational Policy Gradient Method For Reinforcement Learning With General Utilities Highlight: In this paper, we consider policy optimization in Markov Decision Problems, where the objective is a general utility function of the state-action occupancy measure, which subsumes several of the aforementioned examples as special cases. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junyu Zhang; Alec Koppel; Amrit Singh Bedi; Csaba Szepesvari; Mengdi Wang; | |
| 385 | Reverse-engineering Recurrent Neural Network Solutions To A Hierarchical Inference Task For Mice Highlight: We study how recurrent neural networks (RNNs) solve a hierarchical inference task involving two latent variables and disparate timescales separated by 1-2 orders of magnitude. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rylan Schaeffer; Mikail Khona; Leenoy Meshulam; Brain Laboratory International; Ila Fiete; | |
| 386 | Temporal Positive-unlabeled Learning For Biomedical Hypothesis Generation Via Risk Estimation Highlight: We propose a variational inference model to estimate the positive prior, and incorporate it in the learning of node pair embeddings, which are then used for link prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Uchenna Akujuobi; Jun Chen; Mohamed Elhoseiny; Michael Spranger; Xiangliang Zhang; | |
| 387 | Efficient Low Rank Gaussian Variational Inference For Neural Networks Highlight: By using a new form of the reparametrization trick, we derive a computationally efficient algorithm for performing VI with a Gaussian family with a low-rank plus diagonal covariance structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marcin Tomczak; Siddharth Swaroop; Richard Turner; | |
| 388 | Privacy Amplification Via Random Check-Ins Highlight: In this paper, we focus on conducting iterative methods like DP-SGD in the setting of federated learning (FL) wherein the data is distributed among many devices (clients). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Borja Balle; Peter Kairouz; Brendan McMahan; Om Dipakbhai Thakkar; Abhradeep Thakurta; | |
| 389 | Probabilistic Circuits For Variational Inference In Discrete Graphical Models Highlight: In this paper, we propose a new approach that leverages the tractability of probabilistic circuit models, such as Sum Product Networks (SPN), to compute ELBO gradients exactly (without sampling) for a certain class of densities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andy Shih; Stefano Ermon; | |
| 390 | Your Classifier Can Secretly Suffice Multi-Source Domain Adaptation Highlight: In this work, we present a different perspective to MSDA wherein deep models are observed to implicitly align the domains under label supervision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Naveen Venkat; Jogendra Nath Kundu; Durgesh Singh; Ambareesh Revanur; Venkatesh Babu R; | |
| 391 | Labelling Unlabelled Videos From Scratch With Multi-modal Self-supervision Highlight: In this work, we a) show that unsupervised labelling of a video dataset does not come for free from strong feature encoders and b) propose a novel clustering method that allows pseudo-labelling of a video dataset without any human annotations, by leveraging the natural correspondence between audio and visual modalities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuki Asano; Mandela Patrick; Christian Rupprecht; Andrea Vedaldi; | |
| 392 | A Non-Asymptotic Analysis For Stein Variational Gradient Descent Highlight: In this paper, we provide a novel finite time analysis for the SVGD algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anna Korba; Adil SALIM; Michael Arbel; Giulia Luise; Arthur Gretton; | |
| 393 | Robust Meta-learning For Mixed Linear Regression With Small Batches Highlight: We introduce a spectral approach that is simultaneously robust under both scenarios. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weihao Kong; Raghav Somani; Sham Kakade; Sewoong Oh; | |
| 394 | Bayesian Deep Learning And A Probabilistic Perspective Of Generalization Highlight: We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization, and propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction, without significant overhead. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrew Gordon Wilson; Pavel Izmailov; | |
| 395 | Unsupervised Learning Of Object Landmarks Via Self-Training Correspondence Highlight: This paper addresses the problem of unsupervised discovery of object landmarks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dimitrios Mallis; Enrique Sanchez; Matthew Bell; Georgios Tzimiropoulos; | code |
| 396 | Randomized Tests For High-dimensional Regression: A More Efficient And Powerful Solution Highlight: In this paper, we answer this question in the affirmative by leveraging the random projection techniques, and propose a testing procedure that blends the classical $F$-test with a random projection step. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yue Li; Ilmun Kim; Yuting Wei; | |
| 397 | Learning Representations From Audio-Visual Spatial Alignment Highlight: We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pedro Morgado; Yi Li; Nuno Nvasconcelos; | code |
| 398 | Generative View Synthesis: From Single-view Semantics To Novel-view Images Highlight: We propose to push the envelope further, and introduce Generative View Synthesis (GVS) that can synthesize multiple photorealistic views of a scene given a single semantic map. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tewodros Amberbir Habtegebrial; Varun Jampani; Orazio Gallo; Didier Stricker; | code |
| 399 | Towards More Practical Adversarial Attacks On Graph Neural Networks Highlight: Therefore, we propose a greedy procedure to correct the importance score that takes into account of the diminishing-return pattern. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiaqi Ma; Shuangrui Ding; Qiaozhu Mei; | |
| 400 | Multi-Task Reinforcement Learning With Soft Modularization Highlight: Thus, instead of naively sharing parameters across tasks, we introduce an explicit modularization technique on policy representation to alleviate this optimization issue. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruihan Yang; Huazhe Xu; YI WU; Xiaolong Wang; | |
| 401 | Causal Shapley Values: Exploiting Causal Knowledge To Explain Individual Predictions Of Complex Models Highlight: In this paper, we propose a novel framework for computing Shapley values that generalizes recent work that aims to circumvent the independence assumption. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tom Heskes; Evi Sijben; Ioan Gabriel Bucur; Tom Claassen; | |
| 402 | On The Training Dynamics Of Deep Networks With $L_2$ Regularization Highlight: We study the role of $L_2$ regularization in deep learning, and uncover simple relations between the performance of the model, the $L_2$ coefficient, the learning rate, and the number of training steps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aitor Lewkowycz; Guy Gur-Ari; | |
| 403 | Improved Algorithms For Convex-Concave Minimax Optimization Highlight: This paper studies minimax optimization problems minx maxy f(x, y), where f(x, y) is mx-strongly convex with respect to x, my-strongly concave with respect to y and (Lx, Lxy, Ly)-smooth. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuanhao Wang; Jian Li; | |
| 404 | Deep Variational Instance Segmentation Highlight: In this paper, we propose a novel algorithm that directly utilizes a fully convolutional network (FCN) to predict instance labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jialin Yuan; Chao Chen; Fuxin Li; | |
| 405 | Learning Implicit Functions For Topology-Varying Dense 3D Shape Correspondence Highlight: The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Feng Liu; Xiaoming Liu; | |
| 406 | Deep Multimodal Fusion By Channel Exchanging Highlight: To this end, this paper proposes Channel-Exchanging-Network (CEN), a parameter-free multimodal fusion framework that dynamically exchanges channels between sub-networks of different modalities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yikai Wang; Wenbing Huang; Fuchun Sun; Tingyang Xu; Yu Rong; Junzhou Huang; | |
| 407 | Hierarchically Organized Latent Modules For Exploratory Search In Morphogenetic Systems Highlight: In this paper, we motivate the need for what we call Meta-diversity search, arguing that there is not a unique ground truth interesting diversity as it strongly depends on the final observer and its motives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mayalen Etcheverry; Cl�ment Moulin-Frier; Pierre-Yves Oudeyer; | |
| 408 | AI Feynman 2.0: Pareto-optimal Symbolic Regression Exploiting Graph Modularity Highlight: We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Silviu-Marian Udrescu; Andrew Tan; Jiahai Feng; Orisvaldo Neto; Tailin Wu; Max Tegmark; | |
| 409 | Delay And Cooperation In Nonstochastic Linear Bandits Highlight: This paper offers a nearly optimal algorithm for online linear optimization with delayed bandit feedback. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shinji Ito; Daisuke Hatano; Hanna Sumita; Kei Takemura; Takuro Fukunaga; Naonori Kakimura; Ken-Ichi Kawarabayashi; | |
| 410 | Probabilistic Orientation Estimation With Matrix Fisher Distributions Highlight: This paper focuses on estimating probability distributions over the set of 3D ro- tations (SO(3)) using deep neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Mohlin; Josephine Sullivan; G�rald Bianchi; | code |
| 411 | Minimax Dynamics Of Optimally Balanced Spiking Networks Of Excitatory And Inhibitory Neurons Highlight: Overall, we present a novel normative modeling approach for spiking E-I networks, going beyond the widely-used energy-minimizing networks that violate Dale’s law. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qianyi Li; Cengiz Pehlevan; | |
| 412 | Telescoping Density-Ratio Estimation Highlight: To resolve this limitation, we introduce a new framework, telescoping density-ratio estimation (TRE), that enables the estimation of ratios between highly dissimilar densities in high-dimensional spaces. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benjamin Rhodes; Kai Xu; Michael U. Gutmann; | |
| 413 | Towards Deeper Graph Neural Networks With Differentiable Group Normalization Highlight: To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaixiong Zhou; Xiao Huang; Yuening Li; Daochen Zha; Rui Chen; Xia Hu; | |
| 414 | Stochastic Optimization For Performative Prediction Highlight: We initiate the study of stochastic optimization for performative prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Celestine Mendler-D�nner; Juan Perdomo; Tijana Zrnic; Moritz Hardt; | |
| 415 | Learning Differentiable Programs With Admissible Neural Heuristics Highlight: We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ameesh Shah; Eric Zhan; Jennifer Sun; Abhinav Verma; Yisong Yue; Swarat Chaudhuri; | |
| 416 | Improved Guarantees And A Multiple-descent Curve For Column Subset Selection And The Nystrom Method Highlight: We develop techniques which exploit spectral properties of the data matrix to obtain improved approximation guarantees which go beyond the standard worst-case analysis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michal Derezinski; Rajiv Khanna; Michael W. Mahoney; | |
| 417 | Domain Adaptation As A Problem Of Inference On Graphical Models Highlight: To develop an automated way of domain adaptation with multiple source domains, we propose to use a graphical model as a compact way to encode the change property of the joint distribution, which can be learned from data, and then view domain adaptation as a problem of Bayesian inference on the graphical models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kun Zhang; Mingming Gong; Petar Stojanov; Biwei Huang; QINGSONG LIU; Clark Glymour; | |
| 418 | Network Size And Size Of The Weights In Memorization With Two-layers Neural Networks Highlight: In contrast we propose a new training procedure for ReLU networks, based on {\em complex} (as opposed to {\em real}) recombination of the neurons, for which we show approximate memorization with both $O\left(\frac{n}{d} \cdot \frac{\log(1/\epsilon)}{\epsilon}\right)$ neurons, as well as nearly-optimal size of the weights. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sebastien Bubeck; Ronen Eldan; Yin Tat Lee; Dan Mikulincer; | |
| 419 | Certifying Strategyproof Auction Networks Highlight: We propose ways to explicitly verify strategyproofness under a particular valuation profile using techniques from the neural network verification literature. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Curry; Ping-yeh Chiang; Tom Goldstein; John Dickerson; | |
| 420 | Continual Learning Of Control Primitives : Skill Discovery Via Reset-Games Highlight: In this work, we show how a single method can allow an agent to acquire skills with minimal supervision while removing the need for resets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kelvin Xu; Siddharth Verma; Chelsea Finn; Sergey Levine; | |
| 421 | HOI Analysis: Integrating And Decomposing Human-Object Interaction Highlight: In analogy to Harmonic Analysis, whose goal is to study how to represent the signals with the superposition of basic waves, we propose the HOI Analysis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yong-Lu Li; Xinpeng Liu; Xiaoqian Wu; Yizhuo Li; Cewu Lu; | code |
| 422 | Strongly Local P-norm-cut Algorithms For Semi-supervised Learning And Local Graph Clustering Highlight: In this paper, we propose a generalization of the objective function behind these methods involving p-norms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Meng Liu; David F. Gleich; | |
| 423 | Deep Direct Likelihood Knockoffs Highlight: We develop Deep Direct Likelihood Knockoffs (DDLK), which directly minimizes the KL divergence implied by the knockoff swap property. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mukund Sudarshan; Wesley Tansey; Rajesh Ranganath; | |
| 424 | Meta-Neighborhoods Highlight: In this work, we step forward in this direction and propose a semi-parametric method, Meta-Neighborhoods, where predictions are made adaptively to the neighborhood of the input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siyuan Shan; Yang Li; Junier B. Oliva; | |
| 425 | Neural Dynamic Policies For End-to-End Sensorimotor Learning Highlight: In this work, we begin to close this gap and embed dynamics structure into deep neural network-based policies by reparameterizing action spaces with differential equations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shikhar Bahl; Mustafa Mukadam; Abhinav Gupta; Deepak Pathak; | code |
| 426 | A New Inference Approach For Training Shallow And Deep Generalized Linear Models Of Noisy Interacting Neurons Highlight: Here, we develop a two-step inference strategy that allows us to train robust generalised linear models of interacting neurons, by explicitly separating the effects of correlations in the stimulus from network interactions in each training step. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gabriel Mahuas; Giulio Isacchini; Olivier Marre; Ulisse Ferrari; Thierry Mora; | |
| 427 | Decision-Making With Auto-Encoding Variational Bayes Highlight: Motivated by these theoretical results, we propose learning several approximate proposals for the best model and combining them using multiple importance sampling for decision-making. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Romain Lopez; Pierre Boyeau; Nir Yosef; Michael Jordan; Jeffrey Regier; | |
| 428 | Attribution Preservation In Network Compression For Reliable Network Interpretation Highlight: In this paper, we show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions, which could lead to dire consequences for mission-critical applications. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Geondo Park; June Yong Yang; Sung Ju Hwang; Eunho Yang; | |
| 429 | Feature Importance Ranking For Deep Learning Highlight: In this paper, we propose a novel dual-net architecture consisting of operator and selector for discovery of an optimal feature subset of a fixed size and ranking the importance of those features in the optimal subset simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maksymilian Wojtas; Ke Chen; | code |
| 430 | Causal Estimation With Functional Confounders Highlight: We study causal inference when the true confounder value can be expressed as a function of the observed data; we call this setting estimation with functional confounders (EFC). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aahlad Manas Puli; Adler Perotte ; Rajesh Ranganath; | |
| 431 | Model Inversion Networks For Model-Based Optimization Highlight: We propose to address such problems with model inversion networks (MINs), which learn an inverse mapping from scores to inputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aviral Kumar; Sergey Levine; | |
| 432 | Hausdorff Dimension, Heavy Tails, And Generalization In Neural Networks Highlight: Aiming to bridge this gap, in this paper, we prove generalization bounds for SGD under the assumption that its trajectories can be well-approximated by a \emph{Feller process}, which defines a rich class of Markov processes that include several recent SDE representations (both Brownian or heavy-tailed) as its special case. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Umut Simsekli; Ozan Sener; George Deligiannidis; Murat A. Erdogdu; | |
| 433 | Exact Expressions For Double Descent And Implicit Regularization Via Surrogate Random Design Highlight: We provide the first exact non-asymptotic expressions for double descent of the minimum norm linear estimator. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michal Derezinski; Feynman T. Liang; Michael W. Mahoney; | |
| 434 | Certifying Confidence Via Randomized Smoothing Highlight: In this work, we propose a method to generate certified radii for the prediction confidence of the smoothed classifier. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aounon Kumar; Alexander Levine; Soheil Feizi; Tom Goldstein; | code |
| 435 | Learning Physical Constraints With Neural Projections Highlight: We propose a new family of neural networks to predict the behaviors of physical systems by learning their underpinning constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuqi Yang; Xingzhe He; Bo Zhu; | |
| 436 | Robust Optimization For Fairness With Noisy Protected Groups Highlight: First, we study the consequences of naively relying on noisy protected group labels: we provide an upper bound on the fairness violations on the true groups G when the fairness criteria are satisfied on noisy groups ^G. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Serena Wang; Wenshuo Guo; Harikrishna Narasimhan; Andrew Cotter; Maya Gupta; Michael Jordan; | |
| 437 | Noise-Contrastive Estimation For Multivariate Point Processes Highlight: We show how to instead apply a version of noise-contrastive estimation—a general parameter estimation method with a less expensive stochastic objective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongyuan Mei; Tom Wan; Jason Eisner; | |
| 438 | A Game-Theoretic Analysis Of The Empirical Revenue Maximization Algorithm With Endogenous Sampling Highlight: We generalize the definition of an incentive-awareness measure proposed by Lavi et al (2019), to quantify the reduction of ERM’s outputted price due to a change of m>=1 out of N input samples, and provide specific convergence rates of this measure to zero as N goes to infinity for different types of input distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaotie Deng; Ron Lavi; Tao Lin; Qi Qi; Wenwei WANG; Xiang Yan; | |
| 439 | Neural Path Features And Neural Path Kernel : Understanding The Role Of Gates In Deep Learning Highlight: In this paper, we analytically characterise the role of gates and active sub-networks in deep learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chandrashekar Lakshminarayanan; Amit Vikram Singh; | |
| 440 | Multiscale Deep Equilibrium Models Highlight: We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shaojie Bai; Vladlen Koltun; J. Zico Kolter; | code |
| 441 | Sparse Graphical Memory For Robust Planning Highlight: We introduce Sparse Graphical Memory (SGM), a new data structure that stores states and feasible transitions in a sparse memory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Scott Emmons; Ajay Jain; Misha Laskin; Thanard Kurutach; Pieter Abbeel; Deepak Pathak; | code |
| 442 | Second Order PAC-Bayesian Bounds For The Weighted Majority Vote Highlight: We present a novel analysis of the expected risk of weighted majority vote in multiclass classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andres Masegosa; Stephan Lorenzen; Christian Igel; Yevgeny Seldin; | |
| 443 | Dirichlet Graph Variational Autoencoder Highlight: In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jia Li; Jianwei Yu; Jiajin Li; Honglei Zhang; Kangfei Zhao; Yu Rong; Hong Cheng; Junzhou Huang; | |
| 444 | Modeling Task Effects On Meaning Representation In The Brain Via Zero-Shot MEG Prediction Highlight: In the current work, we study Magnetoencephalography (MEG) brain recordings of participants tasked with answering questions about concrete nouns. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mariya Toneva; Otilia Stretcu; Barnabas Poczos; Leila Wehbe; Tom M. Mitchell; | |
| 445 | Counterfactual Vision-and-Language Navigation: Unravelling The Unseen Highlight: We propose a new learning strategy that learns both from observations and generated counterfactual environments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amin Parvaneh; Ehsan Abbasnejad; Damien Teney; Qinfeng Shi; Anton van den Hengel; | |
| 446 | Robust Quantization: One Model To Rule Them All Highlight: To address this issue, we propose a method that provides intrinsic robustness to the model against a broad range of quantization processes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Moran Shkolnik; Brian Chmiel; Ron Banner; Gil Shomron; Yury Nahshan; Alex Bronstein; Uri Weiser; | |
| 447 | Enabling Certification Of Verification-agnostic Networks Via Memory-efficient Semidefinite Programming Highlight: In this work, we propose a first-order dual SDP algorithm that provides (1) any-time bounds (2) requires memory only linear in the total number of network activations and (3) has per-iteration complexity that scales linearly with the complexity of a forward/backward pass through the network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sumanth Dathathri; Krishnamurthy Dvijotham; Alexey Kurakin; Aditi Raghunathan; Jonathan Uesato; Rudy R. Bunel; Shreya Shankar; Jacob Steinhardt; Ian Goodfellow; Percy S. Liang; Pushmeet Kohli; | |
| 448 | Federated Accelerated Stochastic Gradient Descent Highlight: We propose Federated Accelerated Stochastic Gradient Descent (FedAc), a principled acceleration of Federated Averaging (FedAvg, also known as Local SGD) for distributed optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Honglin Yuan; Tengyu Ma; | |
| 449 | Robust Density Estimation Under Besov IPM Losses Highlight: We study minimax convergence rates of nonparametric density estimation under the Huber contamination model, in which a “contaminated” proportion of the data comes from an unknown outlier distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ananya Uppal; Shashank Singh; Barnabas Poczos; | |
| 450 | An Analytic Theory Of Shallow Networks Dynamics For Hinge Loss Classification Highlight: In this paper we study in detail the training dynamics of a simple type of neural network: a single hidden layer trained to perform a classification task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Franco Pellegrini; Giulio Biroli; | |
| 451 | Fixed-Support Wasserstein Barycenters: Computational Hardness And Fast Algorithm Highlight: We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in computing the Wasserstein barycenter of $m$ discrete probability measures supported on a finite metric space of size $n$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianyi Lin; Nhat Ho; Xi Chen; Marco Cuturi; Michael Jordan; | |
| 452 | Learning To Orient Surfaces By Self-supervised Spherical CNNs Highlight: In this work, we show the feasibility of learning a robust canonical orientation for surfaces represented as point clouds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Riccardo Spezialetti; Federico Stella; Marlon Marcon; Luciano Silva; Samuele Salti; Luigi Di Stefano; | |
| 453 | Adam With Bandit Sampling For Deep Learning Highlight: In this paper, we propose a generalization of Adam, called Adambs, that allows us to also adapt to different training examples based on their importance in the model’s convergence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rui Liu; Tianyi Wu; Barzan Mozafari; | |
| 454 | Parabolic Approximation Line Search For DNNs Highlight: Exploiting this parabolic property we introduce a simple and robust line search approach, which performs loss-shape dependent update steps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maximus Mutschler; Andreas Zell; | |
| 455 | Agnostic Learning Of A Single Neuron With Gradient Descent Highlight: We consider the problem of learning the best-fitting single neuron as measured by the expected square loss $\E_{(x,y)\sim \mathcal{D}}[(\sigma(w^\top x)-y)^2]$ over some unknown joint distribution $\mathcal{D}$ by using gradient descent to minimize the empirical risk induced by a set of i.i.d. samples $S\sim \mathcal{D}^n$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Spencer Frei; Yuan Cao; Quanquan Gu; | |
| 456 | Statistical Efficiency Of Thompson Sampling For Combinatorial Semi-Bandits Highlight: We propose to answer the above question for these two families by analyzing variants of the Combinatorial Thompson Sampling policy (CTS). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pierre Perrault; Etienne Boursier; Michal Valko; Vianney Perchet; | |
| 457 | Analytic Characterization Of The Hessian In Shallow ReLU Models: A Tale Of Symmetry Highlight: We consider the optimization problem associated with fitting two-layers ReLU networks with respect to the squared loss, where labels are generated by a target network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yossi Arjevani; Michael Field; | |
| 458 | Generative Causal Explanations Of Black-box Classifiers Highlight: We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matthew O'Shaughnessy; Gregory Canal; Marissa Connor; Christopher Rozell; Mark Davenport; | |
| 459 | Sub-sampling For Efficient Non-Parametric Bandit Exploration Highlight: In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (namely Bernoulli, Gaussian and Poisson distributions). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dorian Baudry; Emilie Kaufmann; Odalric-Ambrym Maillard; | |
| 460 | Learning Under Model Misspecification: Applications To Variational And Ensemble Methods Highlight: In this work, we present a novel analysis of the generalization performance of Bayesian model averaging under model misspecification and i.i.d. data using a new family of second-order PAC-Bayes bounds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andres Masegosa; | |
| 461 | Language Through A Prism: A Spectral Approach For Multiscale Language Representations Highlight: We propose building models that isolate scale-specific information in deep representations, and develop methods for encouraging models during training to learn more about particular scales of interest. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Tamkin; Dan Jurafsky; Noah Goodman; | |
| 462 | DVERGE: Diversifying Vulnerabilities For Enhanced Robust Generation Of Ensembles Highlight: We propose DVERGE, which isolates the adversarial vulnerability in each sub-model by distilling non-robust features, and diversifies the adversarial vulnerability to induce diverse outputs against a transfer attack. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huanrui Yang; Jingyang Zhang; Hongliang Dong; Nathan Inkawhich; Andrew Gardner; Andrew Touchet; Wesley Wilkes; Heath Berry; Hai Li; | code |
| 463 | Towards Practical Differentially Private Causal Graph Discovery Highlight: In this paper, we present a differentially private causal graph discovery algorithm, Priv-PC, which improves both utility and running time compared to the state-of-the-art. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lun Wang; Qi Pang; Dawn Song; | code |
| 464 | Independent Policy Gradient Methods For Competitive Reinforcement Learning Highlight: We obtain global, non-asymptotic convergence guarantees for independent learning algorithms in competitive reinforcement learning settings with two agents (i.e., zero-sum stochastic games). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Constantinos Daskalakis; Dylan J. Foster; Noah Golowich; | |
| 465 | The Value Equivalence Principle For Model-Based Reinforcement Learning Highlight: In this paper we argue that the limited representational resources of model-based RL agents are better used to build models that are directly useful for value-based planning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christopher Grimm; Andre Barreto; Satinder Singh; David Silver; | |
| 466 | Structured Convolutions For Efficient Neural Network Design Highlight: In this work, we tackle model efficiency by exploiting redundancy in the implicit structure of the building blocks of convolutional neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yash Bhalgat; Yizhe Zhang; Jamie Menjay Lin; Fatih Porikli; | |
| 467 | Latent World Models For Intrinsically Motivated Exploration Highlight: In this work we consider partially observable environments with sparse rewards. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aleksandr Ermolov; Nicu Sebe; | code |
| 468 | Estimating Rank-One Spikes From Heavy-Tailed Noise Via Self-Avoiding Walks Highlight: In this work, we exhibit an estimator that works for heavy-tailed noise up to the BBP threshold that is optimal even for Gaussian noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jingqiu Ding; Samuel Hopkins; David Steurer; | |
| 469 | Policy Improvement Via Imitation Of Multiple Oracles Highlight: In this paper, we propose the state-wise maximum of the oracle policies’ values as a natural baseline to resolve con?icting advice from multiple oracles. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ching-An Cheng; Andrey Kolobov; Alekh Agarwal; | |
| 470 | Training Generative Adversarial Networks By Solving Ordinary Differential Equations Highlight: From this perspective, we hypothesise that instabilities in training GANs arise from the integration error in discretising the continuous dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chongli Qin; Yan Wu; Jost Tobias Springenberg; Andy Brock; Jeff Donahue; Timothy Lillicrap; Pushmeet Kohli; | |
| 471 | Learning Of Discrete Graphical Models With Neural Networks Highlight: We introduce NeurISE, a neural net based algorithm for graphical model learning, to tackle this limitation of GRISE. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Abhijith Jayakumar; Andrey Lokhov; Sidhant Misra; Marc Vuffray; | |
| 472 | RepPoints V2: Verification Meets Regression For Object Detection Highlight: In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yihong Chen; Zheng Zhang; Yue Cao; Liwei Wang; Stephen Lin; Han Hu; | |
| 473 | Unfolding The Alternating Optimization For Blind Super Resolution Highlight: Towards these issues, instead of considering these two steps separately, we adopt an alternating optimization algorithm, which can estimate blur kernel and restore SR image in a single model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
zhengxiong luo; Yan Huang; Shang Li; Liang Wang; Tieniu Tan; | |
| 474 | Entrywise Convergence Of Iterative Methods For Eigenproblems Highlight: Here we address the convergence of subspace iteration when distances are measured in the ?2?? norm and provide deterministic bounds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vasileios Charisopoulos; Austin R. Benson; Anil Damle; | |
| 475 | Learning Object-Centric Representations Of Multi-Object Scenes From Multiple Views Highlight: To address this, we propose \textit{The Multi-View and Multi-Object Network (MulMON)}—a method for learning accurate, object-centric representations of multi-object scenes by leveraging multiple views. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nanbo Li; C E; Robert Fisher; | |
| 476 | A Catalyst Framework For Minimax Optimization Highlight: We introduce a generic \emph{two-loop} scheme for smooth minimax optimization with strongly-convex-concave objectives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junchi Yang; Siqi Zhang; Negar Kiyavash; Niao He; | |
| 477 | Self-supervised Co-Training For Video Representation Learning Highlight: The objective of this paper is visual-only self-supervised video representation learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tengda Han; Weidi Xie; Andrew Zisserman; | |
| 478 | Gradient Estimation With Stochastic Softmax Tricks Highlight: Working within the perturbation model framework, we introduce stochastic softmax tricks, which generalize the Gumbel-Softmax trick to combinatorial spaces. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Max Paulus; Dami Choi; Daniel Tarlow; Andreas Krause; Chris J. Maddison; | |
| 479 | Meta-Learning Requires Meta-Augmentation Highlight: We introduce an information-theoretic framework of meta-augmentation, whereby adding randomness discourages the base learner and model from learning trivial solutions that do not generalize to new tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Janarthanan Rajendran; Alexander Irpan; Eric Jang; | |
| 480 | SLIP: Learning To Predict In Unknown Dynamical Systems With Long-term Memory Highlight: We present an efficient and practical (polynomial time) algorithm for online prediction in unknown and partially observed linear dynamical systems (LDS) under stochastic noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Paria Rashidinejad; Jiantao Jiao; Stuart Russell; | |
| 481 | Improving GAN Training With Probability Ratio Clipping And Sample Reweighting Highlight: To solve this issue, we propose a new variational GAN training framework which enjoys superior training stability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yue Wu; Pan Zhou; Andrew Gordon Wilson; Eric Xing; Zhiting Hu; | |
| 482 | Bayesian Bits: Unifying Quantization And Pruning Highlight: We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mart van Baalen; Christos Louizos; Markus Nagel; Rana Ali Amjad; Ying Wang; Tijmen Blankevoort; Max Welling; | |
| 483 | On Testing Of Samplers Highlight: The primary contribution of this paper is an affirmative answer to the above challenge: motivated by Barbarik, but using different techniques and analysis, we design Barbarik2, an algorithm to test whether the distribution generated by a sampler is epsilon-close or eta-far from any target distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kuldeep S Meel; Yash Pralhad Pote; Sourav Chakraborty; | |
| 484 | Gaussian Process Bandit Optimization Of The Thermodynamic Variational Objective Highlight: This paper introduces a bespoke Gaussian process bandit optimization method for automatically choosing these points. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vu Nguyen; Vaden Masrani; Rob Brekelmans; Michael Osborne; Frank Wood; | |
| 485 | MiniLM: Deep Self-Attention Distillation For Task-Agnostic Compression Of Pre-Trained Transformers Highlight: In this work, we present a simple and effective approach to compress large Transformer (Vaswani et al., 2017) based pre-trained models, termed as deep self-attention distillation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenhui Wang; Furu Wei; Li Dong; Hangbo Bao; Nan Yang; Ming Zhou; | |
| 486 | Optimal Epoch Stochastic Gradient Descent Ascent Methods For Min-Max Optimization Highlight: In this paper, we bridge this gap by providinga sharp analysis of epoch-wise stochastic gradient descent ascent method (referredto as Epoch-GDA) for solving strongly convex strongly concave (SCSC) min-maxproblems, without imposing any additional assumption about smoothness or the function’s structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yan Yan; Yi Xu; Qihang Lin; Wei Liu; Tianbao Yang; | |
| 487 | Woodbury Transformations For Deep Generative Flows Highlight: In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant calculation via Sylvester’s determinant identity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
You Lu; Bert Huang; | |
| 488 | Graph Contrastive Learning With Augmentations Highlight: In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuning You; Tianlong Chen; Yongduo Sui; Ting Chen; Zhangyang Wang; Yang Shen; | code |
| 489 | Gradient Surgery For Multi-Task Learning Highlight: In this work, we identify a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develop a simple yet general approach for avoiding such interference between task gradients. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianhe Yu; Saurabh Kumar; Abhishek Gupta; Sergey Levine; Karol Hausman; Chelsea Finn; | |
| 490 | Bayesian Probabilistic Numerical Integration With Tree-Based Models Highlight: This paper proposes to tackle this issue with a new Bayesian numerical integration algorithm based on Bayesian Additive Regression Trees (BART) priors, which we call BART-Int. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Harrison Zhu; Xing Liu; Ruya Kang; Zhichao Shen; Seth Flaxman; Francois-Xavier Briol; | |
| 491 | Deep Learning Versus Kernel Learning: An Empirical Study Of Loss Landscape Geometry And The Time Evolution Of The Neural Tangent Kernel Highlight: We study the relationship between the training dynamics of nonlinear deep networks, the geometry of the loss landscape, and the time evolution of a data-dependent NTK. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stanislav Fort; Gintare Karolina Dziugaite; Mansheej Paul; Sepideh Kharaghani; Daniel M. Roy; Surya Ganguli; | |
| 492 | Graph Meta Learning Via Local Subgraphs Highlight: Here, we introduce G-Meta, a novel meta-learning algorithm for graphs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kexin Huang; Marinka Zitnik; | |
| 493 | Stochastic Deep Gaussian Processes Over Graphs Highlight: In this paper we propose Stochastic Deep Gaussian Processes over Graphs (DGPG), which are deep structure models that learn the mappings between input and output signals in graph domains. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Naiqi Li; Wenjie Li; Jifeng Sun; Yinghua Gao; Yong Jiang; Shu-Tao Xia; | |
| 494 | Bayesian Causal Structural Learning With Zero-Inflated Poisson Bayesian Networks Highlight: To infer causal relationships in zero-inflated count data, we propose a new zero-inflated Poisson Bayesian network (ZIPBN) model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junsouk Choi; Robert Chapkin; Yang Ni; | |
| 495 | Evaluating Attribution For Graph Neural Networks Highlight: In this work we adapt commonly-used attribution methods for GNNs and quantitatively evaluate them using computable ground-truths that are objective and challenging to learn. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benjamin Sanchez-Lengeling; Jennifer Wei; Brian Lee; Emily Reif; Peter Wang; Wesley Wei Qian; Kevin McCloskey; Lucy Colwell ; Alexander Wiltschko; | |
| 496 | On Second Order Behaviour In Augmented Neural ODEs Highlight: In this work, we consider Second Order Neural ODEs (SONODEs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Norcliffe; Cristian Bodnar; Ben Day; Nikola Simidjievski; Pietro Li�; | |
| 497 | Neuron Shapley: Discovering The Responsible Neurons Highlight: We introduce a new multi-armed bandit algorithm that is able to efficiently detect neurons with the largest Shapley value orders of magnitude faster than existing Shapley value approximation methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amirata Ghorbani; James Y. Zou; | |
| 498 | Stochastic Normalizing Flows Highlight: Here we propose a generalized and combined approach to sample target densities: Stochastic Normalizing Flows (SNF) – an arbitrary sequence of deterministic invertible functions and stochastic sampling blocks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hao Wu; Jonas K�hler; Frank Noe; | |
| 499 | GPU-Accelerated Primal Learning For Extremely Fast Large-Scale Classification Highlight: In this work, we show that using judicious GPU-optimization principles, TRON training time for different losses and feature representations may be drastically reduced. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
John T. Halloran; David M. Rocke; | |
| 500 | Random Reshuffling Is Not Always Better Highlight: We give a counterexample to the Operator Inequality of Noncommutative Arithmetic and Geometric Means, a longstanding conjecture that relates to the performance of random reshuffling in learning algorithms (Recht and Ré, "Toward a noncommutative arithmetic-geometric mean inequality: conjectures, case-studies, and consequences," COLT 2012). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christopher M. De Sa; | |
| 501 | Model Agnostic Multilevel Explanations Highlight: In this paper, we propose a meta-method that, given a typical local explainability method, can build a multilevel explanation tree. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Karthikeyan Natesan Ramamurthy; Bhanukiran Vinzamuri; Yunfeng Zhang; Amit Dhurandhar; | |
| 502 | NeuMiss Networks: Differentiable Programming For Supervised Learning With Missing Values Highlight: In this work, we derive the analytical form of the optimal predictor under a linearity assumption and various missing data mechanisms including Missing at Random (MAR) and self-masking (Missing Not At Random). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marine Le Morvan; Julie Josses; Thomas Moreau; Erwan Scornet; Gael Varoquaux; | |
| 503 | Revisiting Parameter Sharing For Automatic Neural Channel Number Search Highlight: In this paper, we aim at providing a better understanding and exploitation of parameter sharing for CNS. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiaxing Wang; Haoli Bai; Jiaxiang Wu; Xupeng Shi; Junzhou Huang; Irwin King; Michael Lyu; Jian Cheng; | |
| 504 | Differentially-Private Federated Linear Bandits Highlight: In this paper, we study this in context of the contextual linear bandit: we consider a collection of agents cooperating to solve a common contextual bandit, while ensuring that their communication remains private. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Abhimanyu Dubey; Alex `Sandy' Pentland; | |
| 505 | Is Plug-in Solver Sample-Efficient For Feature-based Reinforcement Learning? Highlight: We solve this problem via a plug-in solver approach, which builds an empirical model and plans in this empirical model via an arbitrary plug-in solver. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qiwen Cui; Lin Yang; | |
| 506 | Learning Physical Graph Representations From Visual Scenes Highlight: To overcome these limitations, we introduce the idea of “Physical Scene Graphs” (PSGs), which represent scenes as hierarchical graphs, with nodes in the hierarchy corresponding intuitively to object parts at different scales, and edges to physical connections between parts. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniel Bear; Chaofei Fan; Damian Mrowca; Yunzhu Li; Seth Alter; Aran Nayebi; Jeremy Schwartz; Li F. Fei-Fei; Jiajun Wu; Josh Tenenbaum; Daniel L. Yamins; | |
| 507 | Deep Graph Pose: A Semi-supervised Deep Graphical Model For Improved Animal Pose Tracking Highlight: We propose a probabilistic graphical model built on top of deep neural networks, Deep Graph Pose (DGP), to leverage these useful spatial and temporal constraints, and develop an efficient structured variational approach to perform inference in this model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anqi Wu; E. Kelly Buchanan; Matthew Whiteway; Michael Schartner; Guido Meijer; Jean-Paul Noel; Erica Rodriguez; Claire Everett; Amy Norovich; Evan Schaffer; Neeli Mishra; C. Daniel Salzman; Dora Angelaki; Andr�s Bendesky; The International Brain Laboratory The International Brain Laboratory; John P. Cunningham; Liam Paninski; | code |
| 508 | Meta-learning From Tasks With Heterogeneous Attribute Spaces Highlight: We propose a heterogeneous meta-learning method that trains a model on tasks with various attribute spaces, such that it can solve unseen tasks whose attribute spaces are different from the training tasks given a few labeled instances. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tomoharu Iwata; Atsutoshi Kumagai; | |
| 509 | Estimating Decision Tree Learnability With Polylogarithmic Sample Complexity Highlight: We show that top-down decision tree learning heuristics (such as ID3, C4.5, and CART) are amenable to highly efficient {\sl learnability estimation}: for monotone target functions, the error of the decision tree hypothesis constructed by these heuristics can be estimated with {\sl polylogarithmically} many labeled examples, exponentially smaller than the number necessary to run these heuristics, and indeed, exponentially smaller than information-theoretic minimum required to learn a good decision tree. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guy Blanc; Neha Gupta; Jane Lange; Li-Yang Tan; | |
| 510 | Sparse Symplectically Integrated Neural Networks Highlight: We introduce Sparse Symplectically Integrated Neural Networks (SSINNs), a novel model for learning Hamiltonian dynamical systems from data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniel DiPietro; Shiying Xiong; Bo Zhu; | |
| 511 | Continuous Object Representation Networks: Novel View Synthesis Without Target View Supervision Highlight: We propose Continuous Object Representation Networks (CORN), a conditional architecture that encodes an input image’s geometry and appearance that map to a 3D consistent scene representation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicolai Hani; Selim Engin; Jun-Jee Chao; Volkan Isler; | code |
| 512 | Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence Highlight: In this work, we propose a novel, efficient objective function that utilizes the Jensen-Shannon divergence for multiple distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thomas Sutter; Imant Daunhawer; Julia Vogt; | |
| 513 | Solver-in-the-Loop: Learning From Differentiable Physics To Interact With Iterative PDE-Solvers Highlight: We target the problem of reducing numerical errors of iterative PDE solvers and compare different learning approaches for finding complex correction functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kiwon Um; Robert Brand; Yun (Raymond) Fei; Philipp Holl; Nils Thuerey; | |
| 514 | Reinforcement Learning With General Value Function Approximation: Provably Efficient Approach Via Bounded Eluder Dimension Highlight: In this paper, we establish the first provably efficient RL algorithm with general value function approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruosong Wang; Russ R. Salakhutdinov; Lin Yang; | |
| 515 | Predicting Training Time Without Training Highlight: We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luca Zancato; Alessandro Achille; Avinash Ravichandran; Rahul Bhotika; Stefano Soatto; | |
| 516 | How Does This Interaction Affect Me? Interpretable Attribution For Feature Interactions Highlight: We propose an interaction attribution and detection framework called Archipelago which addresses these problems and is also scalable in real-world settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Tsang; Sirisha Rambhatla; Yan Liu; | |
| 517 | Optimal Adaptive Electrode Selection To Maximize Simultaneously Recorded Neuron Yield Highlight: Here, we present an algorithm called classification-based selection (CBS) that optimizes the joint electrode selections for all recording channels so as to maximize isolation quality of detected neurons. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
John Choi; Krishan Kumar; Mohammad Khazali; Katie Wingel; Mahdi Choudhury; Adam S. Charles; Bijan Pesaran; | |
| 518 | Neurosymbolic Reinforcement Learning With Formally Verified Exploration Highlight: We present REVEL, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Greg Anderson; Abhinav Verma; Isil Dillig; Swarat Chaudhuri; | |
| 519 | Wavelet Flow: Fast Training Of High Resolution Normalizing Flows Highlight: This paper introduces Wavelet Flow, a multi-scale, normalizing flow architecture based on wavelets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jason Yu; Konstantinos Derpanis; Marcus A. Brubaker; | |
| 520 | Multi-task Batch Reinforcement Learning With Metric Learning Highlight: To robustify task inference, we propose a novel application of the triplet loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiachen Li; Quan Vuong; Shuang Liu; Minghua Liu; Kamil Ciosek; Henrik Christensen; Hao Su; | |
| 521 | On 1/n Neural Representation And Robustness Highlight: In this work, we investigate the latter by juxtaposing experimental results regarding the covariance spectrum of neural representations in the mouse V1 (Stringer et al) with artificial neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Josue Nassar; Piotr Sokol; Sueyeon Chung; Kenneth D. Harris; Il Memming Park; | |
| 522 | Boundary Thickness And Robustness In Learning Models Highlight: In this paper, we introduce the notion of the boundary thickness of a classifier, and we describe its connection with and usefulness for model robustness. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaoqing Yang; Rajiv Khanna; Yaodong Yu; Amir Gholami; Kurt Keutzer; Joseph E. Gonzalez; Kannan Ramchandran; Michael W. Mahoney; | |
| 523 | Demixed Shared Component Analysis Of Neural Population Data From Multiple Brain Areas Highlight: Here, inspired by a method developed for a single brain area, we introduce a new technique for demixing variables across multiple brain areas, called demixed shared component analysis (dSCA). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu Takagi; Steven Kennerley; Jun-ichiro Hirayama; Laurence Hunt; | |
| 524 | Learning Kernel Tests Without Data Splitting Highlight: Inspired by the selective inference framework, we propose an approach that enables learning the hyperparameters and testing on the full sample without data splitting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonas K�bler; Wittawat Jitkrittum; Bernhard Sch�lkopf; Krikamol Muandet; | |
| 525 | Unsupervised Data Augmentation For Consistency Training Highlight: In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qizhe Xie; Zihang Dai; Eduard Hovy; Thang Luong; Quoc Le; | code |
| 526 | Subgroup-based Rank-1 Lattice Quasi-Monte Carlo Highlight: To address this issue, we propose a simple closed-form rank-1 lattice construction method based on group theory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yueming LYU; Yuan Yuan; Ivor Tsang; | |
| 527 | Minibatch Vs Local SGD For Heterogeneous Distributed Learning Highlight: We analyze Local SGD (aka parallel or federated SGD) and Minibatch SGD in the heterogeneous distributed setting, where each machine has access to stochastic gradient estimates for a different, machine-specific, convex objective; the goal is to optimize w.r.t.~the average objective; and machines can only communicate intermittently. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Blake E. Woodworth; Kumar Kshitij Patel; Nati Srebro; | |
| 528 | Multi-task Causal Learning With Gaussian Processes Highlight: We propose the first multi-task causal Gaussian process (GP) model, which we call DAG-GP, that allows for information sharing across continuous interventions and across experiments on different variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Virginia Aglietti; Theodoros Damoulas; Mauricio �lvarez; Javier Gonzalez; | |
| 529 | Proximity Operator Of The Matrix Perspective Function And Its Applications Highlight: Through this connection, we propose a quadratically convergent Newton algorithm for the root finding problem.Experiments verify that the evaluation of the proximity operator requires at most 8 Newton steps, taking less than 5s for 2000 by 2000 matrices on a standard laptop. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joong-Ho Won; | |
| 530 | Generative 3D Part Assembly Via Dynamic Graph Learning Highlight: In this paper, we focus on the pose estimation subproblem from the vision side involving geometric and relational reasoning over the input part geometry. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
?? ?; Guanqi Zhan; Qingnan Fan; Kaichun Mo; Lin Shao; Baoquan Chen; Leonidas J. Guibas; Hao Dong; | |
| 531 | Improving Natural Language Processing Tasks With Human Gaze-Guided Neural Attention Highlight: As such, our work introduces a practical approach for bridging between data-driven and cognitive models and demonstrates a new way to integrate human gaze-guided neural attention into NLP tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ekta Sood; Simon Tannert; Philipp Mueller; Andreas Bulling; | |
| 532 | The Power Of Comparisons For Actively Learning Linear Classifiers Highlight: While previous results show that active learning performs no better than its supervised alternative for important concept classes such as linear separators, we show that by adding weak distributional assumptions and allowing comparison queries, active learning requires exponentially fewer samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Max Hopkins; Daniel Kane; Shachar Lovett; | |
| 533 | From Boltzmann Machines To Neural Networks And Back Again Highlight: In this work we give new results for learning Restricted Boltzmann Machines, probably the most well-studied class of latent variable models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Surbhi Goel; Adam Klivans; Frederic Koehler; | |
| 534 | Crush Optimism With Pessimism: Structured Bandits Beyond Asymptotic Optimality Highlight: In this paper, we focus on the finite hypothesis case and ask if one can achieve the asymptotic optimality while enjoying bounded regret whenever possible. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kwang-Sung Jun; Chicheng Zhang; | |
| 535 | Pruning Neural Networks Without Any Data By Iteratively Conserving Synaptic Flow Highlight: This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hidenori Tanaka; Daniel Kunin; Daniel L. Yamins; Surya Ganguli; | |
| 536 | Detecting Interactions From Neural Networks Via Topological Analysis Highlight: Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zirui Liu; Qingquan Song; Kaixiong Zhou; Ting-Hsiang Wang; Ying Shan; Xia Hu; | |
| 537 | Neural Bridge Sampling For Evaluating Safety-Critical Autonomous Systems Highlight: In this work, we employ a probabilistic approach to safety evaluation in simulation, where we are concerned with computing the probability of dangerous events. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aman Sinha; Matthew O'Kelly; Russ Tedrake; John C. Duchi; | |
| 538 | Interpretable And Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies From Heterogeneous User Demonstrations Highlight: We propose a personalized and interpretable apprenticeship scheduling algorithm that infers an interpretable representation of all human task demonstrators by extracting decision-making criteria via an inferred, personalized embedding non-parametric in the number of demonstrator types. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rohan Paleja; Andrew Silva; Letian Chen; Matthew Gombolay; | |
| 539 | Task-Agnostic Online Reinforcement Learning With An Infinite Mixture Of Gaussian Processes Highlight: This paper proposes a continual online model-based reinforcement learning approach that does not require pre-training to solve task-agnostic problems with unknown task boundaries. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mengdi Xu; Wenhao Ding; Jiacheng Zhu; ZUXIN LIU; Baiming Chen; Ding Zhao; | |
| 540 | Benchmarking Deep Learning Interpretability In Time Series Predictions Highlight: In this paper, we set out to extensively compare the performance of various saliency-based interpretability methods across diverse neural architectures, including Recurrent Neural Network, Temporal Convolutional Networks, and Transformers in a new benchmark of synthetic time series data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aya Abdelsalam Ismail; Mohamed Gunady; Hector Corrada Bravo; Soheil Feizi; | |
| 541 | Federated Principal Component Analysis Highlight: We present a federated, asynchronous, and $(\varepsilon, \delta)$-differentially private algorithm for $\PCA$ in the memory-limited setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andreas Grammenos; Rodrigo Mendoza Smith; Jon Crowcroft; Cecilia Mascolo; | |
| 542 | (De)Randomized Smoothing For Certifiable Defense Against Patch Attacks Highlight: In this paper, we introduce a certifiable defense against patch attacks that guarantees for a given image and patch attack size, no patch adversarial examples exist. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Levine; Soheil Feizi; | |
| 543 | SMYRF – Efficient Attention Using Asymmetric Clustering Highlight: We propose a novel type of balanced clustering algorithm to approximate attention. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Giannis Daras; Nikita Kitaev; Augustus Odena; Alexandros G. Dimakis; | |
| 544 | Introducing Routing Uncertainty In Capsule Networks Highlight: Rather than performing inefficient local iterative routing between adjacent capsule layers, we propose an alternative global view based on representing the inherent uncertainty in part-object assignment. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fabio De Sousa Ribeiro; Georgios Leontidis; Stefanos Kollias; | |
| 545 | A Simple And Efficient Smoothing Method For Faster Optimization And Local Exploration Highlight: This work proposes a novel smoothing method, called Bend, Mix and Release (BMR), that extends two well-known smooth approximations of the convex optimization literature: randomized smoothing and the Moreau envelope. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kevin Scaman; Ludovic DOS SANTOS; Merwan Barlier; Igor Colin; | |
| 546 | Hyperparameter Ensembles For Robustness And Uncertainty Quantification Highlight: In this paper, we design ensembles not only over weights, but over hyperparameters to improve the state of the art in both settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Florian Wenzel; Jasper Snoek; Dustin Tran; Rodolphe Jenatton; | |
| 547 | Neutralizing Self-Selection Bias In Sampling For Sortition Highlight: In order to still produce panels whose composition resembles that of the population, we develop a sampling algorithm that restores close-to-equal representation probabilities for all agents while satisfying meaningful demographic quotas. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bailey Flanigan; Paul Goelz; Anupam Gupta; Ariel D. Procaccia; | |
| 548 | On The Convergence Of Smooth Regularized Approximate Value Iteration Schemes Highlight: In this work, we analyse these techniques from error propagation perspective using the approximate dynamic programming framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Elena Smirnova; Elvis Dohmatob; | |
| 549 | Off-Policy Evaluation Via The Regularized Lagrangian Highlight: In this paper, we unify these estimators as regularized Lagrangians of the same linear program. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mengjiao Yang; Ofir Nachum; Bo Dai; Lihong Li; Dale Schuurmans; | |
| 550 | The LoCA Regret: A Consistent Metric To Evaluate Model-Based Behavior In Reinforcement Learning Highlight: To address this, we introduce an experimental setup to evaluate model-based behavior of RL methods, inspired by work from neuroscience on detecting model-based behavior in humans and animals. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Harm Van Seijen; Hadi Nekoei; Evan Racah; Sarath Chandar; | |
| 551 | Neural Power Units Highlight: We introduce the Neural Power Unit (NPU) that operates on the full domain of real numbers and is capable of learning arbitrary power functions in a single layer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Niklas Maximilian Heim; Tomas Pevny; Vasek Smidl; | |
| 552 | Towards Scalable Bayesian Learning Of Causal DAGs Highlight: We present algorithmic techniques to signi?cantly reduce the space and time requirements, which make the use of substantially larger values of K feasible. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jussi Viinikka; Antti Hyttinen; Johan Pensar; Mikko Koivisto; | |
| 553 | A Dictionary Approach To Domain-Invariant Learning In Deep Networks Highlight: In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ze Wang; Xiuyuan Cheng; Guillermo Sapiro; Qiang Qiu; | |
| 554 | Bootstrapping Neural Processes Highlight: To this end, we propose the Bootstrapping Neural Process (BNP), a novel extension of the NP family using the bootstrap. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Juho Lee; Yoonho Lee; Jungtaek Kim; Eunho Yang; Sung Ju Hwang; Yee Whye Teh; | |
| 555 | Large-Scale Adversarial Training For Vision-and-Language Representation Learning Highlight: We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhe Gan; Yen-Chun Chen; Linjie Li; Chen Zhu; Yu Cheng; Jingjing Liu; | |
| 556 | Most ReLU Networks Suffer From $\ell^2$ Adversarial Perturbations Highlight: We consider ReLU networks with random weights, in which the dimension decreases at each layer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amit Daniely; Hadas Shacham; | |
| 557 | Compositional Visual Generation With Energy Based Models Highlight: In this paper we show that energy-based models can exhibit this ability by directly combining probability distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yilun Du; Shuang Li; Igor Mordatch; | |
| 558 | Factor Graph Grammars Highlight: We propose the use of hyperedge replacement graph grammars for factor graphs, or actor graph grammars (FGGs) for short. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Chiang; Darcey Riley; | |
| 559 | Erdos Goes Neural: An Unsupervised Learning Framework For Combinatorial Optimization On Graphs Highlight: This work proposes an unsupervised learning framework for CO problems on graphs that can provide integral solutions of certified quality. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nikolaos Karalias; Andreas Loukas; | |
| 560 | Autoregressive Score Matching Highlight: To increase flexibility, we propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariate log-conditionals (scores), which need not be normalized. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chenlin Meng; Lantao Yu; Yang Song; Jiaming Song; Stefano Ermon; | |
| 561 | Debiasing Distributed Second Order Optimization With Surrogate Sketching And Scaled Regularization Highlight: Here, we introduce a new technique for debiasing the local estimates, which leads to both theoretical and empirical improvements in the convergence rate of distributed second order methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michal Derezinski; Burak Bartan; Mert Pilanci; Michael W. Mahoney; | |
| 562 | Neural Controlled Differential Equations For Irregular Time Series Highlight: Here, we demonstrate how this may be resolved through the well-understood mathematics of \emph{controlled differential equations}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Patrick Kidger; James Morrill; James Foster; Terry Lyons; | |
| 563 | On Efficiency In Hierarchical Reinforcement Learning Highlight: In this paper, we discuss the kind of structure in a Markov decision process which gives rise to efficient HRL methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zheng Wen; Doina Precup; Morteza Ibrahimi; Andre Barreto; Benjamin Van Roy; Satinder Singh; | |
| 564 | On Correctness Of Automatic Differentiation For Non-Differentiable Functions Highlight: This status quo raises a natural question: are autodiff systems correct in any formal sense when they are applied to such non-differentiable functions? In this paper, we provide a positive answer to this question. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wonyeol Lee; Hangyeol Yu; Xavier Rival; Hongseok Yang; | |
| 565 | Probabilistic Linear Solvers For Machine Learning Highlight: Unifying earlier work we propose a class of probabilistic linear solvers which jointly infer the matrix, its inverse and the solution from matrix-vector product observations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Wenger; Philipp Hennig; | |
| 566 | Dynamic Regret Of Policy Optimization In Non-Stationary Environments Highlight: We propose two model-free policy optimization algorithms, POWER and POWER++, and establish guarantees for their dynamic regret. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingjie Fei; Zhuoran Yang; Zhaoran Wang; Qiaomin Xie; | |
| 567 | Multipole Graph Neural Operator For Parametric Partial Differential Equations Highlight: Inspired by the classical multipole methods, we purpose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zongyi Li; Nikola Kovachki; Kamyar Azizzadenesheli; Burigede Liu; Andrew Stuart; Kaushik Bhattacharya; Anima Anandkumar; | |
| 568 | BlockGAN: Learning 3D Object-aware Scene Representations From Unlabelled Images Highlight: We present BlockGAN, an image generative model that learns object-aware 3D scene representations directly from unlabelled 2D images. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thu H. Nguyen-Phuoc; Christian Richardt; Long Mai; Yongliang Yang; Niloy Mitra; | |
| 569 | Online Structured Meta-learning Highlight: We overcome this limitation by proposing an online structured meta-learning (OSML) framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huaxiu Yao; Yingbo Zhou; Mehrdad Mahdavi; Zhenhui (Jessie) Li; Richard Socher; Caiming Xiong; | |
| 570 | Learning Strategic Network Emergence Games Highlight: We propose MINE (Multi-agent Inverse models of Network Emergence mechanism), a new learning framework that solves Markov-Perfect network emergence games using multi-agent inverse reinforcement learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rakshit Trivedi; Hongyuan Zha; | |
| 571 | Towards Interpretable Natural Language Understanding With Explanations As Latent Variables Highlight: In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wangchunshu Zhou; Jinyi Hu; Hanlin Zhang; Xiaodan Liang; Maosong Sun; Chenyan Xiong; Jian Tang; | |
| 572 | The Mean-Squared Error Of Double Q-Learning Highlight: In this paper, we establish a theoretical comparison between the asymptotic mean square errors of double Q-learning and Q-learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wentao Weng; Harsh Gupta; Niao He; Lei Ying; R. Srikant; | |
| 573 | What Makes For Good Views For Contrastive Learning? Highlight: In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yonglong Tian; Chen Sun; Ben Poole; Dilip Krishnan; Cordelia Schmid; Phillip Isola; | |
| 574 | Denoising Diffusion Probabilistic Models Highlight: We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Ho; Ajay Jain; Pieter Abbeel; | |
| 575 | Barking Up The Right Tree: An Approach To Search Over Molecule Synthesis DAGs Highlight: We therefore propose a deep generative model that better represents the real world process, by directly outputting molecule synthesis DAGs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
John Bradshaw; Brooks Paige; Matt J. Kusner; Marwin Segler; Jos� Miguel Hern�ndez-Lobato; | |
| 576 | On Uniform Convergence And Low-Norm Interpolation Learning Highlight: We consider an underdetermined noisy linear regression model where the minimum-norm interpolating predictor is known to be consistent, and ask: can uniform convergence in a norm ball, or at least (following Nagarajan and Kolter) the subset of a norm ball that the algorithm selects on a typical input set, explain this success? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lijia Zhou; D.J. Sutherland; Nati Srebro; | |
| 577 | Bandit Samplers For Training Graph Neural Networks Highlight: In this paper, we formulate the optimization of the sampling variance as an adversary bandit problem, where the rewards are related to the node embeddings and learned weights, and can vary constantly. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziqi Liu; Zhengwei Wu; Zhiqiang Zhang; Jun Zhou; Shuang Yang; Le Song; Yuan Qi; | |
| 578 | Sampling From A K-DPP Without Looking At All Items Highlight: In this paper, we develop alpha-DPP, an algorithm which adaptively builds a sufficiently large uniform sample of data that is then used to efficiently generate a smaller set of k items, while ensuring that this set is drawn exactly from the target distribution defined on all n items. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniele Calandriello; Michal Derezinski; Michal Valko; | code |
| 579 | Uncovering The Topology Of Time-Varying FMRI Data Using Cubical Persistence Highlight: To address this challenge, we present a novel topological approach that encodes each time point in an fMRI data set as a persistence diagram of topological features, i.e. high-dimensional voids present in the data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bastian Rieck; Tristan Yates; Christian Bock; Karsten Borgwardt; Guy Wolf; Nicholas Turk-Browne; Smita Krishnaswamy; | |
| 580 | Hierarchical Poset Decoding For Compositional Generalization In Language Highlight: In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yinuo Guo; Zeqi Lin; Jian-Guang Lou; Dongmei Zhang; | |
| 581 | Evaluating And Rewarding Teamwork Using Cooperative Game Abstractions Highlight: We introduce a parametric model called cooperative game abstractions (CGAs) for estimating characteristic functions from data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tom Yan; Christian Kroer; Alexander Peysakhovich; | |
| 582 | Exchangeable Neural ODE For Set Modeling Highlight: In this work we propose a more general formulation to achieve permutation equivariance through ordinary differential equations (ODE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yang Li; Haidong Yi; Christopher Bender; Siyuan Shan; Junier B. Oliva; | |
| 583 | Profile Entropy: A Fundamental Measure For The Learnability And Compressibility Of Distributions Highlight: We show that for samples of discrete distributions, profile entropy is a fundamental measure unifying the concepts of estimation, inference, and compression. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yi Hao; Alon Orlitsky; | |
| 584 | CoADNet: Collaborative Aggregation-and-Distribution Networks For Co-Salient Object Detection Highlight: In this paper, we present an end-to-end collaborative aggregation-and-distribution network (CoADNet) to capture both salient and repetitive visual patterns from multiple images. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qijian Zhang; Runmin Cong; Junhui Hou; Chongyi Li; Yao Zhao; | |
| 585 | Regularized Linear Autoencoders Recover The Principal Components, Eventually Highlight: We show that the inefficiency of learning the optimal representation is not inevitable — we present a simple modification to the gradient descent update that greatly speeds up convergence empirically. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xuchan Bao; James Lucas; Sushant Sachdeva; Roger B. Grosse; | |
| 586 | Semi-Supervised Partial Label Learning Via Confidence-Rated Margin Maximization Highlight: To circumvent this difficulty, the problem of semi-supervised partial label learning is investigated in this paper, where unlabeled data is utilized to facilitate model induction along with partial label training examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei Wang; Min-Ling Zhang; | |
| 587 | GramGAN: Deep 3D Texture Synthesis From 2D Exemplars Highlight: We present a novel texture synthesis framework, enabling the generation of infinite, high-quality 3D textures given a 2D exemplar image. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tiziano Portenier; Siavash Arjomand Bigdeli; Orcun Goksel; | |
| 588 | UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection Highlight: In this paper, we propose a unified WSOD framework, termed UWSOD, to develop a high-capacity general detection model with only image-level labels, which is self-contained and does not require external modules or additional supervision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunhang Shen; Rongrong Ji; Zhiwei Chen; Yongjian Wu; Feiyue Huang; | |
| 589 | Learning Restricted Boltzmann Machines With Sparse Latent Variables Highlight: In this paper, we give an algorithm for learning general RBMs with time complexity $\tilde{O}(n^{2^s+1})$, where $s$ is the maximum number of latent variables connected to the MRF neighborhood of an observed variable. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guy Bresler; Rares-Darius Buhai; | |
| 590 | Sample Complexity Of Asynchronous Q-Learning: Sharper Analysis And Variance Reduction Highlight: Focusing on a $\gamma$-discounted MDP with state space S and action space A, we demonstrate that the $ \ell_{\infty} $-based sample complexity of classical asynchronous Q-learning — namely, the number of samples needed to yield an entrywise $\epsilon$-accurate estimate of the Q-function — is at most on the order of $ \frac{1}{ \mu_{\min}(1-\gamma)^5 \epsilon^2 }+ \frac{ t_{\mathsf{mix}} }{ \mu_{\min}(1-\gamma) } $ up to some logarithmic factor, provided that a proper constant learning rate is adopted. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gen Li; Yuting Wei; Yuejie Chi; Yuantao Gu; Yuxin Chen; | |
| 591 | Curriculum Learning For Multilevel Budgeted Combinatorial Problems Highlight: By framing them in a multi-agent reinforcement learning setting, we devise a value-based method to learn to solve multilevel budgeted combinatorial problems involving two players in a zero-sum game over a graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adel Nabli; Margarida Carvalho; | |
| 592 | FedSplit: An Algorithmic Framework For Fast Federated Optimization Highlight: In order to remedy these issues, we introduce FedSplit, a class of algorithms based on operator splitting procedures for solving distributed convex minimization with additive structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Reese Pathak; Martin J. Wainwright; | |
| 593 | Estimation And Imputation In Probabilistic Principal Component Analysis With Missing Not At Random Data Highlight: We continue this line of research, but extend it to a more general MNAR mechanism, in a more general model of the probabilistic principal component analysis (PPCA), \textit{i.e.}, a low-rank model with random effects. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aude Sportisse; Claire Boyer; Julie Josses; | |
| 594 | Correlation Robust Influence Maximization Highlight: We propose a distributionally robust model for the influence maximization problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Louis Chen; Divya Padmanabhan; Chee Chin Lim; Karthik Natarajan; | |
| 595 | Neuronal Gaussian Process Regression Highlight: Here I propose that the brain implements GP regression and present neural networks (NNs) for it. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Johannes Friedrich; | |
| 596 | Nonconvex Sparse Graph Learning Under Laplacian Constrained Graphical Model Highlight: In this paper, we consider the problem of learning a sparse graph from the Laplacian constrained Gaussian graphical model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiaxi Ying; Jos� Vin�cius de Miranda Cardoso ; Daniel Palomar; | |
| 597 | Synthetic Data Generators — Sequential And Private Highlight: We study the sample complexity of private synthetic data generation over an unbounded sized class of statistical queries, and show that any class that is privately proper PAC learnable admits a private synthetic data generator (perhaps non-efficient). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Olivier Bousquet; Roi Livni; Shay Moran; | |
| 598 | Uncertainty Quantification For Inferring Hawkes Networks Highlight: Aiming towards this, we develop a statistical inference framework to learn causal relationships between nodes from networked data, where the underlying directed graph implies Granger causality. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haoyun Wang; Liyan Xie; Alex Cuozzo; Simon Mak; Yao Xie; | |
| 599 | Implicit Distributional Reinforcement Learning Highlight: To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuguang Yue; Zhendong Wang; Mingyuan Zhou; | |
| 600 | Auxiliary Task Reweighting For Minimum-data Learning Highlight: In this work, we propose a method to automatically reweight auxiliary tasks in order to reduce the data requirement on the main task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Baifeng Shi; Judy Hoffman; Kate Saenko; Trevor Darrell; Huijuan Xu; | code |
| 601 | Small Nash Equilibrium Certificates In Very Large Games Highlight: In this paper we introduce an approach that shows that it is possible to provide exploitability guarantees in such settings without ever exploring the entire game. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Brian Zhang; Tuomas Sandholm; | |
| 602 | Training Linear Finite-State Machines Highlight: In this paper, we introduce a method that can train a multi-layer FSM-based network where FSMs are connected to every FSM in the previous and the next layer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arash Ardakani; Amir Ardakani; Warren Gross; | |
| 603 | Efficient Active Learning Of Sparse Halfspaces With Arbitrary Bounded Noise Highlight: In this work, we substantially improve on it by designing a polynomial time algorithm for active learning of $s$-sparse halfspaces, with a label complexity of $\tilde{O}\big(\frac{s}{(1-2\eta)^4} polylog (d, \frac 1 \epsilon) \big)$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chicheng Zhang; Jie Shen; Pranjal Awasthi; | |
| 604 | Swapping Autoencoder For Deep Image Manipulation Highlight: We propose the Swapping Autoencoder, a deep model designed specifically for image manipulation, rather than random sampling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Taesung Park; Jun-Yan Zhu; Oliver Wang; Jingwan Lu; Eli Shechtman; Alexei Efros; Richard Zhang; | |
| 605 | Self-Supervised Few-Shot Learning On Point Clouds Highlight: To combat this problem, we propose two novel self-supervised pre-training tasks that encode a hierarchical partitioning of the point clouds using a cover-tree, where point cloud subsets lie within balls of varying radii at each level of the cover-tree. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Charu Sharma; Manohar Kaul; | |
| 606 | Faster Differentially Private Samplers Via R�nyi Divergence Analysis Of Discretized Langevin MCMC Highlight: In this work, we establish rapid convergence for these algorithms under distance measures more suitable for differential privacy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arun Ganesh; Kunal Talwar; | |
| 607 | Learning Identifiable And Interpretable Latent Models Of High-dimensional Neural Activity Using Pi-VAE Highlight: To address this problem, we propose a method that integrates key ingredients from latent models and traditional neural encoding models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ding Zhou; Xue-Xin Wei; | |
| 608 | RL Unplugged: A Collection Of Benchmarks For Offline Reinforcement Learning Highlight: In this paper, we propose a benchmark called RL Unplugged to evaluate and compare offline RL methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Caglar Gulcehre; Ziyu Wang; Alexander Novikov; Thomas Paine; Sergio G�mez; Konrad Zolna; Rishabh Agarwal; Josh S. Merel; Daniel J. Mankowitz; Cosmin Paduraru; Gabriel Dulac-Arnold; Jerry Li; Mohammad Norouzi; Matthew Hoffman; Nicolas Heess; Nando de Freitas; | |
| 609 | Dual T: Reducing Estimation Error For Transition Matrix In Label-noise Learning Highlight: Therefore in this paper, we aim to solve this problem by exploiting the divide-and-conquer paradigm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu Yao; Tongliang Liu; Bo Han; Mingming Gong; Jiankang Deng; Gang Niu; Masashi Sugiyama; | |
| 610 | Interior Point Solving For LP-based Prediction+optimisation Highlight: Instead we investigate the use of the more principled logarithmic barrier term, as widely used in interior point solvers for linear programming. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jayanta Mandi; Tias Guns; | |
| 611 | A Simple Normative Network Approximates Local Non-Hebbian Learning In The Cortex Highlight: Mathematically, we start with a family of Reduced-Rank Regression (RRR) objective functions which include Reduced Rank (minimum) Mean Square Error (RRMSE) and Canonical Correlation Analysis (CCA), and derive novel offline and online optimization algorithms, which we call Bio-RRR. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siavash Golkar; David Lipshutz; Yanis Bahroun; Anirvan Sengupta; Dmitri Chklovskii; | |
| 612 | Kernelized Information Bottleneck Leads To Biologically Plausible 3-factor Hebbian Learning In Deep Networks Highlight: Here we present a family of learning rules that does not suffer from any of these problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Roman Pogodin; Peter Latham; | |
| 613 | Understanding The Role Of Training Regimes In Continual Learning Highlight: In this work, we depart from the typical approach of altering the learning algorithm to improve stability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Seyed Iman Mirzadeh; Mehrdad Farajtabar; Razvan Pascanu; Hassan Ghasemzadeh; | |
| 614 | Fair Regression With Wasserstein Barycenters Highlight: We study the problem of learning a real-valued function that satisfies the Demographic Parity constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Evgenii Chzhen; Christophe Denis; Mohamed Hebiri; Luca Oneto; Massimiliano Pontil; | |
| 615 | Training Stronger Baselines For Learning To Optimize Highlight: As research efforts focus on increasingly sophisticated L2O models, we argue for an orthogonal, under-explored theme: improved training techniques for L2O models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianlong Chen; Weiyi Zhang; Zhou Jingyang; Shiyu Chang; Sijia Liu; Lisa Amini; Zhangyang Wang; | code |
| 616 | Exactly Computing The Local Lipschitz Constant Of ReLU Networks Highlight: We present a sufficient condition for which backpropagation always returns an element of the generalized Jacobian, and reframe the problem over this broad class of functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matt Jordan; Alexandros G. Dimakis; | |
| 617 | Strictly Batch Imitation Learning By Energy-based Distribution Matching Highlight: To address this challenge, we propose a novel technique by energy-based distribution matching (EDM): By identifying parameterizations of the (discriminative) model of a policy with the (generative) energy function for state distributions, EDM yields a simple but effective solution that equivalently minimizes a divergence between the occupancy measure for the demonstrator and a model thereof for the imitator. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniel Jarrett; Ioana Bica; Mihaela van der Schaar; | |
| 618 | On The Ergodicity, Bias And Asymptotic Normality Of Randomized Midpoint Sampling Method Highlight: In this paper, we analyze several probabilistic properties of the randomized midpoint discretization method, considering both overdamped and underdamped Langevin dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ye He; Krishnakumar Balasubramanian; Murat A. Erdogdu; | |
| 619 | A Single-Loop Smoothed Gradient Descent-Ascent Algorithm For Nonconvex-Concave Min-Max Problems Highlight: In this paper, we introduce a “smoothing" scheme which can be combined with GDA to stabilize the oscillation and ensure convergence to a stationary solution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiawei Zhang; Peijun Xiao; Ruoyu Sun; Zhiquan Luo; | |
| 620 | Generating Correct Answers For Progressive Matrices Intelligence Tests Highlight: In this work, we focus, instead, on generating a correct answer given the grid, which is a harder task, by definition. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Niv Pekar; Yaniv Benny; Lior Wolf; | |
| 621 | HyNet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss Highlight: In this paper, we investigate how L2 normalisation affects the back-propagated descriptor gradients during training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yurun Tian; Axel Barroso Laguna; Tony Ng; Vassileios Balntas; Krystian Mikolajczyk; | |
| 622 | Preference Learning Along Multiple Criteria: A Game-theoretic Perspective Highlight: In this work, we generalize the notion of a von Neumann winner to the multi-criteria setting by taking inspiration from Blackwell’s approachability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kush Bhatia; Ashwin Pananjady; Peter Bartlett; Anca Dragan; Martin J. Wainwright; | |
| 623 | Multi-Plane Program Induction With 3D Box Priors Highlight: Unlike prior work on image-based program synthesis, which assumes the image contains a single visible 2D plane, we present Box Program Induction (BPI), which infers a program-like scene representation that simultaneously models repeated structure on multiple 2D planes, the 3D position and orientation of the planes, and camera parameters, all from a single image. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yikai Li; Jiayuan Mao; Xiuming Zhang; Bill Freeman; Josh Tenenbaum; Noah Snavely; Jiajun Wu; | |
| 624 | Online Neural Connectivity Estimation With Noisy Group Testing Highlight: Here, we propose a method based on noisy group testing that drastically increases the efficiency of this process in sparse networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anne Draelos; John Pearson; | |
| 625 | Once-for-All Adversarial Training: In-Situ Tradeoff Between Robustness And Accuracy For Free Highlight: Our proposed framework, Once-for-all Adversarial Training (OAT), is built on an innovative model-conditional training framework, with a controlling hyper-parameter as the input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haotao N. Wang; Tianlong Chen; Shupeng Gui; TingKuei Hu; Ji Liu; Zhangyang Wang; | code |
| 626 | Implicit Neural Representations With Periodic Activation Functions Highlight: We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or SIRENs, are ideally suited for representing complex natural signals and their derivatives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vincent Sitzmann; Julien Martel; Alexander Bergman; David Lindell; Gordon Wetzstein; | |
| 627 | Rotated Binary Neural Network Highlight: In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mingbao Lin; Rongrong Ji; Zihan Xu; Baochang Zhang; Yan Wang; Yongjian Wu; Feiyue Huang; Chia-Wen Lin; | code |
| 628 | Community Detection In Sparse Time-evolving Graphs With A Dynamical Bethe-Hessian Highlight: A fast spectral algorithm based on an extension of the Bethe-Hessian matrix is proposed, which benefits from the positive correlation in the class labels and in their temporal evolution and is designed to be applicable to any dynamical graph with a community structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lorenzo Dall'Amico; Romain Couillet; Nicolas Tremblay; | |
| 629 | Simple And Principled Uncertainty Estimation With Deterministic Deep Learning Via Distance Awareness Highlight: This motivates us to study principled approaches to high-quality uncertainty estimation that require only a single deep neural network (DNN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeremiah Liu; Zi Lin; Shreyas Padhy; Dustin Tran; Tania Bedrax Weiss; Balaji Lakshminarayanan; | |
| 630 | Adaptive Learning Of Rank-One Models For Efficient Pairwise Sequence Alignment Highlight: In this work, we propose a new approach to pairwise alignment estimation based on two key new ingredients. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Govinda Kamath; Tavor Baharav; Ilan Shomorony; | |
| 631 | Hierarchical Nucleation In Deep Neural Networks Highlight: In this work we study the evolution of the probability density of the ImageNet dataset across the hidden layers in some state-of-the-art DCNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Diego Doimo; Aldo Glielmo; Alessio Ansuini; Alessandro Laio; | |
| 632 | Fourier Features Let Networks Learn High Frequency Functions In Low Dimensional Domains Highlight: We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matthew Tancik; Pratul Srinivasan; Ben Mildenhall; Sara Fridovich-Keil; Nithin Raghavan; Utkarsh Singhal; Ravi Ramamoorthi; Jonathan Barron; Ren Ng; | |
| 633 | Graph Geometry Interaction Learning Highlight: To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shichao Zhu; Shirui Pan; Chuan Zhou; Jia Wu; Yanan Cao; Bin Wang; | |
| 634 | Differentiable Augmentation For Data-Efficient GAN Training Highlight: To combat it, we propose Differentiable Augmentation (DiffAugment), a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shengyu Zhao; Zhijian Liu; Ji Lin; Jun-Yan Zhu; Song Han; | code |
| 635 | Heuristic Domain Adaptation Highlight: In this paper, we address the modeling of domain-invariant and domain-specific information from the heuristic search perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
shuhao cui; Xuan Jin; Shuhui Wang; Yuan He; Qingming Huang; | code |
| 636 | Learning Certified Individually Fair Representations Highlight: In this work, we introduce the first method that enables data consumers to obtain certificates of individual fairness for existing and new data points. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anian Ruoss; Mislav Balunovic; Marc Fischer; Martin Vechev; | |
| 637 | Part-dependent Label Noise: Towards Instance-dependent Label Noise Highlight: Motivated by this human cognition, in this paper, we approximate the instance-dependent label noise by exploiting \textit{part-dependent} label noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaobo Xia; Tongliang Liu; Bo Han; Nannan Wang; Mingming Gong; Haifeng Liu; Gang Niu; Dacheng Tao; Masashi Sugiyama; | |
| 638 | Tackling The Objective Inconsistency Problem In Heterogeneous Federated Optimization Highlight: Using insights from this analysis, we propose FedNova, a normalized averaging method that eliminates objective inconsistency while preserving fast error convergence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianyu Wang; Qinghua Liu; Hao Liang; Gauri Joshi; H. Vincent Poor; | |
| 639 | An Improved Analysis Of (Variance-Reduced) Policy Gradient And Natural Policy Gradient Methods Highlight: In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yanli Liu; Kaiqing Zhang; Tamer Basar; Wotao Yin; | |
| 640 | Geometric Exploration For Online Control Highlight: We study the control of an \emph{unknown} linear dynamical system under general convex costs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Orestis Plevrakis; Elad Hazan; | |
| 641 | Automatic Curriculum Learning Through Value Disagreement Highlight: Inspired by this, we propose setting up an automatic curriculum for goals that the agent needs to solve. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunzhi Zhang; Pieter Abbeel; Lerrel Pinto; | |
| 642 | MRI Banding Removal Via Adversarial Training Highlight: In this work, we propose the use of an adversarial loss that penalizes banding structures without requiring any human annotation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aaron Defazio; Tullie Murrell; Michael Recht; | |
| 643 | The NetHack Learning Environment Highlight: Here, we present the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for RL research based on the popular single-player terminal-based roguelike game, NetHack. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Heinrich K�ttler; Nantas Nardelli; Alexander Miller; Roberta Raileanu; Marco Selvatici; Edward Grefenstette; Tim Rockt�schel; | code |
| 644 | Language And Visual Entity Relationship Graph For Agent Navigation Highlight: To capture and utilize the relationships, we propose a novel Language and Visual Entity Relationship Graph for modelling the inter-modal relationships between text and vision, and the intra-modal relationships among visual entities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yicong Hong; Cristian Rodriguez; Yuankai Qi; Qi Wu; Stephen Gould; | |
| 645 | ICAM: Interpretable Classification Via Disentangled Representations And Feature Attribution Mapping Highlight: Here, we present a novel framework for creating class specific FA maps through image-to-image translation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cher Bass; Mariana da Silva; Carole Sudre; Petru-Daniel Tudosiu; Stephen Smith; Emma Robinson; | |
| 646 | Spectra Of The Conjugate Kernel And Neural Tangent Kernel For Linear-width Neural Networks Highlight: We study the eigenvalue distributions of the Conjugate Kernel and Neural Tangent Kernel associated to multi-layer feedforward neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhou Fan; Zhichao Wang; | |
| 647 | No-Regret Learning Dynamics For Extensive-Form Correlated Equilibrium Highlight: In this paper, we give the first uncoupled no-regret dynamics that converge to the set of EFCEs in n-player general-sum extensive-form games with perfect recall. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrea Celli; Alberto Marchesi; Gabriele Farina; Nicola Gatti; | |
| 648 | Estimating Weighted Areas Under The ROC Curve Highlight: The results justify learning algorithms which select score functions to maximize the empirical partial area under the curve (pAUC). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andreas Maurer; Massimiliano Pontil; | |
| 649 | Can Implicit Bias Explain Generalization? Stochastic Convex Optimization As A Case Study Highlight: We revisit this paradigm in arguably the simplest non-trivial setup, and study the implicit bias of Stochastic Gradient Descent (SGD) in the context of Stochastic Convex Optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Assaf Dauber; Meir Feder; Tomer Koren; Roi Livni; | |
| 650 | Generalized Hindsight For Reinforcement Learning Highlight: To leverage this insight and efficiently reuse data, we present Generalized Hindsight: an approximate inverse reinforcement learning technique for relabeling behaviors with the right tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Li; Lerrel Pinto; Pieter Abbeel; | |
| 651 | Critic Regularized Regression Highlight: In this paper, we propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziyu Wang; Alexander Novikov; Konrad Zolna; Josh S. Merel; Jost Tobias Springenberg; Scott E. Reed; Bobak Shahriari; Noah Siegel; Caglar Gulcehre; Nicolas Heess; Nando de Freitas; | |
| 652 | Boosting Adversarial Training With Hypersphere Embedding Highlight: In this work, we advocate incorporating the hypersphere embedding (HE) mechanism into the AT procedure by regularizing the features onto compact manifolds, which constitutes a lightweight yet effective module to blend in the strength of representation learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianyu Pang; Xiao Yang; Yinpeng Dong; Taufik Xu; Jun Zhu; Hang Su; | |
| 653 | Beyond Homophily In Graph Neural Networks: Current Limitations And Effective Designs Highlight: Motivated by this limitation, we identify a set of key designs—ego- and neighbor-embedding separation, higher-order neighborhoods, and combination of intermediate representations—that boost learning from the graph structure under heterophily. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiong Zhu; Yujun Yan; Lingxiao Zhao; Mark Heimann; Leman Akoglu; Danai Koutra; | |
| 654 | Modeling Continuous Stochastic Processes With Dynamic Normalizing Flows Highlight: In this work, we propose a novel type of normalizing flow driven by a differential deformation of the continuous-time Wiener process. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruizhi Deng; Bo Chang; Marcus A. Brubaker; Greg Mori; Andreas Lehrmann; | |
| 655 | Efficient Online Learning Of Optimal Rankings: Dimensionality Reduction Via Gradient Descent Highlight: In this work, we show how to achieve low regret for GMSSC in polynomial-time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dimitris Fotakis; Thanasis Lianeas; Georgios Piliouras; Stratis Skoulakis; | |
| 656 | Training Normalizing Flows With The Information Bottleneck For Competitive Generative Classification Highlight: In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of controlled information loss allows for an asymptotically exact formulation of the IB, while keeping the INN’s generative capabilities intact. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lynton Ardizzone; Radek Mackowiak; Carsten Rother; Ullrich K�the; | |
| 657 | Detecting Hands And Recognizing Physical Contact In The Wild Highlight: We propose a novel convolutional network based on Mask-RCNN that can jointly learn to localize hands and predict their physical contact to address this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Supreeth Narasimhaswamy; Trung Nguyen; Minh Hoai Nguyen; | |
| 658 | On The Theory Of Transfer Learning: The Importance Of Task Diversity Highlight: We provide new statistical guarantees for transfer learning via representation learning–when transfer is achieved by learning a feature representation shared across different tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nilesh Tripuraneni; Michael Jordan; Chi Jin; | |
| 659 | Finite-Time Analysis Of Round-Robin Kullback-Leibler Upper Confidence Bounds For Optimal Adaptive Allocation With Multiple Plays And Markovian Rewards Highlight: We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vrettos Moulos; | |
| 660 | Neural Star Domain As Primitive Representation Highlight: To solve this problem, we propose a novel primitive representation named neural star domain (NSD) that learns primitive shapes in the star domain. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuki Kawana; Yusuke Mukuta; Tatsuya Harada; | |
| 661 | Off-Policy Interval Estimation With Lipschitz Value Iteration Highlight: In this work, we propose a provably correct method for obtaining interval bounds for off-policy evaluation in a general continuous setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziyang Tang; Yihao Feng; Na Zhang; Jian Peng; Qiang Liu; | |
| 662 | Inverse Rational Control With Partially Observable Continuous Nonlinear Dynamics Highlight: Here we accommodate continuous nonlinear dynamics and continuous actions, and impute sensory observations corrupted by unknown noise that is private to the animal. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minhae Kwon; Saurabh Daptardar; Paul R. Schrater; Zachary Pitkow; | |
| 663 | Deep Statistical Solvers Highlight: This paper introduces Deep Statistical Solvers (DSS), a new class of trainable solvers for optimization problems, arising e.g., from system simulations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Balthazar Donon; Zhengying Liu; Wenzhuo LIU; Isabelle Guyon; Antoine Marot; Marc Schoenauer; | |
| 664 | Distributionally Robust Parametric Maximum Likelihood Estimation Highlight: To mitigate these issues, we propose a distributionally robust maximum likelihood estimator that minimizes the worst-case expected log-loss uniformly over a parametric Kullback-Leibler ball around a parametric nominal distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Viet Anh Nguyen; Xuhui Zhang; Jose Blanchet; Angelos Georghiou; | |
| 665 | Secretary And Online Matching Problems With Machine Learned Advice Highlight: In particular, we study the following online selection problems: (i) the classical secretary problem, (ii) online bipartite matching and (iii) the graphic matroid secretary problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Antonios Antoniadis; Themis Gouleakis; Pieter Kleer; Pavel Kolev; | |
| 666 | Deep Transformation-Invariant Clustering Highlight: In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict transformations and performs clustering directly in image space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tom Monnier; Thibault Groueix; Mathieu Aubry; | |
| 667 | Overfitting Can Be Harmless For Basis Pursuit, But Only To A Degree Highlight: In contrast, in this paper we study the overfitting solution that minimizes the L1-norm, which is known as Basis Pursuit (BP) in the compressed sensing literature. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peizhong Ju; Xiaojun Lin; Jia Liu; | |
| 668 | Improving Generalization In Reinforcement Learning With Mixture Regularization Highlight: In this work, we introduce a simple approach, named mixreg, which trains agents on a mixture of observations from different training environments and imposes linearity constraints on the observation interpolations and the supervision (e.g. associated reward) interpolations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
KAIXIN WANG; Bingyi Kang; Jie Shao; Jiashi Feng; | code |
| 669 | Pontryagin Differentiable Programming: An End-to-End Learning And Control Framework Highlight: The PDP distinguishes from existing methods by two novel techniques: first, we differentiate through Pontryagin’s Maximum Principle, and this allows to obtain the analytical derivative of a trajectory with respect to tunable parameters within an optimal control system, enabling end-to-end learning of dynamics, policies, or/and control objective functions; and second, we propose an auxiliary control system in the backward pass of the PDP framework, and the output of this auxiliary control system is the analytical derivative of the original system’s trajectory with respect to the parameters, which can be iteratively solved using standard control tools. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wanxin Jin; Zhaoran Wang; Zhuoran Yang; Shaoshuai Mou; | |
| 670 | Learning From Aggregate Observations Highlight: In this paper, we extend MIL beyond binary classification to other problems such as multiclass classification and regression. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yivan Zhang; Nontawat Charoenphakdee; Zhenguo Wu; Masashi Sugiyama; | |
| 671 | The Devil Is In The Detail: A Framework For Macroscopic Prediction Via Microscopic Models Highlight: In this paper, we propose a principled optimization framework for macroscopic prediction by fitting microscopic models based on conditional stochastic optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingxiang Yang; Negar Kiyavash; Le Song; Niao He; | |
| 672 | Subgraph Neural Networks Highlight: Here, we introduce SubGNN, a subgraph neural network to learn disentangled subgraph representations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emily Alsentzer; Samuel Finlayson; Michelle Li; Marinka Zitnik; | |
| 673 | Demystifying Orthogonal Monte Carlo And Beyond Highlight: In this paper we shed new light on the theoretical principles behind OMC, applying theory of negatively dependent random variables to obtain several new concentration results. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Han Lin; Haoxian Chen; Krzysztof M. Choromanski; Tianyi Zhang; Clement Laroche; | |
| 674 | Optimal Robustness-Consistency Trade-offs For Learning-Augmented Online Algorithms Highlight: In this paper, we provide the first set of non-trivial lower bounds for competitive analysis using machine-learned predictions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Wei; Fred Zhang; | |
| 675 | A Scalable Approach For Privacy-Preserving Collaborative Machine Learning Highlight: We propose COPML, a fully-decentralized training framework that achieves scalability and privacy-protection simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jinhyun So; Basak Guler; Salman Avestimehr; | |
| 676 | Glow-TTS: A Generative Flow For Text-to-Speech Via Monotonic Alignment Search Highlight: In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jaehyeon Kim; Sungwon Kim; Jungil Kong; Sungroh Yoon; | |
| 677 | Towards Learning Convolutions From Scratch Highlight: To find architectures with small description length, we propose beta-LASSO, a simple variant of LASSO algorithm that, when applied on fully-connected networks for image classification tasks, learns architectures with local connections and achieves state-of-the-art accuracies for training fully-connected networks on CIFAR-10 (84.50%), CIFAR-100 (57.76%) and SVHN (93.84%) bridging the gap between fully-connected and convolutional networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Behnam Neyshabur; | |
| 678 | Cycle-Contrast For Self-Supervised Video Representation Learning Highlight: We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Quan Kong; Wenpeng Wei; Ziwei Deng; Tomoaki Yoshinaga; Tomokazu Murakami; | |
| 679 | Posterior Re-calibration For Imbalanced Datasets Highlight: In order to deal with shift in the testing label distribution, which imbalance causes, we motivate the problem from the perspective of an optimal Bayes classifier and derive a prior rebalancing technique that can be solved through a KL-divergence based optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junjiao Tian; Yen-Cheng Liu; Nathaniel Glaser; Yen-Chang Hsu; Zsolt Kira; | code |
| 680 | Novelty Search In Representational Space For Sample Efficient Exploration Highlight: We present a new approach for efficient exploration which leverages a low-dimensional encoding of the environment learned with a combination of model-based and model-free objectives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruo Yu Tao; Vincent Francois-Lavet; Joelle Pineau; | |
| 681 | Robust Reinforcement Learning Via Adversarial Training With Langevin Dynamics Highlight: Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm, which is a sampling variant of the two-player policy gradient method. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Parameswaran Kamalaruban; Yu-Ting Huang; Ya-Ping Hsieh; Paul Rolland; Cheng Shi; Volkan Cevher; | |
| 682 | Adversarial Blocking Bandits Highlight: We consider a general adversarial multi-armed blocking bandit setting where each played arm can be blocked (unavailable) for some time periods and the reward per arm is given at each time period adversarially without obeying any distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicholas Bishop; Hau Chan; Debmalya Mandal; Long Tran-Thanh; | |
| 683 | Online Algorithms For Multi-shop Ski Rental With Machine Learned Advice Highlight: In particular, we consider the \emph{multi-shop ski rental} (MSSR) problem, which is a generalization of the classical ski rental problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shufan Wang; Jian Li; Shiqiang Wang; | |
| 684 | Multi-label Contrastive Predictive Coding Highlight: To overcome this limitation, we introduce a novel estimator based on a multi-label classification problem, where the critic needs to jointly identify \emph{multiple} positive samples at the same time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiaming Song; Stefano Ermon; | |
| 685 | Rotation-Invariant Local-to-Global Representation Learning For 3D Point Cloud Highlight: We propose a local-to-global representation learning algorithm for 3D point cloud data, which is appropriate to handle various geometric transformations, especially rotation, without explicit data augmentation with respect to the transformations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
SEOHYUN KIM; JaeYoo Park; Bohyung Han; | |
| 686 | Learning Invariants Through Soft Unification Highlight: We propose Unification Networks, an end-to-end differentiable neural network approach capable of lifting examples into invariants and using those invariants to solve a given task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nuri Cingillioglu; Alessandra Russo; | |
| 687 | One Solution Is Not All You Need: Few-Shot Extrapolation Via Structured MaxEnt RL Highlight: The key insight of this work is that learning diverse behaviors for accomplishing a task can directly lead to behavior that generalizes to varying environments, without needing to perform explicit perturbations during training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Saurabh Kumar; Aviral Kumar; Sergey Levine; Chelsea Finn; | |
| 688 | Variational Bayesian Monte Carlo With Noisy Likelihoods Highlight: In this work, we extend VBMC to deal with noisy log-likelihood evaluations, such as those arising from simulation-based models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luigi Acerbi; | |
| 689 | Finite-Sample Analysis Of Contractive Stochastic Approximation Using Smooth Convex Envelopes Highlight: In this paper, we consider an SA involving a contraction mapping with respect to an arbitrary norm, and show its finite-sample error bounds while using different stepsizes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zaiwei Chen; Siva Theja Maguluri; Sanjay Shakkottai; Karthikeyan Shanmugam; | |
| 690 | Self-Supervised Generative Adversarial Compression Highlight: In this paper, we show that a standard model compression technique, weight pruning and knowledge distillation, cannot be applied to GANs using existing methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chong Yu; Jeff Pool; | |
| 691 | An Efficient Nonconvex Reformulation Of Stagewise Convex Optimization Problems Highlight: We develop a nonconvex reformulation designed to exploit this staged structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rudy R. Bunel; Oliver Hinder; Srinadh Bhojanapalli; Krishnamurthy Dvijotham; | |
| 692 | From Finite To Countable-Armed Bandits Highlight: We propose a fully adaptive online learning algorithm that achieves O(log n) distribution-dependent expected cumulative regret after any number of plays n, and show that this order of regret is best possible. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anand Kalvit; Assaf Zeevi; | |
| 693 | Adversarial Distributional Training For Robust Deep Learning Highlight: In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yinpeng Dong; Zhijie Deng; Tianyu Pang; Jun Zhu; Hang Su; | |
| 694 | Meta-Learning Stationary Stochastic Process Prediction With Convolutional Neural Processes Highlight: Building on this, we propose the Convolutional Neural Process (ConvNP), which endows Neural Processes (NPs) with translation equivariance and extends convolutional conditional NPs to allow for dependencies in the predictive distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrew Foong; Wessel Bruinsma; Jonathan Gordon; Yann Dubois; James Requeima; Richard Turner; | |
| 695 | Theory-Inspired Path-Regularized Differential Network Architecture Search Highlight: In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pan Zhou; Caiming Xiong; Richard Socher; Steven Chu Hong Hoi; | |
| 696 | Conic Descent And Its Application To Memory-efficient Optimization Over Positive Semidefinite Matrices Highlight: We present an extension of the conditional gradient method to problems whose feasible sets are convex cones. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
John C. Duchi; Oliver Hinder; Andrew Naber; Yinyu Ye; | |
| 697 | Learning The Geometry Of Wave-Based Imaging Highlight: We propose a general physics-based deep learning architecture for wave-based imaging problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Konik Kothari; Maarten de Hoop; Ivan Dokmanic; | |
| 698 | Greedy Inference With Structure-exploiting Lazy Maps Highlight: We propose a framework for solving high-dimensional Bayesian inference problems using \emph{structure-exploiting} low-dimensional transport maps or flows. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Brennan; Daniele Bigoni; Olivier Zahm; Alessio Spantini; Youssef Marzouk; | |
| 699 | Nimble: Lightweight And Parallel GPU Task Scheduling For Deep Learning Highlight: To this end, we propose Nimble, a DL execution engine that runs GPU tasks in parallel with minimal scheduling overhead. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Woosuk Kwon; Gyeong-In Yu; Eunji Jeong; Byung-Gon Chun; | |
| 700 | Finding The Homology Of Decision Boundaries With Active Learning Highlight: In this paper, we propose an active learning algorithm to recover the homology of decision boundaries. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weizhi Li; Gautam Dasarathy; Karthikeyan Natesan Ramamurthy; Visar Berisha; | |
| 701 | Reinforced Molecular Optimization With Neighborhood-Controlled Grammars Highlight: Here, we propose MNCE-RL, a graph convolutional policy network for molecular optimization with molecular neighborhood-controlled embedding grammars through reinforcement learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chencheng Xu; Qiao Liu; Minlie Huang; Tao Jiang; | |
| 702 | Natural Policy Gradient Primal-Dual Method For Constrained Markov Decision Processes Highlight: Specifically, we propose a new Natural Policy Gradient Primal-Dual (NPG-PD) method for CMDPs which updates the primal variable via natural policy gradient ascent and the dual variable via projected sub-gradient descent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dongsheng Ding; Kaiqing Zhang; Tamer Basar; Mihailo Jovanovic; | |
| 703 | Classification Under Misspecification: Halfspaces, Generalized Linear Models, And Evolvability Highlight: In this paper, we revisit the problem of distribution-independently learning halfspaces under Massart noise with rate $\eta$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sitan Chen; Frederic Koehler; Ankur Moitra; Morris Yau; | |
| 704 | Certified Defense To Image Transformations Via Randomized Smoothing Highlight: We address this challenge by introducing three different defenses, each with a different guarantee (heuristic, distributional and individual) stemming from the method used to bound the interpolation error. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marc Fischer; Maximilian Baader; Martin Vechev; | code |
| 705 | Estimation Of Skill Distribution From A Tournament Highlight: In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ali Jadbabaie; Anuran Makur; Devavrat Shah; | |
| 706 | Reparameterizing Mirror Descent As Gradient Descent Highlight: We present a general framework for casting a mirror descent update as a gradient descent update on a different set of parameters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ehsan Amid; Manfred K. K. Warmuth; | |
| 707 | General Control Functions For Causal Effect Estimation From IVs Highlight: To construct general control functions and estimate effects, we develop the general control function method (GCFN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aahlad Manas Puli; Rajesh Ranganath; | |
| 708 | Optimal Algorithms For Stochastic Multi-Armed Bandits With Heavy Tailed Rewards Highlight: In this paper, we consider stochastic multi-armed bandits (MABs) with heavy-tailed rewards, whose p-th moment is bounded by a constant nu_p for 1<p<=2. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kyungjae Lee; Hongjun Yang; Sungbin Lim; Songhwai Oh; | |
| 709 | Certified Robustness Of Graph Convolution Networks For Graph Classification Under Topological Attacks Highlight: We propose the first algorithm for certifying the robustness of GCNs to topological attacks in the application of \emph{graph classification}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongwei Jin; Zhan Shi; Venkata Jaya Shankar Ashish Peruri; Xinhua Zhang; | |
| 710 | Zero-Resource Knowledge-Grounded Dialogue Generation Highlight: To this end, we propose representing the knowledge that bridges a context and a response and the way that the knowledge is expressed as latent variables, and devise a variational approach that can effectively estimate a generation model from independent dialogue corpora and knowledge corpora. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Linxiao Li; Can Xu; Wei Wu; YUFAN ZHAO; Xueliang Zhao; Chongyang Tao; | |
| 711 | Targeted Adversarial Perturbations For Monocular Depth Prediction Highlight: We study the effect of adversarial perturbations on the task of monocular depth prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Wong; Safa Cicek; Stefano Soatto; | |
| 712 | Beyond The Mean-Field: Structured Deep Gaussian Processes Improve The Predictive Uncertainties Highlight: We propose a novel Gaussian variational family that allows for retaining covariances between latent processes while achieving fast convergence by marginalising out all global latent variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jakob Lindinger; David Reeb; Christoph Lippert; Barbara Rakitsch; | |
| 713 | Offline Imitation Learning With A Misspecified Simulator Highlight: In this work, we investigate policy learning in the condition of a few expert demonstrations and a simulator with misspecified dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shengyi Jiang; Jingcheng Pang; Yang Yu; | |
| 714 | Multi-Fidelity Bayesian Optimization Via Deep Neural Networks Highlight: To address this issue, we propose Deep Neural Network Multi-Fidelity Bayesian Optimization (DNN-MFBO) that can flexibly capture all kinds of complicated relationships between the fidelities to improve the objective function estimation and hence the optimization performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shibo Li; Wei Xing; Robert Kirby; Shandian Zhe; | |
| 715 | PlanGAN: Model-based Planning With Sparse Rewards And Multiple Goals Highlight: In this work we propose PlanGAN, a model-based algorithm specifically designed for solving multi-goal tasks in environments with sparse rewards. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Henry Charlesworth; Giovanni Montana; | |
| 716 | Bad Global Minima Exist And SGD Can Reach Them Highlight: We find that if we do not regularize \emph{explicitly}, then SGD can be easily made to converge to poorly-generalizing, high-complexity models: all it takes is to first train on a random labeling on the data, before switching to properly training with the correct labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shengchao Liu; Dimitris Papailiopoulos; Dimitris Achlioptas; | |
| 717 | Optimal Prediction Of The Number Of Unseen Species With Multiplicity Highlight: We completely resolve this problem by determining the limit of estimation to be $a \approx (\log n)/\mu$, with both lower and upper bounds matching up to constant factors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yi Hao; Ping Li; | |
| 718 | Characterizing Optimal Mixed Policies: Where To Intervene And What To Observe Highlight: In this paper, we investigate several properties of the class of mixed policies and provide an efficient and effective characterization, including optimality and non-redundancy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sanghack Lee; Elias Bareinboim; | |
| 719 | Factor Graph Neural Networks Highlight: We generalize the GNN into a factor graph neural network (FGNN) providing a simple way to incorporate dependencies among multiple variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhen Zhang; Fan Wu; Wee Sun Lee; | |
| 720 | A Closer Look At Accuracy Vs. Robustness Highlight: With this property in mind, we then prove that robustness and accuracy should both be achievable for benchmark datasets through locally Lipschitz functions, and hence, there should be no inherent tradeoff between robustness and accuracy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yao-Yuan Yang; Cyrus Rashtchian; Hongyang Zhang; Russ R. Salakhutdinov; Kamalika Chaudhuri; | |
| 721 | Curriculum Learning By Dynamic Instance Hardness Highlight: By analogy, in this paper, we study the dynamics of a deep neural network’s (DNN) performance on individual samples during its learning process. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianyi Zhou; Shengjie Wang; Jeff A. Bilmes; | |
| 722 | Spin-Weighted Spherical CNNs Highlight: In this paper, we present a new type of spherical CNN that allows anisotropic filters in an efficient way, without ever leaving the spherical domain. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Carlos Esteves; Ameesh Makadia; Kostas Daniilidis; | |
| 723 | Learning To Execute Programs With Instruction Pointer Attention Graph Neural Networks Highlight: Our aim is to achieve the best of both worlds, and we do so by introducing a novel GNN architecture, the Instruction Pointer Attention Graph Neural Networks (IPA-GNN), which achieves improved systematic generalization on the task of learning to execute programs using control flow graphs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Bieber; Charles Sutton; Hugo Larochelle; Daniel Tarlow; | |
| 724 | AutoPrivacy: Automated Layer-wise Parameter Selection For Secure Neural Network Inference Highlight: In this paper, for fast and accurate secure neural network inference, we propose an automated layer-wise parameter selector, AutoPrivacy, that leverages deep reinforcement learning to automatically determine a set of HE parameters for each linear layer in a HPPNN. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qian Lou; Song Bian; Lei Jiang; | |
| 725 | Baxter Permutation Process Highlight: In this paper, a Bayesian nonparametric (BNP) model for Baxter permutations (BPs), termed BP process (BPP) is proposed and applied to relational data analysis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Masahiro Nakano; Akisato Kimura; Takeshi Yamada; Naonori Ueda; | |
| 726 | Characterizing Emergent Representations In A Space Of Candidate Learning Rules For Deep Networks Highlight: Here we present a continuous two-dimensional space of candidate learning rules, parameterized by levels of top-down feedback and Hebbian learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yinan Cao; Christopher Summerfield; Andrew Saxe; | |
| 727 | Fast, Accurate, And Simple Models For Tabular Data Via Augmented Distillation Highlight: To improve the deployment of AutoML on tabular data, we propose FAST-DAD to distill arbitrarily-complex ensemble predictors into individual models like boosted trees, random forests, and deep networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rasool Fakoor; Jonas W. Mueller; Nick Erickson; Pratik Chaudhari; Alexander J. Smola; | |
| 728 | Adaptive Probing Policies For Shortest Path Routing Highlight: Inspired by traffic routing applications, we consider the problem of finding the shortest path from a source $s$ to a destination $t$ in a graph, when the lengths of the edges are unknown. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aditya Bhaskara; Sreenivas Gollapudi; Kostas Kollias; Kamesh Munagala; | |
| 729 | Approximate Heavily-Constrained Learning With Lagrange Multiplier Models Highlight: Our proposal is to associate a feature vector with each constraint, and to learn a “multiplier model’’ that maps each such vector to the corresponding Lagrange multiplier. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Harikrishna Narasimhan; Andrew Cotter; Yichen Zhou; Serena Wang; Wenshuo Guo; | |
| 730 | Faster Randomized Infeasible Interior Point Methods For Tall/Wide Linear Programs Highlight: In this paper, we consider \emph{infeasible} IPMs for the special case where the number of variables is much larger than the number of constraints (i.e., wide), or vice-versa (i.e., tall) by taking the dual. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Agniva Chowdhury; Palma London; Haim Avron; Petros Drineas; | |
| 731 | Sliding Window Algorithms For K-Clustering Problems Highlight: In this work, we focus on $k$-clustering problems such as $k$-means and $k$-median. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michele Borassi; Alessandro Epasto; Silvio Lattanzi; Sergei Vassilvitskii; Morteza Zadimoghaddam; | |
| 732 | AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning Highlight: Unlike existing methods, we propose an adaptive sharing approach, calledAdaShare, that decides what to share across which tasks to achieve the best recognition accuracy, while taking resource efficiency into account. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ximeng Sun; Rameswar Panda; Rogerio Feris; Kate Saenko; | code |
| 733 | Approximate Cross-Validation For Structured Models Highlight: In the present work, we address (i) by extending ACV to CV schemes with dependence structure between the folds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Soumya Ghosh; William T. Stephenson; Tin D. Nguyen; Sameer Deshpande; Tamara Broderick; | |
| 734 | Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, And Data Augmentation Highlight: We introduce Exemplar VAEs, a family of generative models that bridge the gap between parametric and non-parametric, exemplar based generative models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sajad Norouzi; David J. Fleet; Mohammad Norouzi; | |
| 735 | Debiased Contrastive Learning Highlight: Motivated by this observation, we develop a debiased contrastive objective that corrects for the sampling of same-label datapoints, even without knowledge of the true labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ching-Yao Chuang; Joshua Robinson; Yen-Chen Lin; Antonio Torralba; Stefanie Jegelka; | |
| 736 | UCSG-NET- Unsupervised Discovering Of Constructive Solid Geometry Tree Highlight: On the contrary, we propose a model that extracts a CSG parse tree without any supervision – UCSG-Net. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kacper Kania; Maciej Zieba; Tomasz Kajdanowicz; | |
| 737 | Generalized Boosting Highlight: In this work, we specifically focus on one form of aggregation – \emph{function composition}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arun Suggala; Bingbin Liu; Pradeep Ravikumar; | |
| 738 | COT-GAN: Generating Sequential Data Via Causal Optimal Transport Highlight: We introduce COT-GAN, an adversarial algorithm to train implicit generative models optimized for producing sequential data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianlin Xu; Wenliang Le; Michael Munn; Beatrice Acciaio; | |
| 739 | Impossibility Results For Grammar-Compressed Linear Algebra Highlight: In this paper we consider lossless compression schemes, and ask if we can run our computations on the compressed data as efficiently as if the original data was that small. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amir Abboud; Arturs Backurs; Karl Bringmann; Marvin K�nnemann; | |
| 740 | Understanding Spiking Networks Through Convex Optimization Highlight: Here we turn these findings around and show that virtually all inhibition-dominated SNNs can be understood through the lens of convex optimization, with network connectivity, timescales, and firing thresholds being intricately linked to the parameters of underlying convex optimization problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Allan Mancoo; Sander Keemink; Christian K. Machens; | |
| 741 | Better Full-Matrix Regret Via Parameter-Free Online Learning Highlight: We provide online convex optimization algorithms that guarantee improved full-matrix regret bounds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ashok Cutkosky; | |
| 742 | Large-Scale Methods For Distributionally Robust Optimization Highlight: We propose and analyze algorithms for distributionally robust optimization of convex losses with conditional value at risk (CVaR) and $\chi^2$ divergence uncertainty sets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Daniel Levy; Yair Carmon; John C. Duchi; Aaron Sidford; | |
| 743 | Analysis And Design Of Thompson Sampling For Stochastic Partial Monitoring Highlight: To mitigate these problems, we present a novel Thompson-sampling-based algorithm, which enables us to exactly sample the target parameter from the posterior distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Taira Tsuchiya; Junya Honda; Masashi Sugiyama; | |
| 744 | Bandit Linear Control Highlight: We present a new and efficient algorithm that, for strongly convex and smooth costs, obtains regret that grows with the square root of the time horizon T. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Asaf Cassel; Tomer Koren; | |
| 745 | Refactoring Policy For Compositional Generalizability Using Self-Supervised Object Proposals Highlight: We propose a two-stage framework, which refactorizes a high-reward teacher policy into a generalizable student policy with strong inductive bias. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tongzhou Mu; Jiayuan Gu; Zhiwei Jia; Hao Tang; Hao Su; | |
| 746 | PEP: Parameter Ensembling By Perturbation Highlight: We introduce a new approach, Parameter Ensembling by Perturbation (PEP), that constructs an ensemble of parameter values as random perturbations of the optimal parameter set from training by a Gaussian with a single variance parameter. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alireza Mehrtash; Purang Abolmaesumi; Polina Golland; Tina Kapur; Demian Wassermann; William Wells; | |
| 747 | Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View Highlight: In this paper, we take a step in this direction by providing the first asymptotically precise analysis of linear multiclass classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christos Thrampoulidis; Samet Oymak; Mahdi Soltanolkotabi; | |
| 748 | Adversarial Example Games Highlight: In this work, we provide a theoretical foundation for crafting transferable adversarial examples to entire hypothesis classes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joey Bose; Gauthier Gidel; Hugo Berard; Andre Cianflone; Pascal Vincent; Simon Lacoste-Julien; Will Hamilton; | |
| 749 | Residual Distillation: Towards Portable Deep Neural Networks Without Shortcuts Highlight: In particular, we propose a novel joint-training framework to train plain CNN by leveraging the gradients of the ResNet counterpart. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guilin Li; Junlei Zhang; Yunhe Wang; Chuanjian Liu; Matthias Tan; Yunfeng Lin; Wei Zhang; Jiashi Feng; Tong Zhang; | code |
| 750 | Provably Efficient Neural Estimation Of Structural Equation Models: An Adversarial Approach Highlight: We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using the stochastic gradient descent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luofeng Liao; You-Lin Chen; Zhuoran Yang; Bo Dai; Mladen Kolar; Zhaoran Wang; | |
| 751 | Security Analysis Of Safe And Seldonian Reinforcement Learning Algorithms Highlight: We introduce a new measure of security to quantify the susceptibility to perturbations in training data by creating an attacker model that represents a worst-case analysis, and show that a couple of Seldonian RL methods are extremely sensitive to even a few data corruptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pinar Ozisik; Philip S. Thomas; | |
| 752 | Learning To Play Sequential Games Versus Unknown Opponents Highlight: We propose a novel algorithm for the learner when playing against an adversarial sequence of opponents. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pier Giuseppe Sessa; Ilija Bogunovic; Maryam Kamgarpour; Andreas Krause; | |
| 753 | Further Analysis Of Outlier Detection With Deep Generative Models Highlight: In this work, we present a possible explanation for this phenomenon, starting from the observation that a model’s typical set and high-density region may not conincide. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziyu Wang; Bin Dai; David Wipf; Jun Zhu; | |
| 754 | Bridging Imagination And Reality For Model-Based Deep Reinforcement Learning Highlight: In this paper, we propose a novel model-based reinforcement learning algorithm, called BrIdging Reality and Dream (BIRD). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guangxiang Zhu; Minghao Zhang; Honglak Lee; Chongjie Zhang; | |
| 755 | Neural Networks Learning And Memorization With (almost) No Over-Parameterization Highlight: In this paper we prove that SGD on depth two neural networks can memorize samples, learn polynomials with bounded weights, and learn certain kernel spaces, with {\em near optimal} network size, sample complexity, and runtime. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amit Daniely; | |
| 756 | Exploiting Higher Order Smoothness In Derivative-free Optimization And Continuous Bandits Highlight: We address the problem of zero-order optimization of a strongly convex function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arya Akhavan; Massimiliano Pontil; Alexandre Tsybakov; | |
| 757 | Towards A Combinatorial Characterization Of Bounded-Memory Learning Highlight: In this paper we aim to develop combinatorial dimensions that characterize bounded memory learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alon Gonen; Shachar Lovett; Michal Moshkovitz; | |
| 758 | Chaos, Extremism And Optimism: Volume Analysis Of Learning In Games Highlight: We perform volume analysis of Multiplicative Weights Updates (MWU) and its optimistic variant (OMWU) in zero-sum as well as coordination games. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yun Kuen Cheung; Georgios Piliouras; | |
| 759 | On Regret With Multiple Best Arms Highlight: Our goal is to design algorithms that can automatically adapt to the unknown hardness of the problem, i.e., the number of best arms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yinglun Zhu; Robert Nowak; | |
| 760 | Matrix Completion With Hierarchical Graph Side Information Highlight: We consider a matrix completion problem that exploits social or item similarity graphs as side information. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adel Elmahdy; Junhyung Ahn; Changho Suh; Soheil Mohajer; | |
| 761 | Is Long Horizon RL More Difficult Than Short Horizon RL? Highlight: Our analysis introduces two ideas: (i) the construction of an $\varepsilon$-net for near-optimal policies whose log-covering number scales only logarithmically with the planning horizon, and (ii) the Online Trajectory Synthesis algorithm, which adaptively evaluates all policies in a given policy class and enjoys a sample complexity that scales logarithmically with the cardinality of the given policy class. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruosong Wang; Simon S. Du; Lin Yang; Sham Kakade; | |
| 762 | Hamiltonian Monte Carlo Using An Adjoint-differentiated Laplace Approximation: Bayesian Inference For Latent Gaussian Models And Beyond Highlight: To implement this scheme efficiently, we derive a novel adjoint method that propagates the minimal information needed to construct the gradient of the approximate marginal likelihood. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Charles Margossian; Aki Vehtari; Daniel Simpson; Raj Agrawal; | |
| 763 | Adversarial Learning For Robust Deep Clustering Highlight: In this paper, we propose a robust deep clustering method based on adversarial learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xu Yang; Cheng Deng; Kun Wei; Junchi Yan; Wei Liu; | code |
| 764 | Learning Mutational Semantics Highlight: We propose an unsupervised solution based on language models that simultaneously learn continuous latent representations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Brian Hie; Ellen Zhong; Bryan Bryson; Bonnie Berger; | |
| 765 | Learning To Learn Variational Semantic Memory Highlight: In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiantong Zhen; Yingjun Du; Huan Xiong; Qiang Qiu; Cees Snoek; Ling Shao; | |
| 766 | Myersonian Regression Highlight: Motivated by pricing applications in online advertising, we study a variant of linear regression with a discontinuous loss function that we term Myersonian regression. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Allen Liu; Renato Leme; Jon Schneider; | |
| 767 | Learnability With Indirect Supervision Signals Highlight: In this paper, we develop a unified theoretical framework for multi-class classification when the supervision is provided by a variable that contains nonzero mutual information with the gold label. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaifu Wang; Qiang Ning; Dan Roth; | |
| 768 | Towards Safe Policy Improvement For Non-Stationary MDPs Highlight: We take the first steps towards ensuring safety, with high confidence, for smoothly-varying non-stationary decision problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yash Chandak; Scott Jordan; Georgios Theocharous; Martha White; Philip S. Thomas; | |
| 769 | Finer Metagenomic Reconstruction Via Biodiversity Optimization Highlight: Here, we leverage a recently developed notion of biological diversity that simultaneously accounts for organism similarities and retains the optimization strategy underlying compressive-sensing-based approaches. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simon Foucart; David Koslicki; | |
| 770 | Causal Discovery In Physical Systems From Videos Highlight: In particular, our goal is to discover the structural dependencies among environmental and object variables: inferring the type and strength of interactions that have a causal effect on the behavior of the dynamical system. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunzhu Li; Antonio Torralba; Anima Anandkumar; Dieter Fox; Animesh Garg; | |
| 771 | Glyph: Fast And Accurately Training Deep Neural Networks On Encrypted Data Highlight: In this paper, we propose, Glyph, an FHE-based technique to fast and accurately train DNNs on encrypted data by switching between TFHE (Fast Fully Homomorphic Encryption over the Torus) and BGV cryptosystems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qian Lou; Bo Feng; Geoffrey Charles Fox; Lei Jiang; | |
| 772 | Smoothed Analysis Of Online And Differentially Private Learning Highlight: In this paper, we apply the framework of smoothed analysis [Spielman and Teng, 2004], in which adversarially chosen inputs are perturbed slightly by nature. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nika Haghtalab; Tim Roughgarden; Abhishek Shetty; | |
| 773 | Self-Paced Deep Reinforcement Learning Highlight: In this paper, we propose an answer by interpreting the curriculum generation as an inference problem, where distributions over tasks are progressively learned to approach the target task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pascal Klink; Carlo D'Eramo; Jan R. Peters; Joni Pajarinen; | |
| 774 | Kalman Filtering Attention For User Behavior Modeling In CTR Prediction Highlight: To tackle the two limitations, we propose a novel attention mechanism, termed Kalman Filtering Attention (KFAtt), that considers the weighted pooling in attention as a maximum a posteriori (MAP) estimation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hu Liu; Jing LU; Xiwei Zhao; Sulong Xu; Hao Peng; Yutong Liu; Zehua Zhang; Jian Li; Junsheng Jin; Yongjun Bao; Weipeng Yan; | |
| 775 | Towards Maximizing The Representation Gap Between In-Domain & Out-of-Distribution Examples Highlight: We address this shortcoming by proposing a novel loss function for DPN to maximize the representation gap between in-domain and OOD examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jay Nandy; Wynne Hsu; Mong Li Lee; | |
| 776 | Fully Convolutional Mesh Autoencoder Using Efficient Spatially Varying Kernels Highlight: In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yi Zhou; Chenglei Wu; Zimo Li; Chen Cao; Yuting Ye; Jason Saragih; Hao Li; Yaser Sheikh; | |
| 777 | GNNGuard: Defending Graph Neural Networks Against Adversarial Attacks Highlight: Here, we develop GNNGuard, a general defense approach against a variety of training-time attacks that perturb the discrete graph structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiang Zhang; Marinka Zitnik; | |
| 778 | Geo-PIFu: Geometry And Pixel Aligned Implicit Functions For Single-view Human Reconstruction Highlight: We propose Geo-PIFu, a method to recover a 3D mesh from a monocular color image of a clothed person. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tong He; John Collomosse; Hailin Jin; Stefano Soatto; | |
| 779 | Optimal Visual Search Based On A Model Of Target Detectability In Natural Images Highlight: We present a novel approach for approximating the foveated detectability of a known target in natural backgrounds based on biological aspects of human visual system. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shima Rashidi; Krista Ehinger; Andrew Turpin; Lars Kulik; | |
| 780 | Towards Convergence Rate Analysis Of Random Forests For Classification Highlight: We present the first finite-sample rate O(n^{-1/(8d+2)}) on the convergence of pure random forests for classification, which can be improved to be of O(n^{-1/(3.87d+2)}) by considering the midpoint splitting mechanism. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei Gao; Zhi-Hua Zhou; | |
| 781 | List-Decodable Mean Estimation Via Iterative Multi-Filtering Highlight: We study the problem of {\em list-decodable mean estimation} for bounded covariance distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilias Diakonikolas; Daniel Kane; Daniel Kongsgaard; | |
| 782 | Exact Recovery Of Mangled Clusters With Same-Cluster Queries Highlight: We study the cluster recovery problem in the semi-supervised active clustering framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marco Bressan; Nicol� Cesa-Bianchi; Silvio Lattanzi; Andrea Paudice; | |
| 783 | Steady State Analysis Of Episodic Reinforcement Learning Highlight: In this paper we proved that unique steady-state distributions pervasively exist in the learning environment of episodic learning tasks, and that the marginal distributions of the system state indeed approach to the steady state in essentially all episodic tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huang Bojun; | |
| 784 | Direct Feedback Alignment Scales To Modern Deep Learning Tasks And Architectures Highlight: Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment (DFA) to neural view synthesis, recommender systems, geometric learning, and natural language processing. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julien Launay; Iacopo Poli; Fran�ois Boniface; Florent Krzakala; | |
| 785 | Bayesian Optimization For Iterative Learning Highlight: In this paper, we present a Bayesian optimization(BO) approach which exploits the iterative structure of learning algorithms for efficient hyperparameter tuning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vu Nguyen; Sebastian Schulze; Michael Osborne; | |
| 786 | Minimax Bounds For Generalized Linear Models Highlight: We establish a new class of minimax prediction error bounds for generalized linear models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kuan-Yun Lee; Thomas Courtade; | |
| 787 | Projection Robust Wasserstein Distance And Riemannian Optimization Highlight: Our contribution in this paper is to revisit the original motivation behind WPP/PRW, but take the hard route of showing that, despite its non-convexity and lack of nonsmoothness, and even despite some hardness results proved by~\citet{Niles-2019-Estimation} in a minimax sense, the original formulation for PRW/WPP \textit{can} be efficiently computed in practice using Riemannian optimization, yielding in relevant cases better behavior than its convex relaxation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianyi Lin; Chenyou Fan; Nhat Ho; Marco Cuturi; Michael Jordan; | |
| 788 | CoinDICE: Off-Policy Confidence Interval Estimation Highlight: By applying the generalized empirical likelihood method to the resulting Lagrangian, we propose CoinDICE, a novel and efficient algorithm for computing confidence intervals. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bo Dai; Ofir Nachum; Yinlam Chow; Lihong Li; Csaba Szepesvari; Dale Schuurmans; | |
| 789 | Simple And Fast Algorithm For Binary Integer And Online Linear Programming Highlight: In this paper, we develop a simple and fast online algorithm for solving a class of binary integer linear programs (LPs) arisen in the general resource allocation problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaocheng Li; Chunlin Sun; Yinyu Ye; | |
| 790 | Learning Diverse And Discriminative Representations Via The Principle Of Maximal Coding Rate Reduction Highlight: To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of {\em Maximal Coding Rate Reduction} ($\text{MCR}^2$), an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaodong Yu; Kwan Ho Ryan Chan; Chong You; Chaobing Song; Yi Ma; | |
| 791 | Learning Rich Rankings Highlight: In this work, we contribute a contextual repeated selection (CRS) model that leverages recent advances in choice modeling to bring a natural multimodality and richness to the rankings space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arjun Seshadri; Stephen Ragain; Johan Ugander; | |
| 792 | Color Visual Illusions: A Statistics-based Computational Model Highlight: Given this tool, we present a model that supports the approach and explains lightness and color visual illusions in a unified manner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Elad Hirsch; Ayellet Tal; | |
| 793 | Retrieval-Augmented Generation For Knowledge-Intensive NLP Tasks Highlight: We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Patrick Lewis; Ethan Perez; Aleksandra Piktus; Fabio Petroni; Vladimir Karpukhin; Naman Goyal; Heinrich K�ttler; Mike Lewis; Wen-tau Yih; Tim Rockt�schel; Sebastian Riedel; Douwe Kiela; | |
| 794 | Universal Guarantees For Decision Tree Induction Via A Higher-order Splitting Criterion Highlight: We propose a simple extension of {\sl top-down decision tree learning heuristics} such as ID3, C4.5, and CART. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guy Blanc; Neha Gupta; Jane Lange; Li-Yang Tan; | |
| 795 | Trade-offs And Guarantees Of Adversarial Representation Learning For Information Obfuscation Highlight: In light of this gap, we develop a novel theoretical framework for attribute obfuscation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Han Zhao; Jianfeng Chi; Yuan Tian; Geoffrey J. Gordon; | |
| 796 | A Boolean Task Algebra For Reinforcement Learning Highlight: In this work we formalise the logical composition of tasks as a Boolean algebra. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Geraud Nangue Tasse; Steven James; Benjamin Rosman; | |
| 797 | Learning With Differentiable Pertubed Optimizers Highlight: In order to expand the scope of learning problems that can be solved in an end-to-end fashion, we propose a systematic method to transform optimizers into operations that are differentiable and never locally constant. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Quentin Berthet; Mathieu Blondel; Olivier Teboul; Marco Cuturi; Jean-Philippe Vert; Francis Bach; | |
| 798 | Optimal Learning From Verified Training Data Highlight: To tackle this problem, we present a Stackelberg competition model for least squares regression, in which data is provided by agents who wish to achieve specific predictions for their data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicholas Bishop; Long Tran-Thanh; Enrico Gerding; | |
| 799 | Online Linear Optimization With Many Hints Highlight: We study an online linear optimization (OLO) problem in which the learner is provided access to $K$ “hint” vectors in each round prior to making a decision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aditya Bhaskara; Ashok Cutkosky; Ravi Kumar; Manish Purohit; | |
| 800 | Dynamical Mean-field Theory For Stochastic Gradient Descent In Gaussian Mixture Classification Highlight: We apply dynamical mean-field theory from statistical physics to track the dynamics of the algorithm in the high-dimensional limit via a self-consistent stochastic process. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Francesca Mignacco; Florent Krzakala; Pierfrancesco Urbani; Lenka Zdeborov�; | |
| 801 | Causal Discovery From Soft Interventions With Unknown Targets: Characterization And Learning Highlight: In this paper, we investigate the task of structural learning in non-Markovian systems (i.e., when latent variables affect more than one observable) from a combination of observational and soft experimental data when the interventional targets are unknown. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amin Jaber; Murat Kocaoglu; Karthikeyan Shanmugam; Elias Bareinboim; | |
| 802 | Exploiting The Surrogate Gap In Online Multiclass Classification Highlight: We present \textproc{Gaptron}, a randomized first-order algorithm for online multiclass classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dirk van der Hoeven; | |
| 803 | The Pitfalls Of Simplicity Bias In Neural Networks Highlight: We attempt to reconcile SB and the superior standard generalization of neural networks with the non-robustness observed in practice by introducing piecewise-linear and image-based datasets, which (a) incorporate a precise notion of simplicity, (b) comprise multiple predictive features with varying levels of simplicity, and (c) capture the non-robustness of neural networks trained on real data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Harshay Shah; Kaustav Tamuly; Aditi Raghunathan; Prateek Jain; Praneeth Netrapalli; | |
| 804 | Automatically Learning Compact Quality-aware Surrogates For Optimization Problems Highlight: To address these shortcomings, we learn a low-dimensional surrogate model of a large optimization problem by representing the feasible space in terms of meta-variables, each of which is a linear combination of the original variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kai Wang; Bryan Wilder; Andrew Perrault; Milind Tambe; | |
| 805 | Empirical Likelihood For Contextual Bandits Highlight: We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nikos Karampatziakis; John Langford; Paul Mineiro; | |
| 806 | Can Q-Learning With Graph Networks Learn A Generalizable Branching Heuristic For A SAT Solver? Highlight: We present Graph-Q-SAT, a branching heuristic for a Boolean SAT solver trained with value-based reinforcement learning (RL) using Graph Neural Networks for function approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vitaly Kurin; Saad Godil; Shimon Whiteson; Bryan Catanzaro; | |
| 807 | Non-reversible Gaussian Processes For Identifying Latent Dynamical Structure In Neural Data Highlight: We therefore introduce GPFADS (Gaussian Process Factor Analysis with Dynamical Structure), which models single-trial neural population activity using low-dimensional, non-reversible latent processes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Virginia Rutten; Alberto Bernacchia; Maneesh Sahani; Guillaume Hennequin; | |
| 808 | Listening To Sounds Of Silence For Speech Denoising Highlight: We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruilin Xu; Rundi Wu; Yuko Ishiwaka; Carl Vondrick; Changxi Zheng; | |
| 809 | BoxE: A Box Embedding Model For Knowledge Base Completion Highlight: Here, we propose a spatio-translational embedding model, called BoxE, that simultaneously addresses all these limitations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ralph Abboud; Ismail Ceylan; Thomas Lukasiewicz; Tommaso Salvatori; | |
| 810 | Coherent Hierarchical Multi-Label Classification Networks Highlight: In this paper, we propose C-HMCNN(h), a novel approach for HMC problems, which, given a network h for the underlying multi-label classification problem, exploits the hierarchy information in order to produce predictions coherent with the constraint and improve performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eleonora Giunchiglia; Thomas Lukasiewicz; | |
| 811 | Walsh-Hadamard Variational Inference For Bayesian Deep Learning Highlight: Inspired by the literature on kernel methods, and in particular on structured approximations of distributions of random matrices, this paper proposes Walsh-Hadamard Variational Inference (WHVI), which uses Walsh-Hadamardbased factorization strategies to reduce the parameterization and accelerate computations, thus avoiding over-regularization issues with the variational objective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simone Rossi; Sebastien Marmin; Maurizio Filippone; | |
| 812 | Federated Bayesian Optimization Via Thompson Sampling Highlight: This paper presents federated Thompson sampling (FTS) which overcomes a number of key challenges of FBO and FL in a principled way: We (a) use random Fourier features to approximate the Gaussian process surrogate model used in BO, which naturally produces the parameters to be exchanged between agents, (b) design FTS based on Thompson sampling, which significantly reduces the number of parameters to be exchanged, and (c) provide a theoretical convergence guarantee that is robust against heterogeneous agents, which is a major challenge in FL and FBO. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhongxiang Dai; Bryan Kian Hsiang Low; Patrick Jaillet; | |
| 813 | MultiON: Benchmarking Semantic Map Memory Using Multi-Object Navigation Highlight: We propose the multiON task, which requires navigation to an episode-specific sequence of objects in a realistic environment. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Saim Wani; Shivansh Patel; Unnat Jain; Angel Chang; Manolis Savva; | |
| 814 | Neural Complexity Measures Highlight: We propose Neural Complexity (NC), a meta-learning framework for predicting generalization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yoonho Lee; Juho Lee; Sung Ju Hwang; Eunho Yang; Seungjin Choi; | |
| 815 | Optimal Iterative Sketching Methods With The Subsampled Randomized Hadamard Transform Highlight: Our technical contributions include a novel formula for the second moment of the inverse of projected matrices. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Lacotte; Sifan Liu; Edgar Dobriban; Mert Pilanci; | |
| 816 | Provably Adaptive Reinforcement Learning In Metric Spaces Highlight: We provide a refined analysis of the algorithm of Sinclair, Banerjee, and Yu (2019) and show that its regret scales with the zooming dimension of the instance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tongyi Cao; Akshay Krishnamurthy; | |
| 817 | ShapeFlow: Learnable Deformation Flows Among 3D Shapes Highlight: We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chiyu Jiang; Jingwei Huang; Andrea Tagliasacchi; Leonidas J. Guibas; | |
| 818 | Self-Supervised Learning By Cross-Modal Audio-Video Clustering Highlight: Based on this intuition, we propose Cross-Modal Deep Clustering (XDC), a novel self-supervised method that leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for the other modality (e.g., video). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Humam Alwassel; Dhruv Mahajan; Bruno Korbar; Lorenzo Torresani; Bernard Ghanem; Du Tran; | |
| 819 | Optimal Query Complexity Of Secure Stochastic Convex Optimization Highlight: We study the \emph{secure} stochastic convex optimization problem: a learner aims to learn the optimal point of a convex function through sequentially querying a (stochastic) gradient oracle, in the meantime, there exists an adversary who aims to free-ride and infer the learning outcome of the learner from observing the learner’s queries. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei Tang; Chien-Ju Ho; Yang Liu; | |
| 820 | DynaBERT: Dynamic BERT With Adaptive Width And Depth Highlight: In this paper, we propose a novel dynamic BERT model (abbreviated as DynaBERT), which can flexibly adjust the size and latency by selecting adaptive width and depth. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lu Hou; Zhiqi Huang; Lifeng Shang; Xin Jiang; Xiao Chen; Qun Liu; | code |
| 821 | Generalization Bound Of Gradient Descent For Non-Convex Metric Learning Highlight: In this paper, we theoretically address this question and prove the agnostic Probably Approximately Correct (PAC) learnability for metric learning algorithms with non-convex objective functions optimized via gradient descent (GD); in particular, our theoretical guarantee takes the iteration number into account. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
MINGZHI DONG; Xiaochen Yang; Rui Zhu; Yujiang Wang; Jing-Hao Xue; | |
| 822 | Dynamic Submodular Maximization Highlight: In this paper, we propose the first dynamic algorithm for this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Morteza Monemizadeh; | |
| 823 | Inference For Batched Bandits Highlight: In this work, we develop methods for inference on data collected in batches using a bandit algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kelly Zhang; Lucas Janson; Susan Murphy; | |
| 824 | Approximate Cross-Validation With Low-Rank Data In High Dimensions Highlight: Guided by this observation, we develop a new algorithm for ACV that is fast and accurate in the presence of ALR data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
William T. Stephenson; Madeleine Udell; Tamara Broderick; | |
| 825 | GANSpace: Discovering Interpretable GAN Controls Highlight: This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Erik H�rk�nen; Aaron Hertzmann; Jaakko Lehtinen; Sylvain Paris; | |
| 826 | Differentiable Expected Hypervolume Improvement For Parallel Multi-Objective Bayesian Optimization Highlight: We derive a novel formulation of q-Expected Hypervolume Improvement (qEHVI), an acquisition function that extends EHVI to the parallel, constrained evaluation setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Samuel Daulton; Maximilian Balandat; Eytan Bakshy; | |
| 827 | Neuron-level Structured Pruning Using Polarization Regularizer Highlight: To achieve this goal, we propose a new regularizer on scaling factors, namely polarization regularizer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tao Zhuang; Zhixuan Zhang; Yuheng Huang; Xiaoyi Zeng; Kai Shuang; Xiang Li; | |
| 828 | Limits On Testing Structural Changes In Ising Models Highlight: We present novel information-theoretic limits on detecting sparse changes in Isingmodels, a problem that arises in many applications where network changes canoccur due to some external stimuli. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aditya Gangrade; Bobak Nazer; Venkatesh Saligrama; | |
| 829 | Field-wise Learning For Multi-field Categorical Data Highlight: We propose a new method for learning with multi-field categorical data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhibin Li; Jian Zhang; Yongshun Gong; Yazhou Yao; Qiang Wu; | code |
| 830 | Continual Learning In Low-rank Orthogonal Subspaces Highlight: We propose to learn tasks in different (low-rank) vector subspaces that are kept orthogonal to each other in order to minimize interference. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arslan Chaudhry; Naeemullah Khan; Puneet Dokania; Philip Torr; | |
| 831 | Unsupervised Learning Of Visual Features By Contrasting Cluster Assignments Highlight: In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mathilde Caron; Ishan Misra; Julien Mairal; Priya Goyal; Piotr Bojanowski; Armand Joulin; | |
| 832 | Sharpened Generalization Bounds Based On Conditional Mutual Information And An Application To Noisy, Iterative Algorithms Highlight: In this work, we study the proposal, by Steinke and Zakynthinou (2020), to reason about the generalization error of a learning algorithm by introducing a super sample that contains the training sample as a random subset and computing mutual information conditional on the super sample. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mahdi Haghifam; Jeffrey Negrea; Ashish Khisti; Daniel M. Roy; Gintare Karolina Dziugaite; | |
| 833 | Learning Deformable Tetrahedral Meshes For 3D Reconstruction Highlight: We introduce \emph{Deformable Tetrahedral Meshes} (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jun Gao; Wenzheng Chen; Tommy Xiang; Alec Jacobson; Morgan McGuire; Sanja Fidler; | |
| 834 | Information Theoretic Limits Of Learning A Sparse Rule Highlight: We consider generalized linear models in regimes where the number of nonzero components of the signal and accessible data points are sublinear with respect to the size of the signal. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cl�ment Luneau; jean barbier; Nicolas Macris; | |
| 835 | Self-supervised Learning Through The Eyes Of A Child Highlight: In this paper, our goal is precisely to achieve such progress by utilizing modern self-supervised deep learning methods and a recent longitudinal, egocentric video dataset recorded from the perspective of three young children (Sullivan et al., 2020). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emin Orhan; Vaibhav Gupta; Brenden M. Lake; | |
| 836 | Unsupervised Semantic Aggregation And Deformable Template Matching For Semi-Supervised Learning Highlight: In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tao Han; Junyu Gao; Yuan Yuan; Qi Wang; | code |
| 837 | A Game-theoretic Analysis Of Networked System Control For Common-pool Resource Management Using Multi-agent Reinforcement Learning Highlight: However, instead of focusing on biologically evolved human-like agents, our concern is rather to better understand the learning and operating behaviour of engineered networked systems comprising general-purpose reinforcement learning agents, subject only to nonbiological constraints such as memory, computation and communication bandwidth. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arnu Pretorius; Scott Cameron; Elan van Biljon; Thomas Makkink; Shahil Mawjee; Jeremy du Plessis; Jonathan Shock; Alexandre Laterre; Karim Beguir; | |
| 838 | What Shapes Feature Representations? Exploring Datasets, Architectures, And Training Highlight: We study these questions using synthetic datasets in which the task-relevance of input features can be controlled directly. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Katherine Hermann; Andrew Lampinen; | |
| 839 | Optimal Best-arm Identification In Linear Bandits Highlight: We study the problem of best-arm identification with fixed confidence in stochastic linear bandits. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yassir Jedra; Alexandre Proutiere; | |
| 840 | Data Diversification: A Simple Strategy For Neural Machine Translation Highlight: We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xuan-Phi Nguyen; Shafiq Joty; Kui Wu; Ai Ti Aw; | |
| 841 | Interstellar: Searching Recurrent Architecture For Knowledge Graph Embedding Highlight: In this work, based on the relational paths, which are composed of a sequence of triplets, we define the Interstellar as a recurrent neural architecture search problem for the short-term and long-term information along the paths. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yongqi Zhang; Quanming Yao; Lei Chen; | |
| 842 | CoSE: Compositional Stroke Embeddings Highlight: We present a generative model for stroke-based drawing tasks which is able to model complex free-form structures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emre Aksan; Thomas Deselaers; Andrea Tagliasacchi; Otmar Hilliges; | code |
| 843 | Learning Multi-Agent Coordination For Enhancing Target Coverage In Directional Sensor Networks Highlight: To realize this, we propose a Hierarchical Target-oriented Multi-Agent Coordination (HiT-MAC), which decomposes the target coverage problem into two-level tasks: targets assignment by a coordinator and tracking assigned targets by executors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jing Xu; Fangwei Zhong; Yizhou Wang; | |
| 844 | Biological Credit Assignment Through Dynamic Inversion Of Feedforward Networks Highlight: Overall, our work introduces an alternative perspective on credit assignment in the brain, and proposes a special role for temporal dynamics and feedback control during learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
William Podlaski; Christian K. Machens; | |
| 845 | Discriminative Sounding Objects Localization Via Self-supervised Audiovisual Matching Highlight: In this paper, we propose a two-stage learning framework to perform self-supervised class-aware sounding object localization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Di Hu; Rui Qian; Minyue Jiang; Xiao Tan; Shilei Wen; Errui Ding; Weiyao Lin; Dejing Dou; | code |
| 846 | Learning Multi-Agent Communication Through Structured Attentive Reasoning Highlight: By developing an explicit architecture that is targeted towards communication, our work aims to open new directions to overcome important challenges in multi-agent cooperation through learned communication. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Murtaza Rangwala; Ryan Williams; | |
| 847 | Private Identity Testing For High-Dimensional Distributions Highlight: In this work we present novel differentially private identity (goodness-of-fit) testers for natural and widely studied classes of multivariate product distributions: Gaussians in R^d with known covariance and product distributions over {\pm 1}^d. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cl�ment L. Canonne; Gautam Kamath; Audra McMillan; Jonathan Ullman; Lydia Zakynthinou; | |
| 848 | On The Optimal Weighted $\ell_2$ Regularization In Overparameterized Linear Regression Highlight: We consider the linear model $\vy=\vX\vbeta_{\star}+\vepsilon$ with $\vX\in \mathbb{R}^{n\times p}$ in the overparameterized regime $p>n$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Denny Wu; Ji Xu; | |
| 849 | An Efficient Asynchronous Method For Integrating Evolutionary And Gradient-based Policy Search Highlight: In this paper, we introduce an Asynchronous Evolution Strategy-Reinforcement Learning (AES-RL) that maximizes the parallel efficiency of ES and integrates it with policy gradient methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kyunghyun Lee; Byeong-Uk Lee; Ukcheol Shin; In So Kweon; | |
| 850 | MetaSDF: Meta-Learning Signed Distance Functions Highlight: Here, we formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vincent Sitzmann; Eric Chan; Richard Tucker; Noah Snavely; Gordon Wetzstein; | |
| 851 | Simple And Scalable Sparse K-means Clustering Via Feature Ranking Highlight: In this paper, we propose a novel framework for sparse k-means clustering that is intuitive, simple to implement, and competitive with state-of-the-art algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhiyue Zhang; Kenneth Lange; Jason Xu; | |
| 852 | Model-based Adversarial Meta-Reinforcement Learning Highlight: We propose a minimax objective and optimize it by alternating between learning the dynamics model on a fixed task and finding the \textit{adversarial} task for the current model — the task for which the policy induced by the model is maximally suboptimal. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zichuan Lin; Garrett Thomas; Guangwen Yang; Tengyu Ma; | |
| 853 | Graph Policy Network For Transferable Active Learning On Graphs Highlight: In this paper, we study active learning for GNNs, i.e., how to efficiently label the nodes on a graph to reduce the annotation cost of training GNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shengding Hu; Zheng Xiong; Meng Qu; Xingdi Yuan; Marc-Alexandre C�t�; Zhiyuan Liu; Jian Tang; | |
| 854 | Towards A Better Global Loss Landscape Of GANs Highlight: In this work, we perform a global landscape analysis of the empirical loss of GANs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruoyu Sun; Tiantian Fang; Alexander Schwing; | code |
| 855 | Weighted QMIX: Expanding Monotonic Value Function Factorisation For Deep Multi-Agent Reinforcement Learning Highlight: We propose two weighting schemes and prove that they recover the correct maximal action for any joint action $Q$-values, and therefore for $Q^*$ as well. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tabish Rashid; Gregory Farquhar; Bei Peng; Shimon Whiteson; | |
| 856 | BanditPAM: Almost Linear Time K-Medoids Clustering Via Multi-Armed Bandits Highlight: We propose BanditPAM, a randomized algorithm inspired by techniques from multi-armed bandits, that reduces the complexity of each PAM iteration from O(n^2) to O(nlogn) and returns the same results with high probability, under assumptions on the data that often hold in practice. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mo Tiwari; Martin J. Zhang; James Mayclin; Sebastian Thrun; Chris Piech; Ilan Shomorony; | |
| 857 | UDH: Universal Deep Hiding For Steganography, Watermarking, And Light Field Messaging Highlight: Exploiting its property of being \emph{universal}, we propose universal watermarking as a timely solution to address the concern of the exponentially increasing amount of images/videos. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaoning Zhang; Philipp Benz; Adil Karjauv; Geng Sun; In Kweon; | code |
| 858 | Evidential Sparsification Of Multimodal Latent Spaces In Conditional Variational Autoencoders Highlight: We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder, while preserving its learned multimodality. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Masha Itkina; Boris Ivanovic; Ransalu Senanayake; Mykel J. Kochenderfer; Marco Pavone; | |
| 859 | An Unbiased Risk Estimator For Learning With Augmented Classes Highlight: In this paper we show that, by using unlabeled training data to approximate the potential distribution of augmented classes, an unbiased risk estimator of the testing distribution can be established for the LAC problem under mild assumptions, which paves a way to develop a sound approach with theoretical guarantees. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu-Jie Zhang; Peng Zhao; Lanjihong Ma; Zhi-Hua Zhou; | |
| 860 | AutoBSS: An Efficient Algorithm For Block Stacking Style Search Highlight: The proposed method, AutoBSS, is a novel AutoML algorithm based on Bayesian optimization by iteratively refining and clustering Block Stacking Style Code (BSSC), which can find optimal BSS in a few trials without biased evaluation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
yikang zhang; Jian Zhang; Zhao Zhong; | |
| 861 | Pushing The Limits Of Narrow Precision Inferencing At Cloud Scale With Microsoft Floating Point Highlight: In this paper, we explore the limits of Microsoft Floating Point (MSFP), a new class of datatypes developed for production cloud-scale inferencing on custom hardware. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bita Darvish Rouhani; Daniel Lo; Ritchie Zhao; Ming Liu; Jeremy Fowers; Kalin Ovtcharov ; Anna Vinogradsky; Sarah Massengill ; Lita Yang; Ray Bittner; Alessandro Forin; Haishan Zhu; Taesik Na; Prerak Patel; Shuai Che; Lok Chand Koppaka ; XIA SONG; Subhojit Som; Kaustav Das; Saurabh T; Steve Reinhardt ; Sitaram Lanka; Eric Chung; Doug Burger; | |
| 862 | Stochastic Optimization With Laggard Data Pipelines Highlight: We provide the first convergence analyses of "data-echoed" extensions of common optimization methods, showing that they exhibit provable improvements over their synchronous counterparts. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Naman Agarwal; Rohan Anil; Tomer Koren; Kunal Talwar; Cyril Zhang; | |
| 863 | Self-supervised Auxiliary Learning With Meta-paths For Heterogeneous Graphs Highlight: In this paper, to learn graph neural networks on heterogeneous graphs we propose a novel self-supervised auxiliary learning method using meta paths, which are composite relations of multiple edge types. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dasol Hwang; Jinyoung Park; Sunyoung Kwon; KyungMin Kim; Jung-Woo Ha; Hyunwoo J. Kim; | |
| 864 | GPS-Net: Graph-based Photometric Stereo Network Highlight: In this paper, we present a Graph-based Photometric Stereo Network, which unifies per-pixel and all-pixel processings to explore both inter-image and intra-image information. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhuokun Yao; Kun Li; Ying Fu; Haofeng Hu; Boxin Shi; | |
| 865 | Consistent Structural Relation Learning For Zero-Shot Segmentation Highlight: In this work, we propose a Consistent Structural Relation Learning (CSRL) approach to constrain the generating of unseen visual features by exploiting the structural relations between seen and unseen categories. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peike Li; Yunchao Wei; Yi Yang; | |
| 866 | Model Selection In Contextual Stochastic Bandit Problems Highlight: We study bandit model selection in stochastic environments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aldo Pacchiano; My Phan; Yasin Abbasi Yadkori; Anup Rao; Julian Zimmert; Tor Lattimore; Csaba Szepesvari; | |
| 867 | Truncated Linear Regression In High Dimensions Highlight: In order to deal with both truncation and high-dimensionality at the same time, we develop new techniques that not only generalize the existing ones but we believe are of independent interest. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Constantinos Daskalakis; Dhruv Rohatgi; Emmanouil Zampetakis; | |
| 868 | Incorporating Pragmatic Reasoning Communication Into Emergent Language Highlight: Given that their combination has been explored in linguistics, in this work, we combine computational models of short-term mutual reasoning-based pragmatics with long-term language emergentism. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yipeng Kang; Tonghan Wang; Gerard de Melo; | |
| 869 | Deep Subspace Clustering With Data Augmentation Highlight: We propose a technique to exploit the benefits of data augmentation in DSC algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mahdi Abavisani; Alireza Naghizadeh; Dimitris Metaxas; Vishal Patel; | |
| 870 | An Empirical Process Approach To The Union Bound: Practical Algorithms For Combinatorial And Linear Bandits Highlight: This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julian Katz-Samuels; Lalit Jain; zohar karnin; Kevin G. Jamieson; | |
| 871 | Can Graph Neural Networks Count Substructures? Highlight: Inspired by this, we propose to study the expressive power of graph neural networks (GNNs) via their ability to count attributed graph substructures, extending recent works that examine their power in graph isomorphism testing and function approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhengdao Chen; Lei Chen; Soledad Villar; Joan Bruna; | |
| 872 | A Bayesian Perspective On Training Speed And Model Selection Highlight: We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Clare Lyle; Lisa Schut; Robin Ru; Yarin Gal; Mark van der Wilk; | |
| 873 | On The Modularity Of Hypernetworks Highlight: In this paper, we define the property of modularity as the ability to effectively learn a different function for each input instance $I$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tomer Galanti; Lior Wolf; | |
| 874 | Doubly Robust Off-Policy Value And Gradient Estimation For Deterministic Policies Highlight: To circumvent this issue, we propose several new doubly robust estimators based on different kernelization approaches. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nathan Kallus; Masatoshi Uehara; | |
| 875 | Provably Efficient Neural GTD For Off-Policy Learning Highlight: This paper studies a gradient temporal difference (GTD) algorithm using neural network (NN) function approximators to minimize the mean squared Bellman error (MSBE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hoi-To Wai; Zhuoran Yang; Zhaoran Wang; Mingyi Hong; | |
| 876 | Learning Discrete Energy-based Models Via Auxiliary-variable Local Exploration Highlight: In this paper we propose \modelshort, a new algorithm for learning conditional and unconditional EBMs for discrete structured data, where parameter gradients are estimated using a learned sampler that mimics local search. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hanjun Dai; Rishabh Singh; Bo Dai; Charles Sutton; Dale Schuurmans; | |
| 877 | Stable And Expressive Recurrent Vision Models Highlight: Here, we develop a new learning algorithm, "contractor recurrent back-propagation" (C-RBP), which alleviates these issues by achieving constant O(1) memory-complexity with steps of recurrent processing. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Drew Linsley; Alekh Karkada Ashok; Lakshmi Narasimhan Govindarajan; Rex Liu; Thomas Serre; | code |
| 878 | Entropic Optimal Transport Between Unbalanced Gaussian Measures Has A Closed Form Highlight: In this paper, we propose to fill the void at the intersection between these two schools of thought in OT by proving that the entropy-regularized optimal transport problem between two Gaussian measures admits a closed form. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hicham Janati; Boris Muzellec; Gabriel Peyr�; Marco Cuturi; | |
| 879 | BRP-NAS: Prediction-based NAS Using GCNs Highlight: To address this problem, we propose BRP-NAS, an efficient hardware-aware NAS enabled by an accurate performance predictor-based on graph convolutional network (GCN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lukasz Dudziak; Thomas Chau; Mohamed Abdelfattah; Royson Lee; Hyeji Kim; Nicholas Lane; | |
| 880 | Deep Shells: Unsupervised Shape Correspondence With Optimal Transport Highlight: We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marvin Eisenberger; Aysim Toker; Laura Leal-Taix�; Daniel Cremers; | |
| 881 | ISTA-NAS: Efficient And Consistent Neural Architecture Search By Sparse Coding Highlight: In this paper, we formulate neural architecture search as a sparse coding problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yibo Yang; Hongyang Li; Shan You; Fei Wang; Chen Qian; Zhouchen Lin; | |
| 882 | Rel3D: A Minimally Contrastive Benchmark For Grounding Spatial Relations In 3D Highlight: In this paper, we fill this gap by constructing Rel3D: the first large-scale, human-annotated dataset for grounding spatial relations in 3D. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ankit Goyal; Kaiyu Yang; Dawei Yang; Jia Deng; | code |
| 883 | Regularizing Black-box Models For Improved Interpretability Highlight: Our method, ExpO, is a hybridization of these approaches that regularizes a model for explanation quality at training time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gregory Plumb; Maruan Al-Shedivat; �ngel Alexander Cabrera; Adam Perer; Eric Xing; Ameet Talwalkar; | |
| 884 | Trust The Model When It Is Confident: Masked Model-based Actor-Critic Highlight: In this work, we find that better model usage can make a huge difference. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Feiyang Pan; Jia He; Dandan Tu; Qing He; | |
| 885 | Semi-Supervised Neural Architecture Search Highlight: In this paper, we propose SemiNAS, a semi-supervised NAS approach that leverages numerous unlabeled architectures (without evaluation and thus nearly no cost). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Renqian Luo; Xu Tan; Rui Wang; Tao Qin; Enhong Chen; Tie-Yan Liu; | |
| 886 | Consistency Regularization For Certified Robustness Of Smoothed Classifiers Highlight: We found that the trade-off between accuracy and certified robustness of smoothed classifiers can be greatly controlled by simply regularizing the prediction consistency over noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jongheon Jeong; Jinwoo Shin; | |
| 887 | Robust Multi-Agent Reinforcement Learning With Model Uncertainty Highlight: In this work, we study the problem of multi-agent reinforcement learning (MARL) with model uncertainty, which is referred to as robust MARL. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaiqing Zhang; TAO SUN; Yunzhe Tao; Sahika Genc; Sunil Mallya; Tamer Basar; | |
| 888 | SIRI: Spatial Relation Induced Network For Spatial Description Resolution Highlight: Mimicking humans, who sequentially traverse spatial relationship words and objects with a first-person view to locate their target, we propose a novel spatial relationship induced (SIRI) network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
peiyao wang; Weixin Luo; Yanyu Xu; Haojie Li; Shugong Xu; Jianyu Yang; Shenghua Gao; | code |
| 889 | Adaptive Shrinkage Estimation For Streaming Graphs Highlight: In this work, we consider the fundamental problem of estimating the higher-order dependencies using adaptive sampling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nesreen Ahmed; Nick Duffield; | |
| 890 | Make One-Shot Video Object Segmentation Efficient Again Highlight: To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tim Meinhardt; Laura Leal-Taix�; | |
| 891 | Depth Uncertainty In Neural Networks Highlight: Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited. To solve this, we perform probabilistic reasoning over the depth of neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Javier Antoran; James Allingham; Jos� Miguel Hern�ndez-Lobato; | |
| 892 | Non-Euclidean Universal Approximation Highlight: We present general conditions describing feature and readout maps that preserve an architecture’s ability to approximate any continuous functions uniformly on compacts. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anastasis Kratsios; Ievgen Bilokopytov; | |
| 893 | Constraining Variational Inference With Geometric Jensen-Shannon Divergence Highlight: We present a regularisation mechanism based on the {\em skew-geometric Jensen-Shannon divergence} $\left(\textrm{JS}^{\textrm{G}_{\alpha}}\right)$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jacob Deasy; Nikola Simidjievski; Pietro Li�; | |
| 894 | Gibbs Sampling With People Highlight: We formulate both methods from a utility-theory perspective, and show that the new method can be interpreted as ‘Gibbs Sampling with People’ (GSP). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peter Harrison; Raja Marjieh; Federico Adolfi; Pol van Rijn; Manuel Anglada-Tort; Ofer Tchernichovski; Pauline Larrouy-Maestri; Nori Jacoby; | |
| 895 | HM-ANN: Efficient Billion-Point Nearest Neighbor Search On Heterogeneous Memory Highlight: In this work, we present a novel graph-based similarity search algorithm called HM-ANN, which takes both memory and data heterogeneity into consideration and enables billion-scale similarity search on a single node without using compression. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jie Ren; Minjia Zhang; Dong Li; | |
| 896 | FrugalML: How To Use ML Prediction APIs More Accurately And Cheaply Highlight: We take a first step towards addressing this challenge by proposing FrugalML, a principled framework that jointly learns the strength and weakness of each API on different data, and performs an efficient optimization to automatically identify the best sequential strategy to adaptively use the available APIs within a budget constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lingjiao Chen; Matei Zaharia; James Y. Zou; | |
| 897 | Sharp Representation Theorems For ReLU Networks With Precise Dependence On Depth Highlight: We prove dimension free representation results for neural networks with D ReLU layers under square loss for a class of functions G_D defined in the paper. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guy Bresler; Dheeraj Nagaraj; | |
| 898 | Shared Experience Actor-Critic For Multi-Agent Reinforcement Learning Highlight: We propose a general method for efficient exploration by sharing experience amongst agents. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Filippos Christianos; Lukas Sch�fer; Stefano Albrecht; | |
| 899 | Monotone Operator Equilibrium Networks Highlight: In this paper, we develop a new class of implicit-depth model based on the theory of monotone operators, the Monotone Operator Equilibrium Network (monDEQ). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ezra Winston; J. Zico Kolter; | code |
| 900 | When And How To Lift The Lockdown? Global COVID-19 Scenario Analysis And Policy Assessment Using Compartmental Gaussian Processes Highlight: To this end, this paper develops a Bayesian model for predicting the effects of COVID-19 containment policies in a global context — we treat each country as a distinct data point, and exploit variations of policies across countries to learn country-specific policy effects. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhaozhi Qian; Ahmed M. Alaa; Mihaela van der Schaar; | |
| 901 | Unsupervised Learning Of Lagrangian Dynamics From Images For Prediction And Control Highlight: We introduce a new unsupervised neural network model that learns Lagrangian dynamics from images, with interpretability that benefits prediction and control. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaofeng Desmond Zhong; Naomi Leonard; | |
| 902 | High-Dimensional Sparse Linear Bandits Highlight: We derive a novel O(n^{2/3}) dimension-free minimax regret lower bound for sparse linear bandits in the data-poor regime where the horizon is larger than the ambient dimension and where the feature vectors admit a well-conditioned exploration distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Botao Hao; Tor Lattimore; Mengdi Wang; | |
| 903 | Non-Stochastic Control With Bandit Feedback Highlight: To overcome this issue, we propose an efficient algorithm for the general setting of bandit convex optimization for loss functions with memory, which may be of independent interest. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Paula Gradu; John Hallman; Elad Hazan; | |
| 904 | Generalized Leverage Score Sampling For Neural Networks Highlight: In this work, we generalize the results in [Avron, Kapralov, Musco, Musco, Velingker and Zandieh 17] to a broader class of kernels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jason D. Lee; Ruoqi Shen; Zhao Song; Mengdi Wang; zheng Yu; | |
| 905 | An Optimal Elimination Algorithm For Learning A Best Arm Highlight: In this paper we propose a new approach for $(\epsilon,\delta)$-\texttt{PAC} learning a best arm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Avinatan Hassidim; Ron Kupfer; Yaron Singer; | |
| 906 | Efficient Projection-free Algorithms For Saddle Point Problems Highlight: In this paper, we study projection-free algorithms for convex-strongly-concave saddle point problems with complicated constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cheng Chen; Luo Luo; Weinan Zhang; Yong Yu; | |
| 907 | A Mathematical Model For Automatic Differentiation In Machine Learning Highlight: In this work we articulate the relationships between differentiation of programs as implemented in practice, and differentiation of nonsmooth functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
J�r�me Bolte; Edouard Pauwels; | |
| 908 | Unsupervised Text Generation By Learning From Search Highlight: In this work, we propose TGLS, a novel framework for unsupervised Text Generation by Learning from Search. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jingjing Li; Zichao Li; Lili Mou; Xin Jiang; Michael Lyu; Irwin King; | |
| 909 | Learning Compositional Rules Via Neural Program Synthesis Highlight: In this work, we present a neuro-symbolic model which learns entire rule systems from a small set of examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maxwell Nye; Armando Solar-Lezama; Josh Tenenbaum; Brenden M. Lake; | |
| 910 | Incorporating BERT Into Parallel Sequence Decoding With Adapters Highlight: In this paper, we propose to address this problem by taking two different BERT models as the encoder and decoder respectively, and fine-tuning them by introducing simple and lightweight adapter modules, which are inserted between BERT layers and tuned on the task-specific dataset. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junliang Guo; Zhirui Zhang; Linli Xu; Hao-Ran Wei; Boxing Chen; Enhong Chen; | |
| 911 | Estimating Fluctuations In Neural Representations Of Uncertain Environments Highlight: In this paper, we develop a new state-space modeling framework to address two important issues related to remapping. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sahand Farhoodi; Mark Plitt; Lisa Giocomo; Uri Eden; | |
| 912 | Discover, Hallucinate, And Adapt: Open Compound Domain Adaptation For Semantic Segmentation Highlight: In this paper, we investigate open compound domain adaptation (OCDA), which deals with mixed and novel situations at the same time, for semantic segmentation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
KwanYong Park; Sanghyun Woo; Inkyu Shin; In So Kweon; | |
| 913 | SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm Highlight: We present $\SURF$, an algorithm for approximating distributions by piecewise polynomials. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yi Hao; Ayush Jain; Alon Orlitsky; Vaishakh Ravindrakumar; | |
| 914 | Understanding Approximate Fisher Information For Fast Convergence Of Natural Gradient Descent In Wide Neural Networks Highlight: In this work, we reveal that, under specific conditions, NGD with approximate Fisher information achieves the same fast convergence to global minima as exact NGD. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ryo Karakida; Kazuki Osawa; | |
| 915 | General Transportability Of Soft Interventions: Completeness Results Highlight: In this paper, we extend transportability theory to encompass these more complex types of interventions, which are known as "soft," both relative to the input as well as the target distribution of the analysis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Juan Correa; Elias Bareinboim; | |
| 916 | GAIT-prop: A Biologically Plausible Learning Rule Derived From Backpropagation Of Error Highlight: Here, we derive an exact correspondence between backpropagation and a modified form of target propagation (GAIT-prop) where the target is a small perturbation of the forward pass. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nasir Ahmad; Marcel A. J. van Gerven; Luca Ambrogioni; | |
| 917 | Lipschitz Bounds And Provably Robust Training By Laplacian Smoothing Highlight: In this work we propose a graph-based learning framework to train models with provable robustness to adversarial perturbations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vishaal Krishnan; Abed AlRahman Al Makdah; Fabio Pasqualetti; | |
| 918 | SCOP: Scientific Control For Reliable Neural Network Pruning Highlight: This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yehui Tang; Yunhe Wang; Yixing Xu; Dacheng Tao; Chunjing XU; Chao Xu; Chang Xu; | |
| 919 | Provably Consistent Partial-Label Learning Highlight: In this paper, we propose the first generation model of candidate label sets, and develop two PLL methods that are guaranteed to be provably consistent, i.e., one is risk-consistent and the other is classifier-consistent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lei Feng; Jiaqi Lv; Bo Han; Miao Xu; Gang Niu; Xin Geng; Bo An; Masashi Sugiyama; | |
| 920 | Robust, Accurate Stochastic Optimization For Variational Inference Highlight: Motivated by recent theory, we propose a simple and parallel way to improve SGD estimates for variational inference. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Akash Kumar Dhaka; Alejandro Catalina; Michael R. Andersen; M�ns Magnusson; Jonathan Huggins; Aki Vehtari; | |
| 921 | Discovering Conflicting Groups In Signed Networks Highlight: In this paper we study the problem of detecting $k$ conflicting groups in a signed network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruo-Chun Tzeng; Bruno Ordozgoiti; Aristides Gionis; | |
| 922 | Learning Some Popular Gaussian Graphical Models Without Condition Number Bounds Highlight: Here we give the first fixed polynomial-time algorithms for learning attractive GGMs and walk-summable GGMs with a logarithmic number of samples without any such assumptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Kelner; Frederic Koehler; Raghu Meka; Ankur Moitra; | |
| 923 | Sense And Sensitivity Analysis: Simple Post-Hoc Analysis Of Bias Due To Unobserved Confounding Highlight: The purpose of this paper is to develop Austen plots, a sensitivity analysis tool to aid such judgments by making it easier to reason about potential bias induced by unobserved confounding. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Victor Veitch; Anisha Zaveri; | |
| 924 | Mix And Match: An Optimistic Tree-Search Approach For Learning Models From Mixture Distributions Highlight: We consider a covariate shift problem where one has access to several different training datasets for the same learning problem and a small validation set which possibly differs from all the individual training distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matthew Faw; Rajat Sen; Karthikeyan Shanmugam; Constantine Caramanis; Sanjay Shakkottai; | |
| 925 | Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition Highlight: To enable fine-grained analysis, we describe an interpretable, symmetric decomposition of the variance into terms associated with the randomness from sampling, initialization, and the labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ben Adlam; Jeffrey Pennington; | |
| 926 | VIME: Extending The Success Of Self- And Semi-supervised Learning To Tabular Domain Highlight: In this paper, we fill this gap by proposing novel self- and semi-supervised learning frameworks for tabular data, which we refer to collectively as VIME (Value Imputation and Mask Estimation). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jinsung Yoon; Yao Zhang; James Jordon; Mihaela van der Schaar; | |
| 927 | The Smoothed Possibility Of Social Choice Highlight: We develop a framework that leverages the smoothed complexity analysis by Spielman and Teng to circumvent paradoxes and impossibility theorems in social choice, motivated by modern applications of social choice powered by AI and ML. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lirong Xia; | |
| 928 | A Decentralized Parallel Algorithm For Training Generative Adversarial Nets Highlight: In this paper, we address this difficulty by designing the \textbf{first gradient-based decentralized parallel algorithm} which allows workers to have multiple rounds of communications in one iteration and to update the discriminator and generator simultaneously, and this design makes it amenable for the convergence analysis of the proposed decentralized algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mingrui Liu; Wei Zhang; Youssef Mroueh; Xiaodong Cui; Jarret Ross; Tianbao Yang; Payel Das; | |
| 929 | Phase Retrieval In High Dimensions: Statistical And Computational Phase Transitions Highlight: We consider the phase retrieval problem of reconstructing a $n$-dimensional real or complex signal $\mathbf{X}^\star$ from $m$ (possibly noisy) observations $Y_\mu = | \sum_{i=1}^n \Phi_{\mu i} X^{\star}_i/\sqrt{n}|$, for a large class of correlated real and complex random sensing matrices $\mathbf{\Phi}$, in a high-dimensional setting where $m,n\to\infty$ while $\alpha = m/n=\Theta(1)$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Antoine Maillard; Bruno Loureiro; Florent Krzakala; Lenka Zdeborov�; | |
| 930 | Fair Performance Metric Elicitation Highlight: Specifically, we propose a novel strategy to elicit group-fair performance metrics for multiclass classification problems with multiple sensitive groups that also includes selecting the trade-off between predictive performance and fairness violation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gaurush Hiranandani; Harikrishna Narasimhan; Oluwasanmi O. Koyejo; | |
| 931 | Hybrid Variance-Reduced SGD Algorithms For Minimax Problems With Nonconvex-Linear Function Highlight: We develop a novel and single-loop variance-reduced algorithm to solve a class of stochastic nonconvex-convex minimax problems involving a nonconvex-linear objective function, which has various applications in different fields such as ma- chine learning and robust optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Quoc Tran Dinh; Deyi Liu; Lam Nguyen; | |
| 932 | Belief-Dependent Macro-Action Discovery In POMDPs Using The Value Of Information Highlight: Here, we present a method for extracting belief-dependent, variable-length macro-actions directly from a low-level POMDP model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Genevieve Flaspohler; Nicholas A. Roy; John W. Fisher III; | |
| 933 | Soft Contrastive Learning For Visual Localization Highlight: In this paper, we show why such divisions are problematic for learning localization features. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Janine Thoma; Danda Pani Paudel; Luc V. Gool; | |
| 934 | Fine-Grained Dynamic Head For Object Detection Highlight: To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lin Song; Yanwei Li; Zhengkai Jiang; Zeming Li; Hongbin Sun; Jian Sun; Nanning Zheng; | code |
| 935 | LoCo: Local Contrastive Representation Learning Highlight: In this work, we discover that by overlapping local blocks stacking on top of each other, we effectively increase the decoder depth and allow upper blocks to implicitly send feedbacks to lower blocks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuwen Xiong; Mengye Ren; Raquel Urtasun; | |
| 936 | Modeling And Optimization Trade-off In Meta-learning Highlight: We introduce and rigorously define the trade-off between accurate modeling and optimization ease in meta-learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Katelyn Gao; Ozan Sener; | |
| 937 | SnapBoost: A Heterogeneous Boosting Machine Highlight: In this work, we study a Heterogeneous Newton Boosting Machine (HNBM) in which the base hypothesis class may vary across boosting iterations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thomas Parnell; Andreea Anghel; Malgorzata Lazuka; Nikolas Ioannou; Sebastian Kurella; Peshal Agarwal; Nikolaos Papandreou; Haralampos Pozidis; | |
| 938 | On Adaptive Distance Estimation Highlight: We provide a static data structure for distance estimation which supports {\it adaptive} queries. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yeshwanth Cherapanamjeri; Jelani Nelson; | |
| 939 | Stage-wise Conservative Linear Bandits Highlight: For this problem, we present two novel algorithms, stage-wise conservative linear Thompson Sampling (SCLTS) and stage-wise conservative linear UCB (SCLUCB), that respect the baseline constraints and enjoy probabilistic regret bounds of order $\mathcal{O}(\sqrt{T} \log^{3/2}T)$ and $\mathcal{O}(\sqrt{T} \log T)$, respectively. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ahmadreza Moradipari; Christos Thrampoulidis; Mahnoosh Alizadeh; | |
| 940 | RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces Highlight: We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sebastien Ehrhardt; Oliver Groth; Aron Monszpart; Martin Engelcke; Ingmar Posner; Niloy Mitra; Andrea Vedaldi; | code |
| 941 | Metric-Free Individual Fairness In Online Learning Highlight: We study an online learning problem subject to the constraint of individual fairness, which requires that similar individuals are treated similarly. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yahav Bechavod; Christopher Jung; Steven Z. Wu; | |
| 942 | GreedyFool: Distortion-Aware Sparse Adversarial Attack Highlight: In this paper, we propose a novel two-stage distortion-aware greedy-based method dubbed as ”GreedyFool". Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaoyi Dong; Dongdong Chen; Jianmin Bao; Chuan Qin; Lu Yuan; Weiming Zhang; Nenghai Yu; Dong Chen; | |
| 943 | VAEM: A Deep Generative Model For Heterogeneous Mixed Type Data Highlight: We propose an extension of variational autoencoders (VAEs) called VAEM to handle such heterogeneous data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chao Ma; Sebastian Tschiatschek; Richard Turner; Jos� Miguel Hern�ndez-Lobato; Cheng Zhang; | |
| 944 | RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist Highlight: In this paper, we devise a novel template-free algorithm for automatic retrosynthetic expansion inspired by how chemists approach retrosynthesis prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaochao Yan; Qianggang Ding; Peilin Zhao; Shuangjia Zheng; JINYU YANG; Yang Yu; Junzhou Huang; | |
| 945 | Sample-Efficient Optimization In The Latent Space Of Deep Generative Models Via Weighted Retraining Highlight: We introduce an improved method for efficient black-box optimization, which performs the optimization in the low-dimensional, continuous latent manifold learned by a deep generative model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Austin Tripp; Erik Daxberger; Jos� Miguel Hern�ndez-Lobato; | |
| 946 | Improved Sample Complexity For Incremental Autonomous Exploration In MDPs Highlight: In this paper, we introduce a novel model-based approach that interleaves discovering new states from $s_0$ and improving the accuracy of a model estimate that is used to compute goal-conditioned policies. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jean Tarbouriech; Matteo Pirotta; Michal Valko; Alessandro Lazaric; | |
| 947 | TinyTL: Reduce Memory, Not Parameters For Efficient On-Device Learning Highlight: In this work, we present Tiny-Transfer-Learning (TinyTL) for memory-efficient on-device learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Han Cai; Chuang Gan; Ligeng Zhu; Song Han; | code |
| 948 | RD$^2$: Reward Decomposition With Representation Decomposition Highlight: In this work, we propose a set of novel reward decomposition principles by constraining uniqueness and compactness of different state features/representations relevant to different sub-rewards. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zichuan Lin; Derek Yang; Li Zhao; Tao Qin; Guangwen Yang; Tie-Yan Liu; | |
| 949 | Self-paced Contrastive Learning With Hybrid Memory For Domain Adaptive Object Re-ID Highlight: To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yixiao Ge; Feng Zhu; Dapeng Chen; Rui Zhao; hongsheng Li; | |
| 950 | Fairness Constraints Can Help Exact Inference In Structured Prediction Highlight: We find that, in contrast to the known trade-offs between fairness and model performance, the addition of the fairness constraint improves the probability of exact recovery. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kevin Bello; Jean Honorio; | |
| 951 | Instance-based Generalization In Reinforcement Learning Highlight: We propose training a shared belief representation over an ensemble of specialized policies, from which we compute a consensus policy that is used for data collection, disallowing instance-speci?c exploitation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Martin Bertran; Natalia Martinez; Mariano Phielipp; Guillermo Sapiro; | |
| 952 | Smooth And Consistent Probabilistic Regression Trees Highlight: We propose here a generalization of regression trees, referred to as Probabilistic Regression (PR) trees, that adapt to the smoothness of the prediction function relating input and output variables while preserving the interpretability of the prediction and being robust to noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sami Alkhoury; Emilie Devijver; Marianne Clausel; Myriam Tami; Eric Gaussier; georges Oppenheim; | |
| 953 | Computing Valid P-value For Optimal Changepoint By Selective Inference Using Dynamic Programming Highlight: In this paper, we introduce a novel method to perform statistical inference on the significance of the CPs, estimated by a Dynamic Programming (DP)-based optimal CP detection algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vo Nguyen Le Duy; Hiroki Toda; Ryota Sugiyama; Ichiro Takeuchi; | |
| 954 | Factorized Neural Processes For Neural Processes: K-Shot Prediction Of Neural Responses Highlight: We overcome this limitation by formulating the problem as $K$-shot prediction to directly infer a neuron’s tuning function from a small set of stimulus-response pairs using a Neural Process. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ronald (James) Cotton; Fabian Sinz; Andreas Tolias; | |
| 955 | Winning The Lottery With Continuous Sparsification Highlight: We revisit fundamental aspects of pruning algorithms, pointing out missing ingredients in previous approaches, and develop a method, Continuous Sparsification, which searches for sparse networks based on a novel approximation of an intractable l0 regularization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pedro Savarese; Hugo Silva; Michael Maire; | |
| 956 | Adversarial Robustness Via Robust Low Rank Representations Highlight: In this work we highlight the benefits of natural low rank representations that often exist for real data such as images, for training neural networks with certified robustness guarantees. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pranjal Awasthi; Himanshu Jain; Ankit Singh Rawat; Aravindan Vijayaraghavan; | |
| 957 | Joints In Random Forests Highlight: In this paper, we demonstrate that DTs and RFs can naturally be interpreted as generative models, by drawing a connection to Probabilistic Circuits, a prominent class of tractable probabilistic models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alvaro Correia; Robert Peharz; Cassio P. de Campos; | |
| 958 | Compositional Generalization By Learning Analytical Expressions Highlight: Inspired by work in cognition which argues compositionality can be captured by variable slots with symbolic functions, we present a refreshing view that connects a memory-augmented neural model with analytical expressions, to achieve compositional generalization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qian Liu; Shengnan An; Jian-Guang Lou; Bei Chen; Zeqi Lin; Yan Gao; Bin Zhou; Nanning Zheng; Dongmei Zhang; | |
| 959 | JAX MD: A Framework For Differentiable Physics Highlight: We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Samuel Schoenholz; Ekin Dogus Cubuk; | |
| 960 | An Implicit Function Learning Approach For Parametric Modal Regression Highlight: In this work, we propose a parametric modal regression algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yangchen Pan; Ehsan Imani; Amir-massoud Farahmand; Martha White; | |
| 961 | SDF-SRN: Learning Signed Distance 3D Object Reconstruction From Static Images Highlight: In this paper, we address this issue and propose SDF-SRN, an approach that requires only a single view of objects at training time, offering greater utility for real-world scenarios. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chen-Hsuan Lin; Chaoyang Wang; Simon Lucey; | |
| 962 | Coresets For Robust Training Of Deep Neural Networks Against Noisy Labels Highlight: To tackle this challenge, we propose a novel approach with strong theoretical guarantees for robust training of neural networks trained with noisy labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Baharan Mirzasoleiman; Kaidi Cao; Jure Leskovec; | |
| 963 | Adapting To Misspecification In Contextual Bandits Highlight: We introduce a new family of oracle-efficient algorithms for $\varepsilon$-misspecified contextual bandits that adapt to unknown model misspecification—both for finite and infinite action settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dylan J. Foster; Claudio Gentile; Mehryar Mohri; Julian Zimmert; | |
| 964 | Convergence Of Meta-Learning With Task-Specific Adaptation Over Partial Parameters Highlight: In this paper, we characterize the convergence rate and the computational complexity for ANIL under two representative inner-loop loss geometries, i.e., strongly-convexity and nonconvexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaiyi Ji; Jason D. Lee; Yingbin Liang; H. Vincent Poor; | |
| 965 | MetaPerturb: Transferable Regularizer For Heterogeneous Tasks And Architectures Highlight: To bridge the gap between the two, we propose a transferable perturbation, MetaPerturb, which is meta-learned to improve generalization performance on unseen data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeong Un Ryu; JaeWoong Shin; Hae Beom Lee; Sung Ju Hwang; | |
| 966 | Learning To Solve TV Regularised Problems With Unrolled Algorithms Highlight: In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hamza Cherkaoui; Jeremias Sulam; Thomas Moreau; | |
| 967 | Object-Centric Learning With Slot Attention Highlight: In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Francesco Locatello; Dirk Weissenborn; Thomas Unterthiner; Aravindh Mahendran; Georg Heigold; Jakob Uszkoreit; Alexey Dosovitskiy; Thomas Kipf; | |
| 968 | Improving Robustness Against Common Corruptions By Covariate Shift Adaptation Highlight: The key insight is that in many scenarios, multiple unlabeled examples of the corruptions are available and can be used for unsupervised online adaptation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Steffen Schneider; Evgenia Rusak; Luisa Eck; Oliver Bringmann; Wieland Brendel; Matthias Bethge; | |
| 969 | Deep Smoothing Of The Implied Volatility Surface Highlight: We present a neural network (NN) approach to fit and predict implied volatility surfaces (IVSs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Damien Ackerer; Natasa Tagasovska; Thibault Vatter; | |
| 970 | Probabilistic Inference With Algebraic Constraints: Theoretical Limits And Practical Approximations Highlight: In this work, we advance the WMI framework on both the theoretical and algorithmic side. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhe Zeng; Paolo Morettin; Fanqi Yan; Antonio Vergari; Guy Van den Broeck; | |
| 971 | Provable Online CP/PARAFAC Decomposition Of A Structured Tensor Via Dictionary Learning Highlight: We consider the problem of factorizing a structured 3-way tensor into its constituent Canonical Polyadic (CP) factors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sirisha Rambhatla; Xingguo Li; Jarvis Haupt; | |
| 972 | Look-ahead Meta Learning For Continual Learning Highlight: In this work, we propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gunshi Gupta; Karmesh Yadav; Liam Paull; | |
| 973 | A Polynomial-time Algorithm For Learning Nonparametric Causal Graphs Highlight: We establish finite-sample guarantees for a polynomial-time algorithm for learning a nonlinear, nonparametric directed acyclic graphical (DAG) model from data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ming Gao; Yi Ding; Bryon Aragam; | |
| 974 | Sparse Learning With CART Highlight: This paper aims to study the statistical properties of regression trees constructed with CART. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jason Klusowski; | |
| 975 | Proximal Mapping For Deep Regularization Highlight: In contrast to prevalent methods that optimize them indirectly through model weights, we propose inserting proximal mapping as a new layer to the deep network, which directly and explicitly produces well regularized hidden layer outputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
mao li; Yingyi Ma; Xinhua Zhang; | |
| 976 | Identifying Causal-Effect Inference Failure With Uncertainty-Aware Models Highlight: We introduce a practical approach for integrating uncertainty estimation into a class of state-of-the-art neural network methods used for individual-level causal estimates. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrew Jesson; S�ren Mindermann; Uri Shalit; Yarin Gal; | |
| 977 | Hierarchical Granularity Transfer Learning Highlight: In this paper, we introduce a new task, named Hierarchical Granularity Transfer Learning (HGTL), to recognize sub-level categories with basic-level annotations and semantic descriptions for hierarchical categories. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shaobo Min; Hongtao Xie; Hantao Yao; Xuran Deng; Zheng-Jun Zha; Yongdong Zhang; | |
| 978 | Deep Active Inference Agents Using Monte-Carlo Methods Highlight: In this paper, we present a neural architecture for building deep active inference agents operating in complex, continuous state-spaces using multiple forms of Monte-Carlo (MC) sampling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zafeirios Fountas; Noor Sajid; Pedro Mediano; Karl Friston; | |
| 979 | Consistent Estimation Of Identifiable Nonparametric Mixture Models From Grouped Observations Highlight: This work proposes an algorithm that consistently estimates any identifiable mixture model from grouped observations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Ritchie; Robert A. Vandermeulen; Clayton Scott; | |
| 980 | Manifold Structure In Graph Embeddings Highlight: However, this paper shows that existing random graph models, including graphon and other latent position models, predict the data should live near a much lower-dimensional set. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Patrick Rubin-Delanchy; | |
| 981 | Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization Of The Classifier With Application To Real-Time Information Filtering On The Web Highlight: We propose new algorithms that generalize the learned Bloom filter by using the complete spectrum of the score regions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhenwei Dai; Anshumali Shrivastava; | |
| 982 | MCUNet: Tiny Deep Learning On IoT Devices Highlight: We propose MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ji Lin; Wei-Ming Chen; Yujun Lin; john cohn; Chuang Gan; Song Han; | |
| 983 | In Search Of Robust Measures Of Generalization Highlight: Focusing on generalization bounds, this work addresses the question of how to evaluate such bounds empirically. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gintare Karolina Dziugaite; Alexandre Drouin; Brady Neal; Nitarshan Rajkumar; Ethan Caballero; Linbo Wang; Ioannis Mitliagkas; Daniel M. Roy; | |
| 984 | Task-agnostic Exploration In Reinforcement Learning Highlight: We present an efficient task-agnostic RL algorithm, \textsc{UCBZero}, that finds $\epsilon$-optimal policies for $N$ arbitrary tasks after at most $\tilde O(\log(N)H^5SA/\epsilon^2)$ exploration episodes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xuezhou Zhang; Yuzhe Ma; Adish Singla; | |
| 985 | Multi-task Additive Models For Robust Estimation And Automatic Structure Discovery Highlight: To tackle this problem, we propose a new class of additive models, called Multi-task Additive Models (MAM), by integrating the mode-induced metric, the structure-based regularizer, and additive hypothesis spaces into a bilevel optimization framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingjie Wang; Hong Chen; Feng Zheng; Chen Xu; Tieliang Gong; Yanhong Chen; | |
| 986 | Provably Efficient Reward-Agnostic Navigation With Linear Value Iteration Highlight: We present a computationally tractable algorithm for the reward-free setting and show how it can be used to learn a near optimal policy for any (linear) reward function, which is revealed only once learning has completed. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrea Zanette; Alessandro Lazaric; Mykel J. Kochenderfer; Emma Brunskill; | |
| 987 | Softmax Deep Double Deterministic Policy Gradients Highlight: In this paper, we propose to use the Boltzmann softmax operator for value function estimation in continuous control. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ling Pan; Qingpeng Cai; Longbo Huang; | |
| 988 | Online Decision Based Visual Tracking Via Reinforcement Learning Highlight: Unlike previous fusion-based methods, we propose a novel ensemble framework, named DTNet, with an online decision mechanism for visual tracking based on hierarchical reinforcement learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
ke Song; Wei Zhang; Ran Song; Yibin Li; | code |
| 989 | Efficient Marginalization Of Discrete And Structured Latent Variables Via Sparsity Highlight: In this paper, we propose a new training strategy which replaces these estimators by an exact yet efficient marginalization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gon�alo Correia; Vlad Niculae; Wilker Aziz; Andr� Martins; | |
| 990 | DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation By Transferring From GANs Highlight: Therefore, in this work, we propose a novel deep hierarchical Image-to-Image Translation method, called DeepI2I. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
yaxing wang; Lu Yu; Joost van de Weijer; | |
| 991 | Distributional Robustness With IPMs And Links To Regularization And GANs Highlight: We extend this line of work for the purposes of understanding robustness via regularization by studying uncertainty sets constructed with Integral Probability Metrics (IPMs) – a large family of divergences including the MMD, Total Variation and Wasserstein distances. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hisham Husain; | |
| 992 | A Shooting Formulation Of Deep Learning Highlight: To this end, we introduce a shooting formulation which shifts the perspective from parameterizing a network layer-by-layer to parameterizing over optimal networks described only by a set of initial conditions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fran�ois-Xavier Vialard; Roland Kwitt; Susan Wei; Marc Niethammer; | |
| 993 | CSI: Novelty Detection Via Contrastive Learning On Distributionally Shifted Instances Highlight: In this paper, we propose a simple, yet effective method named contrasting shifted instances (CSI), inspired by the recent success on contrastive learning of visual representations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jihoon Tack; Sangwoo Mo; Jongheon Jeong; Jinwoo Shin; | code |
| 994 | Learning Implicit Credit Assignment For Cooperative Multi-Agent Reinforcement Learning Highlight: We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Meng Zhou; Ziyu Liu; Pengwei Sui; Yixuan Li; Yuk Ying Chung; | |
| 995 | MATE: Plugging In Model Awareness To Task Embedding For Meta Learning Highlight: To allow for better generalization, we propose a novel task representation called model-aware task embedding (MATE) that incorporates not only the data distributions of different tasks, but also the complexity of the tasks through the models used. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaohan Chen; Zhangyang Wang; Siyu Tang; Krikamol Muandet; | code |
| 996 | Restless-UCB, An Efficient And Low-complexity Algorithm For Online Restless Bandits Highlight: In Restless-UCB, we present a novel method to construct offline instances, which only requires $O(N)$ time-complexity ($N$ is the number of arms) and is exponentially better than the complexity of existing learning policy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siwei Wang; Longbo Huang; John C. S. Lui; | |
| 997 | Predictive Information Accelerates Learning In RL Highlight: We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will happen next is necessary for success on many tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kuang-Huei Lee; Ian Fischer; Anthony Liu; Yijie Guo; Honglak Lee; John Canny; Sergio Guadarrama; | |
| 998 | Robust And Heavy-Tailed Mean Estimation Made Simple, Via Regret Minimization Highlight: In this paper, we provide a meta-problem and a duality theorem that lead to a new unified view on robust and heavy-tailed mean estimation in high dimensions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sam Hopkins; Jerry Li; Fred Zhang; | |
| 999 | High-Fidelity Generative Image Compression Highlight: We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fabian Mentzer; George D. Toderici; Michael Tschannen; Eirikur Agustsson; | |
| 1000 | A Statistical Mechanics Framework For Task-Agnostic Sample Design In Machine Learning Highlight: In this paper, we present a statistical mechanics framework to understand the effect of sampling properties of training data on the generalization gap of machine learning (ML) algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bhavya Kailkhura; Jayaraman J. Thiagarajan; Qunwei Li; Jize Zhang; Yi Zhou; Timo Bremer; | |
| 1001 | Counterexample-Guided Learning Of Monotonic Neural Networks Highlight: We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aishwarya Sivaraman; Golnoosh Farnadi; Todd Millstein; Guy Van den Broeck; | |
| 1002 | A Novel Approach For Constrained Optimization In Graphical Models Highlight: We propose a class of approximate algorithms for solving this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sara Rouhani; Tahrima Rahman; Vibhav Gogate; | |
| 1003 | Global Convergence Of Deep Networks With One Wide Layer Followed By Pyramidal Topology Highlight: In this paper, we prove that, for deep networks, a single layer of width N following the input layer suffices to ensure a similar guarantee. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Quynh N. Nguyen; Marco Mondelli; | |
| 1004 | On The Trade-off Between Adversarial And Backdoor Robustness Highlight: In this paper, we conduct experiments to study whether adversarial robustness and backdoor robustness can affect each other and find a trade-off—by increasing the robustness of a network to adversarial examples, the network becomes more vulnerable to backdoor attacks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cheng-Hsin Weng; Yan-Ting Lee; Shan-Hung (Brandon) Wu; | |
| 1005 | Implicit Graph Neural Networks Highlight: To overcome this difficulty, we propose a graph learning framework, called Implicit Graph Neural Networks (IGNN), where predictions are based on the solution of a fixed-point equilibrium equation involving implicitly defined "state" vectors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fangda Gu; Heng Chang; Wenwu Zhu; Somayeh Sojoudi; Laurent El Ghaoui; | |
| 1006 | Rethinking Importance Weighting For Deep Learning Under Distribution Shift Highlight: In this paper, we rethink IW and theoretically show it suffers from a circular dependency: we need not only WE for WC, but also WC for WE where a trained deep classifier is used as the feature extractor (FE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tongtong Fang; Nan Lu; Gang Niu; Masashi Sugiyama; | |
| 1007 | Guiding Deep Molecular Optimization With Genetic Exploration Highlight: In this paper, we propose genetic expert-guided learning (GEGL), a simple yet novel framework for training a deep neural network (DNN) to generate highly-rewarding molecules. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sung-Soo Ahn; Junsu Kim; Hankook Lee; Jinwoo Shin; | code |
| 1008 | Temporal Spike Sequence Learning Via Backpropagation For Deep Spiking Neural Networks Highlight: We present a novel Temporal Spike Sequence Learning Backpropagation (TSSL-BP) method for training deep SNNs, which breaks down error backpropagation across two types of inter-neuron and intra-neuron dependencies and leads to improved temporal learning precision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenrui Zhang; Peng Li; | |
| 1009 | TSPNet: Hierarchical Feature Learning Via Temporal Semantic Pyramid For Sign Language Translation Highlight: In this paper, we explore the temporal semantic structures of sign videos to learn more discriminative features. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
DONGXU LI; Chenchen Xu; Xin Yu; Kaihao Zhang; Benjamin Swift; Hanna Suominen; Hongdong Li; | code |
| 1010 | Neural Topographic Factor Analysis For FMRI Data Highlight: We propose Neural Topographic Factor Analysis (NTFA), a probabilistic factor analysis model that infers embeddings for participants and stimuli. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eli Sennesh; Zulqarnain Khan; Yiyu Wang; J Benjamin Hutchinson; Ajay Satpute; Jennifer Dy; Jan-Willem van de Meent; | |
| 1011 | Neural Architecture Generator Optimization Highlight: In this work we 1) are the first to investigate casting NAS as a problem of finding the optimal network generator and 2) we propose a new, hierarchical and graph-based search space capable of representing an extremely large variety of network types, yet only requiring few continuous hyper-parameters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Robin Ru; Pedro Esperan�a; Fabio Maria Carlucci; | |
| 1012 | A Bandit Learning Algorithm And Applications To Auction Design Highlight: In this paper, we introduce a new notion of $(\lambda,\mu)$-concave functions and present a bandit learning algorithm that achieves a performance guarantee which is characterized as a function of the concavity parameters $\lambda$ and $\mu$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kim Thang Nguyen; | |
| 1013 | MetaPoison: Practical General-purpose Clean-label Data Poisoning Highlight: We propose MetaPoison, a first-order method that approximates the bilevel problem via meta-learning and crafts poisons that fool neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
W. Ronny Huang; Jonas Geiping; Liam Fowl; Gavin Taylor; Tom Goldstein; | |
| 1014 | Sample Efficient Reinforcement Learning Via Low-Rank Matrix Estimation Highlight: As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Devavrat Shah; Dogyoon Song; Zhi Xu; Yuzhe Yang; | |
| 1015 | Training Generative Adversarial Networks With Limited Data Highlight: We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tero Karras; Miika Aittala; Janne Hellsten; Samuli Laine; Jaakko Lehtinen; Timo Aila; | |
| 1016 | Deeply Learned Spectral Total Variation Decomposition Highlight: In this paper, we present a neural network approximation of a non-linear spectral decomposition. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tamara Grossmann; Yury Korolev; Guy Gilboa; Carola Schoenlieb; | |
| 1017 | FracTrain: Fractionally Squeezing Bit Savings Both Temporally And Spatially For Efficient DNN Training Highlight: In this paper, we explore from an orthogonal direction: how to fractionally squeeze out more training cost savings from the most redundant bit level, progressively along the training trajectory and dynamically per input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yonggan Fu; Haoran You; Yang Zhao; Yue Wang; Chaojian Li; Kailash Gopalakrishnan; Zhangyang Wang; Yingyan Lin; | code |
| 1018 | Improving Neural Network Training In Low Dimensional Random Bases Highlight: We propose re-drawing the random subspace at each step, which yields significantly better performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Frithjof Gressmann; Zach Eaton-Rosen; Carlo Luschi; | |
| 1019 | Safe Reinforcement Learning Via Curriculum Induction Highlight: This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor that saves the agent from violating constraints during learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matteo Turchetta; Andrey Kolobov; Shital Shah; Andreas Krause; Alekh Agarwal; | |
| 1020 | Leverage The Average: An Analysis Of KL Regularization In Reinforcement Learning Highlight: We study KL regularization within an approximate value iteration scheme and show that it implicitly averages q-values. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nino Vieillard; Tadashi Kozuno; Bruno Scherrer; Olivier Pietquin; Remi Munos; Matthieu Geist; | |
| 1021 | How Robust Are The Estimated Effects Of Nonpharmaceutical Interventions Against COVID-19? Highlight: To answer this question, we investigate 2 state-of-the-art NPI effectiveness models and propose 6 variants that make different structural assumptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mrinank Sharma; S�ren Mindermann; Jan Brauner; Gavin Leech; Anna Stephenson; Tom� Gavenciak; Jan Kulveit; Yee Whye Teh; Leonid Chindelevitch; Yarin Gal; | |
| 1022 | Beyond Individualized Recourse: Interpretable And Interactive Summaries Of Actionable Recourses Highlight: To this end, we propose a novel model agnostic framework called Actionable Recourse Summaries (AReS) to construct global counterfactual explanations which provide an interpretable and accurate summary of recourses for the entire population. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaivalya Rawal; Himabindu Lakkaraju; | |
| 1023 | Generalization Error In High-dimensional Perceptrons: Approaching Bayes Error With Convex Optimization Highlight: We consider a commonly studied supervised classification of a synthetic dataset whose labels are generated by feeding a one-layer non-linear neural network with random iid inputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benjamin Aubin; Florent Krzakala; Yue Lu; Lenka Zdeborov�; | |
| 1024 | Projection Efficient Subgradient Method And Optimal Nonsmooth Frank-Wolfe Method Highlight: We consider the classical setting of optimizing a nonsmooth Lipschitz continuous convex function over a convex constraint set, when having access to a (stochastic) first-order oracle (FO) for the function and a projection oracle (PO) for the constraint set. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kiran K. Thekumparampil; Prateek Jain; Praneeth Netrapalli; Sewoong Oh; | |
| 1025 | PGM-Explainer: Probabilistic Graphical Model Explanations For Graph Neural Networks Highlight: In this paper, we propose PGM-Explainer, a Probabilistic Graphical Model (PGM) model-agnostic explainer for GNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minh Vu; My T. Thai; | |
| 1026 | Few-Cost Salient Object Detection With Adversarial-Paced Learning Highlight: To address this problem, this paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only, thus dramatically alleviating human labor in training models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dingwen Zhang; HaiBin Tian; Jungong Han; | |
| 1027 | Minimax Estimation Of Conditional Moment Models Highlight: We introduce a min-max criterion function, under which the estimation problem can be thought of as solving a zero-sum game between a modeler who is optimizing over the hypothesis space of the target model and an adversary who identifies violating moments over a test function space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nishanth Dikkala; Greg Lewis; Lester Mackey; Vasilis Syrgkanis; | |
| 1028 | Causal Imitation Learning With Unobserved Confounders Highlight: In this paper, we relax this assumption and study imitation learning when sensory inputs of the learner and the expert differ. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junzhe Zhang; Daniel Kumor; Elias Bareinboim; | |
| 1029 | Your GAN Is Secretly An Energy-based Model And You Should Use Discriminator Driven Latent Sampling Highlight: We show that the sum of the implicit generator log-density $\log p_g$ of a GAN with the logit score of the discriminator defines an energy function which yields the true data density when the generator is imperfect but the discriminator is optimal, thus making it possible to improve on the typical generator (with implicit density $p_g$). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tong Che; Ruixiang ZHANG; Jascha Sohl-Dickstein; Hugo Larochelle; Liam Paull; Yuan Cao; Yoshua Bengio; | |
| 1030 | Learning Black-Box Attackers With Transferable Priors And Query Feedback Highlight: By combining transferability-based and query-based black-box attack, we propose a surprisingly simple baseline approach (named SimBA++) using the surrogate model, which significantly outperforms several state-of-the-art methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiancheng YANG; Yangzhou Jiang; Xiaoyang Huang; Bingbing Ni; Chenglong Zhao; | code |
| 1031 | Locally Differentially Private (Contextual) Bandits Learning Highlight: We study locally differentially private (LDP) bandits learning in this paper. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kai Zheng; Tianle Cai; Weiran Huang; Zhenguo Li; Liwei Wang; | |
| 1032 | Invertible Gaussian Reparameterization: Revisiting The Gumbel-Softmax Highlight: We propose a modular and more flexible family of reparameterizable distributions where Gaussian noise is transformed into a one-hot approximation through an invertible function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andres Potapczynski; Gabriel Loaiza-Ganem; John P. Cunningham; | code |
| 1033 | Kernel Based Progressive Distillation For Adder Neural Networks Highlight: In this paper, we present a novel method for further improving the performance of ANNs without increasing the trainable parameters via a progressive kernel based knowledge distillation (PKKD) method. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yixing Xu; Chang Xu; Xinghao Chen; Wei Zhang; Chunjing XU; Yunhe Wang; | |
| 1034 | Adversarial Soft Advantage Fitting: Imitation Learning Without Policy Optimization Highlight: We propose to remove the burden of the policy optimization steps by leveraging a novel discriminator formulation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Paul Barde; Julien Roy; Wonseok Jeon; Joelle Pineau; Chris Pal; Derek Nowrouzezahrai; | |
| 1035 | Agree To Disagree: Adaptive Ensemble Knowledge Distillation In Gradient Space Highlight: In this paper, we examine the diversity of teacher models in the gradient space and regard the ensemble knowledge distillation as a multi-objective optimization problem so that we can determine a better optimization direction for the training of student network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shangchen Du; Shan You; Xiaojie Li; Jianlong Wu; Fei Wang; Chen Qian; Changshui Zhang; | |
| 1036 | The Wasserstein Proximal Gradient Algorithm Highlight: In this work, we propose a Forward Backward (FB) discretization scheme that can tackle the case where the objective function is the sum of a smooth and a nonsmooth geodesically convex terms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adil SALIM; Anna Korba; Giulia Luise; | |
| 1037 | Universally Quantized Neural Compression Highlight: We demonstrate that a uniform noise channel can also be implemented at test time using universal quantization (Ziv, 1985). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eirikur Agustsson; Lucas Theis; | |
| 1038 | Temporal Variability In Implicit Online Learning Highlight: In this work, we shed light on this behavior carrying out a careful regret analysis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicol� Campolongo; Francesco Orabona; | |
| 1039 | Investigating Gender Bias In Language Models Using Causal Mediation Analysis Highlight: We propose a methodology grounded in the theory of causal mediation analysis for interpreting which parts of a model are causally implicated in its behavior. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jesse Vig; Sebastian Gehrmann; Yonatan Belinkov; Sharon Qian; Daniel Nevo; Yaron Singer; Stuart Shieber; | |
| 1040 | Off-Policy Imitation Learning From Observations Highlight: In this work, we propose a sample-efficient LfO approach which enables off-policy optimization in a principled manner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhuangdi Zhu; Kaixiang Lin; Bo Dai; Jiayu Zhou; | |
| 1041 | Escaping Saddle-Point Faster Under Interpolation-like Conditions Highlight: In this paper, we show that under over-parametrization several standard stochastic optimization algorithms escape saddle-points and converge to local-minimizers much faster. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Abhishek Roy; Krishnakumar Balasubramanian; Saeed Ghadimi; Prasant Mohapatra; | |
| 1042 | Mat�rn Gaussian Processes On Riemannian Manifolds Highlight: In this work, we propose techniques for computing the kernels of these processes on compact Riemannian manifolds via spectral theory of the Laplace-Beltrami operator in a fully constructive manner, thereby allowing them to be trained via standard scalable techniques such as inducing point methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Viacheslav Borovitskiy; Alexander Terenin; Peter Mostowsky; Marc Deisenroth; | |
| 1043 | Improved Techniques For Training Score-Based Generative Models Highlight: We provide a new theoretical analysis of learning and sampling from score models in high dimensional spaces, explaining existing failure modes and motivating new solutions that generalize across datasets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yang Song; Stefano Ermon; | |
| 1044 | Wav2vec 2.0: A Framework For Self-Supervised Learning Of Speech Representations Highlight: We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexei Baevski; Yuhao Zhou; Abdel-rahman Mohamed; Michael Auli; | |
| 1045 | A Maximum-Entropy Approach To Off-Policy Evaluation In Average-Reward MDPs Highlight: In a more general setting, when the feature dynamics are approximately linear and for arbitrary rewards, we propose a new approach for estimating stationary distributions with function approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nevena Lazic; Dong Yin; Mehrdad Farajtabar; Nir Levine; Dilan Gorur; Chris Harris; Dale Schuurmans; | |
| 1046 | Instead Of Rewriting Foreign Code For Machine Learning, Automatically Synthesize Fast Gradients Highlight: This paper presents Enzyme, a high-performance automatic differentiation (AD) compiler plugin for the LLVM compiler framework capable of synthesizing gradients of statically analyzable programs expressed in the LLVM intermediate representation (IR). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
William Moses; Valentin Churavy; | |
| 1047 | Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? Highlight: In this work, we find empirically that pre-training architecture representations using only neural architectures without their accuracies as labels improves the downstream architecture search efficiency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shen Yan; Yu Zheng; Wei Ao; Xiao Zeng; Mi Zhang; | |
| 1048 | Value-driven Hindsight Modelling Highlight: We develop an approach for representation learning in RL that sits in between these two extremes: we propose to learn what to model in a way that can directly help value prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arthur Guez; Fabio Viola; Theophane Weber; Lars Buesing; Steven Kapturowski; Doina Precup; David Silver; Nicolas Heess; | |
| 1049 | Dynamic Regret Of Convex And Smooth Functions Highlight: Specifically, we propose novel online algorithms that are capable of leveraging smoothness and replace the dependence on $T$ in the dynamic regret by problem-dependent quantities: the variation in gradients of loss functions, the cumulative loss of the comparator sequence, and the minimum of the previous two terms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peng Zhao; Yu-Jie Zhang; Lijun Zhang; Zhi-Hua Zhou; | |
| 1050 | On Convergence Of Nearest Neighbor Classifiers Over Feature Transformations Highlight: This leads to an emerging gap between our theoretical understanding of kNN and its practical applications. In this paper, we take a first step towards bridging this gap. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luka Rimanic; Cedric Renggli; Bo Li; Ce Zhang; | |
| 1051 | Mitigating Manipulation In Peer Review Via Randomized Reviewer Assignments Highlight: We then present a (randomized) algorithm for reviewer assignment that can optimally solve the reviewer-assignment problem under any given constraints on the probability of assignment for any reviewer-paper pair. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Steven Jecmen; Hanrui Zhang; Ryan Liu; Nihar Shah; Vincent Conitzer; Fei Fang; | |
| 1052 | Contrastive Learning Of Global And Local Features For Medical Image Segmentation With Limited Annotations Highlight: In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Krishna Chaitanya; Ertunc Erdil; Neerav Karani; Ender Konukoglu; | code |
| 1053 | Self-Supervised Graph Transformer On Large-Scale Molecular Data Highlight: To address them both, we propose a novel framework, GROVER, which stands for Graph Representation frOm self-superVised mEssage passing tRansformer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu Rong; Yatao Bian; Tingyang Xu; Weiyang Xie; Ying WEI; Wenbing Huang; Junzhou Huang; | |
| 1054 | Generative Neurosymbolic Machines Highlight: In this paper, we propose Generative Neurosymbolic Machines, a generative model that combines the benefits of distributed and symbolic representations to support both structured representations of symbolic components and density-based generation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jindong Jiang; Sungjin Ahn; | |
| 1055 | How Many Samples Is A Good Initial Point Worth In Low-rank Matrix Recovery? Highlight: In this paper, we quantify the relationship between the quality of the initial guess and the corresponding reduction in data requirements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jialun Zhang; Richard Zhang; | |
| 1056 | CSER: Communication-efficient SGD With Error Reset Highlight: We propose a novel SGD variant: \underline{C}ommunication-efficient \underline{S}GD with \underline{E}rror \underline{R}eset, or \underline{CSER}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cong Xie; Shuai Zheng; Oluwasanmi O. Koyejo; Indranil Gupta; Mu Li; Haibin Lin; | |
| 1057 | Efficient Estimation Of Neural Tuning During Naturalistic Behavior Highlight: We develop efficient procedures for parameter learning by optimizing a generalized cross-validation score and infer marginal confidence bounds for the contribution of each feature to neural responses. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edoardo Balzani; Kaushik Lakshminarasimhan; Dora Angelaki; Cristina Savin; | |
| 1058 | High-recall Causal Discovery For Autocorrelated Time Series With Latent Confounders Highlight: We present a new method for linear and nonlinear, lagged and contemporaneous constraint-based causal discovery from observational time series in the presence of latent confounders. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andreas Gerhardus; Jakob Runge; | |
| 1059 | Forget About The LiDAR: Self-Supervised Depth Estimators With MED Probability Volumes Highlight: We present extensive experimental results on the KITTI, CityScapes, and Make3D datasets to verify our method’s effectiveness. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Juan Luis Gonzalez; Munchurl Kim; | |
| 1060 | Joint Contrastive Learning With Infinite Possibilities Highlight: This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qi Cai; Yu Wang; Yingwei Pan; Ting Yao; Tao Mei; | code |
| 1061 | Robust Gaussian Covariance Estimation In Nearly-Matrix Multiplication Time Highlight: In this paper, we demonstrate a novel algorithm that achieves the same statistical guarantees, but which runs in time $\widetilde{O} (T(N, d) \log \kappa)$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jerry Li; Guanghao Ye; | |
| 1062 | Adversarially-learned Inference Via An Ensemble Of Discrete Undirected Graphical Models Highlight: Instead, we propose an inference-agnostic adversarial training framework which produces an infinitely-large ensemble of graphical models (AGMs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adarsh K Jeewajee; Leslie Kaelbling; | |
| 1063 | GS-WGAN: A Gradient-Sanitized Approach For Learning Differentially Private Generators Highlight: To this end, we propose Gradient-sanitized Wasserstein Generative Adversarial Networks (GS-WGAN), which allows releasing a sanitized form of the sensitive data with rigorous privacy guarantees. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dingfan Chen; Tribhuvanesh Orekondy; Mario Fritz; | |
| 1064 | SurVAE Flows: Surjections To Bridge The Gap Between VAEs And Flows Highlight: In this paper, we introduce SurVAE Flows: A modular framework of composable transformations that encompasses VAEs and normalizing flows. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Didrik Nielsen; Priyank Jaini; Emiel Hoogeboom; Ole Winther; Max Welling; | |
| 1065 | Learning Causal Effects Via Weighted Empirical Risk Minimization Highlight: In this paper, we develop a learning framework that marries two families of methods, benefiting from the generality of the causal identification theory and the effectiveness of the estimators produced based on the principle of ERM. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yonghan Jung; Jin Tian; Elias Bareinboim; | |
| 1066 | Revisiting The Sample Complexity Of Sparse Spectrum Approximation Of Gaussian Processes Highlight: We introduce a new scalable approximation for Gaussian processes with provable guarantees which holds simultaneously over its entire parameter space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minh Hoang; Nghia Hoang; Hai Pham; David Woodruff; | |
| 1067 | Incorporating Interpretable Output Constraints In Bayesian Neural Networks Highlight: We introduce a novel probabilistic framework for reasoning with such constraints and formulate a prior that enables us to effectively incorporate them into Bayesian neural networks (BNNs), including a variant that can be amortized over tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wanqian Yang; Lars Lorch; Moritz Graule; Himabindu Lakkaraju; Finale Doshi-Velez; | |
| 1068 | Multi-Stage Influence Function Highlight: In this paper, we develop a multi-stage influence function score to track predictions from a finetuned model all the way back to the pretraining data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongge Chen; Si Si; Yang Li; Ciprian Chelba; Sanjiv Kumar; Duane Boning; Cho-Jui Hsieh; | |
| 1069 | Probabilistic Fair Clustering Highlight: In this paper, we generalize this by assuming imperfect knowledge of group membership through probabilistic assignments, and present algorithms in this more general setting with approximation ratio guarantees. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Seyed Esmaeili; Brian Brubach; Leonidas Tsepenekas; John Dickerson; | |
| 1070 | Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty Highlight: In this paper, we introduce stochastic segmentation networks (SSNs), an efficient probabilistic method for modelling aleatoric uncertainty with any image segmentation network architecture. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Miguel Monteiro; Loic Le Folgoc; Daniel Coelho de Castro; Nick Pawlowski; Bernardo Marques; Konstantinos Kamnitsas; Mark van der Wilk; Ben Glocker; | |
| 1071 | ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based On Nonlinear ICA Highlight: We consider the identifiability theory of probabilistic models and establish sufficient conditions under which the representations learnt by a very broad family of conditional energy-based models are unique in function space, up to a simple transformation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilyes Khemakhem; Ricardo Monti; Diederik Kingma; Aapo Hyvarinen; | |
| 1072 | Testing Determinantal Point Processes Highlight: In this paper, we investigate DPPs from a new perspective: property testing of distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Khashayar Gatmiry; Maryam Aliakbarpour; Stefanie Jegelka; | |
| 1073 | CogLTX: Applying BERT To Long Texts Highlight: Founded on the cognitive theory stemming from Baddeley, our CogLTX framework identifies key sentences by training a judge model, concatenates them for reasoning and enables multi-step reasoning via rehearsal and decay. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ming Ding; Chang Zhou; Hongxia Yang; Jie Tang; | |
| 1074 | F-GAIL: Learning F-Divergence For Generative Adversarial Imitation Learning Highlight: In this work, we propose f-GAIL – a new generative adversarial imitation learning model – that automatically learns a discrepancy measure from the f-divergence family as well as a policy capable of producing expert-like behaviors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xin Zhang; Yanhua Li; Ziming Zhang; Zhi-Li Zhang; | |
| 1075 | Non-parametric Models For Non-negative Functions Highlight: In this paper we provide the first model for non-negative functions which benefits from the same good properties of linear models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ulysse Marteau-Ferey; Francis Bach; Alessandro Rudi; | |
| 1076 | Uncertainty Aware Semi-Supervised Learning On Graph Data Highlight: In this work, we propose a multi-source uncertainty framework using a GNN that reflects various types of predictive uncertainties in both deep learning and belief/evidence theory domains for node classification predictions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xujiang Zhao; Feng Chen; Shu Hu; Jin-Hee Cho; | |
| 1077 | ConvBERT: Improving BERT With Span-based Dynamic Convolution Highlight: We therefore propose a novel span-based dynamic convolution to replace these self-attention heads to directly model local dependencies. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zi-Hang Jiang; Weihao Yu; Daquan Zhou; Yunpeng Chen; Jiashi Feng; Shuicheng Yan; | |
| 1078 | Practical No-box Adversarial Attacks Against DNNs Highlight: We propose three mechanisms for training with a very small dataset (on the order of tens of examples) and find that prototypical reconstruction is the most effective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qizhang Li; Yiwen Guo; Hao Chen; | code |
| 1079 | Breaking The Sample Size Barrier In Model-Based Reinforcement Learning With A Generative Model Highlight: We investigate the sample efficiency of reinforcement learning in a ?-discounted infinite-horizon Markov decision process (MDP) with state space S and action space A, assuming access to a generative model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gen Li; Yuting Wei; Yuejie Chi; Yuantao Gu; Yuxin Chen; | |
| 1080 | Walking In The Shadow: A New Perspective On Descent Directions For Constrained Minimization Highlight: In this work, we attempt to demystify the impact of movement in these directions towards attaining constrained minimizers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hassan Mortagy; Swati Gupta; Sebastian Pokutta; | |
| 1081 | Path Sample-Analytic Gradient Estimators For Stochastic Binary Networks Highlight: We propose a new method for this estimation problem combining sampling and analytic approximation steps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Shekhovtsov; Viktor Yanush; Boris Flach; | |
| 1082 | Reward Propagation Using Graph Convolutional Networks Highlight: We propose a new framework for learning potential functions by leveraging ideas from graph representation learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Martin Klissarov; Doina Precup; | |
| 1083 | LoopReg: Self-supervised Learning Of Implicit Surface Correspondences, Pose And Shape For 3D Human Mesh Registration Highlight: Our main contribution is LoopReg, an end-to-end learning framework to register a corpus of scans to a common 3D human model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bharat Lal Bhatnagar; Cristian Sminchisescu; Christian Theobalt; Gerard Pons-Moll; | |
| 1084 | Fully Dynamic Algorithm For Constrained Submodular Optimization Highlight: We study this classic problem in the fully dynamic setting, where elements can be both inserted and removed. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Silvio Lattanzi; Slobodan Mitrovic; Ashkan Norouzi-Fard; Jakub M. Tarnawski; Morteza Zadimoghaddam; | |
| 1085 | Robust Optimal Transport With Applications In Generative Modeling And Domain Adaptation Highlight: In this paper, we resolve these issues by deriving a computationally-efficient dual form of the robust OT optimization that is amenable to modern deep learning applications. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yogesh Balaji; Rama Chellappa; Soheil Feizi; | code |
| 1086 | Autofocused Oracles For Model-based Design Highlight: In particular, we (i) formalize the data-driven design problem as a non-zero-sum game, (ii) develop a principled strategy for retraining the regression model as the design algorithm proceeds—what we refer to as autofocusing, and (iii) demonstrate the promise of autofocusing empirically. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Clara Fannjiang; Jennifer Listgarten; | |
| 1087 | Debiasing Averaged Stochastic Gradient Descent To Handle Missing Values Highlight: We propose an averaged stochastic gradient algorithm handling missing values in linear models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aude Sportisse; Claire Boyer; Aymeric Dieuleveut; Julie Josses; | |
| 1088 | Trajectory-wise Multiple Choice Learning For Dynamics Generalization In Reinforcement Learning Highlight: In this paper, we present a new model-based RL algorithm, coined trajectory-wise multiple choice learning, that learns a multi-headed dynamics model for dynamics generalization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Younggyo Seo; Kimin Lee; Ignasi Clavera Gilaberte; Thanard Kurutach; Jinwoo Shin; Pieter Abbeel; | code |
| 1089 | CompRess: Self-Supervised Learning By Compressing Representations Highlight: In this work, instead of designing a new pseudo task for self-supervised learning, we develop a model compression method to compress an already learned, deep self-supervised model (teacher) to a smaller one (student). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Soroush Abbasi Koohpayegani; Ajinkya Tejankar; Hamed Pirsiavash; | code |
| 1090 | Sample Complexity And Effective Dimension For Regression On Manifolds Highlight: Manifold models arise in a wide variety of modern machine learning problems, and our goal is to help understand the effectiveness of various implicit and explicit dimensionality-reduction methods that exploit manifold structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrew McRae; Justin Romberg; Mark Davenport; | |
| 1091 | The Phase Diagram Of Approximation Rates For Deep Neural Networks Highlight: We explore the phase diagram of approximation rates for deep neural networks and prove several new theoretical results. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dmitry Yarotsky; Anton Zhevnerchuk; | |
| 1092 | Timeseries Anomaly Detection Using Temporal Hierarchical One-Class Network Highlight: In this paper, we propose the Temporal Hierarchical One-Class (THOC) network, a temporal one-class classification model for timeseries anomaly detection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lifeng Shen; Zhuocong Li; James Kwok; | |
| 1093 | EcoLight: Intersection Control In Developing Regions Under Extreme Budget And Network Constraints Highlight: This paper presents EcoLight intersection control for developing regions, where budget is constrained and network connectivity is very poor. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sachin Chauhan; Kashish Bansal; Rijurekha Sen; | |
| 1094 | Reconstructing Perceptive Images From Brain Activity By Shape-Semantic GAN Highlight: Inspired by the theory that visual features are hierarchically represented in cortex, we propose to break the complex visual signals into multi-level components and decode each component separately. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tao Fang; Yu Qi; Gang Pan; | |
| 1095 | Emergent Complexity And Zero-shot Transfer Via Unsupervised Environment Design Highlight: We propose Unsupervised Environment Design (UED) as an alternative paradigm, where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Dennis; Natasha Jaques; Eugene Vinitsky; Alexandre Bayen; Stuart Russell; Andrew Critch; Sergey Levine; | |
| 1096 | A Spectral Energy Distance For Parallel Speech Synthesis Highlight: Here, we propose a new learning method that allows us to train highly parallel models of speech, without requiring access to an analytical likelihood function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexey Gritsenko; Tim Salimans; Rianne van den Berg; Jasper Snoek; Nal Kalchbrenner; | |
| 1097 | Simulating A Primary Visual Cortex At The Front Of CNNs Improves Robustness To Image Perturbations Highlight: Inspired by this observation, we developed VOneNets, a new class of hybrid CNN vision models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joel Dapello; Tiago Marques; Martin Schrimpf; Franziska Geiger; David Cox; James J. DiCarlo; | |
| 1098 | Learning From Positive And Unlabeled Data With Arbitrary Positive Shift Highlight: Our key insight is that only the negative class’s distribution need be fixed. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zayd Hammoudeh; Daniel Lowd; | |
| 1099 | Deep Energy-based Modeling Of Discrete-Time Physics Highlight: In this study, we propose a deep energy-based physical model that admits a specific differential geometric structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Takashi Matsubara; Ai Ishikawa; Takaharu Yaguchi; | |
| 1100 | Quantifying Learnability And Describability Of Visual Concepts Emerging In Representation Learning Highlight: In this paper, we consider in particular how to characterise visual groupings discovered automatically by deep neural networks, starting with state-of-the-art clustering methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Iro Laina; Ruth Fong; Andrea Vedaldi; | |
| 1101 | Self-Learning Transformations For Improving Gaze And Head Redirection Highlight: In this paper we propose a novel generative model for images of faces, that is capable of producing high-quality images under fine-grained control over eye gaze and head orientation angles. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yufeng Zheng; Seonwook Park; Xucong Zhang; Shalini De Mello; Otmar Hilliges; | code |
| 1102 | Language-Conditioned Imitation Learning For Robot Manipulation Tasks Highlight: Motivated by insights into the human teaching process, we introduce a method for incorporating unstructured natural language into imitation learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simon Stepputtis; Joseph Campbell; Mariano Phielipp; Stefan Lee; Chitta Baral; Heni Ben Amor; | |
| 1103 | POMDPs In Continuous Time And Discrete Spaces Highlight: In this paper, we give a mathematical description of a continuous-time partial observable Markov decision process (POMDP). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bastian Alt; Matthias Schultheis; Heinz Koeppl; | |
| 1104 | Exemplar Guided Active Learning Highlight: We describe an active learning approach that (1) explicitly searches for rare classes by leveraging the contextual embedding spaces provided by modern language models, and (2) incorporates a stopping rule that ignores classes once we prove that they occur below our target threshold with high probability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jason S. Hartford; Kevin Leyton-Brown; Hadas Raviv; Dan Padnos; Shahar Lev; Barak Lenz; | |
| 1105 | Grasp Proposal Networks: An End-to-End Solution For Visual Learning Of Robotic Grasps Highlight: To this end, we propose in this work a novel, end-to-end \emph{Grasp Proposal Network (GPNet)}, to predict a diverse set of 6-DOF grasps for an unseen object observed from a single and unknown camera view. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaozheng Wu; Jian Chen; Qiaoyu Cao; Jianchi Zhang; Yunxin Tai; Lin Sun; Kui Jia; | code |
| 1106 | Node Embeddings And Exact Low-Rank Representations Of Complex Networks Highlight: In this work we show that the results of Seshadhri et al. are intimately connected to the model they use rather than the low-dimensional structure of complex networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sudhanshu Chanpuriya; Cameron Musco; Konstantinos Sotiropoulos; Charalampos Tsourakakis; | |
| 1107 | Fictitious Play For Mean Field Games: Continuous Time Analysis And Applications Highlight: In this paper, we deepen the analysis of continuous time Fictitious Play learning algorithm to the consideration of various finite state Mean Field Game settings (finite horizon, $\gamma$-discounted), allowing in particular for the introduction of an additional common noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sarah Perrin; Julien Perolat; Mathieu Lauriere; Matthieu Geist; Romuald Elie; Olivier Pietquin; | |
| 1108 | Steering Distortions To Preserve Classes And Neighbors In Supervised Dimensionality Reduction Highlight: The supervised mapping method introduced in the present paper, called ClassNeRV, proposes an original stress function that takes class annotation into account and evaluates embedding quality both in terms of false neighbors and missed neighbors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Beno�t Colange; Jaakko Peltonen; Michael Aupetit; Denys Dutykh; Sylvain Lespinats; | |
| 1109 | On Infinite-Width Hypernetworks Highlight: In this work, we study wide over-parameterized hypernetworks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Etai Littwin; Tomer Galanti; Lior Wolf; Greg Yang; | |
| 1110 | Interferobot: Aligning An Optical Interferometer By A Reinforcement Learning Agent Highlight: Here we train an RL agent to align a Mach-Zehnder interferometer, which is an essential part of many optical experiments, based on images of interference fringes acquired by a monocular camera. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dmitry Sorokin; Alexander Ulanov; Ekaterina Sazhina; Alexander Lvovsky; | |
| 1111 | Program Synthesis With Pragmatic Communication Highlight: This work introduces a new inductive bias derived by modeling the program synthesis task as rational communication, drawing insights from recursive reasoning models of pragmatics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yewen Pu; Kevin Ellis; Marta Kryven; Josh Tenenbaum; Armando Solar-Lezama; | |
| 1112 | Principal Neighbourhood Aggregation For Graph Nets Highlight: Accordingly, we propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degree-scalers (which generalize the sum aggregator). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gabriele Corso; Luca Cavalleri; Dominique Beaini; Pietro Li�; Petar Velickovic; | |
| 1113 | Reliable Graph Neural Networks Via Robust Aggregation Highlight: We propose a robust aggregation function motivated by the field of robust statistics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simon Geisler; Daniel Z�gner; Stephan G�nnemann; | |
| 1114 | Instance Selection For GANs Highlight: In this work we propose a novel approach to improve sample quality: altering the training dataset via instance selection before model training has taken place. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Terrance DeVries; Michal Drozdzal; Graham W. Taylor; | code |
| 1115 | Linear Disentangled Representations And Unsupervised Action Estimation Highlight: In this work we empirically show that linear disentangled representations are not present in standard VAE models and that they instead require altering the loss landscape to induce them. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matthew Painter; Adam Prugel-Bennett; Jonathon Hare; | |
| 1116 | Video Frame Interpolation Without Temporal Priors Highlight: In this work, we solve the video frame interpolation problem in a general situation, where input frames can be acquired under uncertain exposure (and interval) time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Youjian Zhang; Chaoyue Wang; Dacheng Tao; | code |
| 1117 | Learning Compositional Functions Via Multiplicative Weight Updates Highlight: This paper proves that multiplicative weight updates satisfy a descent lemma tailored to compositional functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeremy Bernstein; Jiawei Zhao; Markus Meister; Ming-Yu Liu; Anima Anandkumar; Yisong Yue; | |
| 1118 | Sample Complexity Of Uniform Convergence For Multicalibration Highlight: In this work, we address the multicalibration error and decouple it from the prediction error. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eliran Shabat; Lee Cohen; Yishay Mansour; | |
| 1119 | Differentiable Neural Architecture Search In Equivalent Space With Exploration Enhancement Highlight: Differently, this paper utilizes a variational graph autoencoder to injectively transform the discrete architecture space into an equivalently continuous latent space, to resolve the incongruence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Miao Zhang; Huiqi Li; Shirui Pan; Xiaojun Chang; Zongyuan Ge; Steven Su; | |
| 1120 | The Interplay Between Randomness And Structure During Learning In RNNs Highlight: We show how the low-dimensional task structure leads to low-rank changes to connectivity, and how random initial connectivity facilitates learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Friedrich Schuessler; Francesca Mastrogiuseppe; Alexis Dubreuil; Srdjan Ostojic; Omri Barak; | |
| 1121 | A Generalized Neural Tangent Kernel Analysis For Two-layer Neural Networks Highlight: In this paper, we provide a generalized neural tangent kernel analysis and show that noisy gradient descent with weight decay can still exhibit a “kernel-like” behavior. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zixiang Chen; Yuan Cao; Quanquan Gu; Tong Zhang; | |
| 1122 | Instance-wise Feature Grouping Highlight: In this paper, we formally define two types of redundancies using information theory: \textit{Representation} and \textit{Relevant redundancies}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aria Masoomi; Chieh Wu; Tingting Zhao; Zifeng Wang; Peter Castaldi; Jennifer Dy; | |
| 1123 | Robust Disentanglement Of A Few Factors At A Time Highlight: Building on top of this observation we introduce the recursive rPU-VAE approach. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benjamin Estermann; Markus Marks; Mehmet Fatih Yanik; | |
| 1124 | PC-PG: Policy Cover Directed Exploration For Provable Policy Gradient Learning Highlight: This work introduces the the POLICY COVER GUIDED POLICY GRADIENT (PC- PG) algorithm, which provably balances the exploration vs. exploitation tradeoff using an ensemble of learned policies (the policy cover). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alekh Agarwal; Mikael Henaff; Sham Kakade; Wen Sun; | |
| 1125 | Group Contextual Encoding For 3D Point Clouds Highlight: In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point Cloud scenarios. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xu Liu; Chengtao Li; Jian Wang; Jingbo Wang; Boxin Shi; Xiaodong He; | |
| 1126 | Latent Bandits Revisited Highlight: In this work, we propose general algorithms for latent bandits, based on both upper confidence bounds and Thompson sampling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joey Hong; Branislav Kveton; Manzil Zaheer; Yinlam Chow; Amr Ahmed; Craig Boutilier; | |
| 1127 | Is Normalization Indispensable For Training Deep Neural Network? Highlight: In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jie Shao; Kai Hu; Changhu Wang; Xiangyang Xue; Bhiksha Raj; | |
| 1128 | Optimization And Generalization Of Shallow Neural Networks With Quadratic Activation Functions Highlight: We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the overparametrized regime where the layer width m is larger than the input dimension d. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stefano Sarao Mannelli; Eric Vanden-Eijnden; Lenka Zdeborov�; | |
| 1129 | Intra Order-preserving Functions For Calibration Of Multi-Class Neural Networks Highlight: In this work, we aim to learn general post-hoc calibration functions that can preserve the top-k predictions of any deep network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amir Rahimi; Amirreza Shaban; Ching-An Cheng; Richard Hartley; Byron Boots; | |
| 1130 | Linear Time Sinkhorn Divergences Using Positive Features Highlight: We propose to use instead ground costs of the form $c(x,y)=-\log\dotp{\varphi(x)}{\varphi(y)}$ where $\varphi$ is a map from the ground space onto the positive orthant $\RR^r_+$, with $r\ll n$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Meyer Scetbon; Marco Cuturi; | |
| 1131 | VarGrad: A Low-Variance Gradient Estimator For Variational Inference Highlight: We analyse the properties of an unbiased gradient estimator of the ELBO for variational inference, based on the score function method with leave-one-out control variates. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lorenz Richter; Ayman Boustati; Nikolas N�sken; Francisco Ruiz; Omer Deniz Akyildiz; | |
| 1132 | A Convolutional Auto-Encoder For Haplotype Assembly And Viral Quasispecies Reconstruction Highlight: This paper proposes a read clustering method based on a convolutional auto-encoder designed to first project sequenced fragments to a low-dimensional space and then estimate the probability of the read origin using learned embedded features. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziqi Ke; Haris Vikalo; | code |
| 1133 | Promoting Stochasticity For Expressive Policies Via A Simple And Efficient Regularization Method Highlight: To tackle this problem, we propose a novel regularization method that is compatible with a broad range of expressive policy architectures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qi Zhou; Yufei Kuang; Zherui Qiu; Houqiang Li; Jie Wang; | |
| 1134 | Adversarial Counterfactual Learning And Evaluation For Recommender System Highlight: We propose a principled solution by introducing a minimax empirical risk formulation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Da Xu; Chuanwei Ruan; Evren Korpeoglu; Sushant Kumar; Kannan Achan; | |
| 1135 | Memory-Efficient Learning Of Stable Linear Dynamical Systems For Prediction And Control Highlight: We propose a novel algorithm for learning stable LDSs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Georgios Mamakoukas; Orest Xherija; Todd Murphey; | code |
| 1136 | Evolving Normalization-Activation Layers Highlight: Normalization layers and activation functions are fundamental components in deep networks and typically co-locate with each other. Here we propose to design them using an automated approach. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hanxiao Liu; Andy Brock; Karen Simonyan; Quoc Le; | |
| 1137 | ScaleCom: Scalable Sparsified Gradient Compression For Communication-Efficient Distributed Training Highlight: To mitigate these issues, we propose a new compression technique, Scalable Sparsified Gradient Compression (ScaleComp), that (i) leverages similarity in the gradient distribution amongst learners to provide a commutative compressor and keep communication cost constant to worker number and (ii) includes low-pass filter in local gradient accumulations to mitigate the impacts of large batch size training and significantly improve scalability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chia-Yu Chen; Jiamin Ni; Songtao Lu; Xiaodong Cui; Pin-Yu Chen; Xiao Sun; Naigang Wang; Swagath Venkataramani; Vijayalakshmi (Viji) Srinivasan; Wei Zhang; Kailash Gopalakrishnan; | |
| 1138 | RelationNet++: Bridging Visual Representations For Object Detection Via Transformer Decoder Highlight: This paper presents an attention-based decoder module similar as that in Transformer~\cite{vaswani2017attention} to bridge other representations into a typical object detector built on a single representation format, in an end-to-end fashion. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cheng Chi; Fangyun Wei; Han Hu; | code |
| 1139 | Efficient Learning Of Discrete Graphical Models Highlight: In this work, we provide the first sample-efficient method based on the Interaction Screening framework that allows one to provably learn fully general discrete factor models with node-specific discrete alphabets and multi-body interactions, specified in an arbitrary basis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marc Vuffray; Sidhant Misra; Andrey Lokhov; | |
| 1140 | Near-Optimal SQ Lower Bounds For Agnostically Learning Halfspaces And ReLUs Under Gaussian Marginals Highlight: We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilias Diakonikolas; Daniel Kane; Nikos Zarifis; | |
| 1141 | Neurosymbolic Transformers For Multi-Agent Communication Highlight: We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeevana Priya Inala; Yichen Yang; James Paulos; Yewen Pu; Osbert Bastani; Vijay Kumar; Martin Rinard; Armando Solar-Lezama; | |
| 1142 | Fairness In Streaming Submodular Maximization: Algorithms And Hardness Highlight: In this work we address the question: Is it possible to create fair summaries for massive datasets? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marwa El Halabi; Slobodan Mitrovic; Ashkan Norouzi-Fard; Jakab Tardos; Jakub M. Tarnawski; | |
| 1143 | Smoothed Geometry For Robust Attribution Highlight: To mitigate these attacks in practice, we propose an inexpensive regularization method that promotes these conditions in DNNs, as well as a stochastic smoothing technique that does not require re-training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zifan Wang; Haofan Wang; Shakul Ramkumar; Piotr Mardziel; Matt Fredrikson; Anupam Datta; | |
| 1144 | Fast Adversarial Robustness Certification Of Nearest Prototype Classifiers For Arbitrary Seminorms Highlight: We prove that if NPCs use a dissimilarity measure induced by a seminorm, the hypothesis margin is a tight lower bound on the size of adversarial attacks and can be calculated in constant time—this provides the first adversarial robustness certificate calculable in reasonable time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sascha Saralajew; Lars Holdijk; Thomas Villmann; | |
| 1145 | Multi-agent Active Perception With Prediction Rewards Highlight: In this paper, we model multi-agent active perception as a decentralized partially observable Markov decision process (Dec-POMDP) with a convex centralized prediction reward. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mikko Lauri; Frans Oliehoek; | |
| 1146 | A Local Temporal Difference Code For Distributional Reinforcement Learning Highlight: Here, we introduce the Laplace code: a local temporal difference code for distributional reinforcement learning that is representationally powerful and computationally straightforward. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pablo Tano; Peter Dayan; Alexandre Pouget; | |
| 1147 | Learning With Optimized Random Features: Exponential Speedup By Quantum Machine Learning Without Sparsity And Low-Rank Assumptions Highlight: Here, we develop a quantum algorithm for sampling from this optimized distribution over features, in runtime O(D) that is linear in the dimension D of the input data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hayata Yamasaki; Sathyawageeswar Subramanian; Sho Sonoda; Masato Koashi; | |
| 1148 | CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations Highlight: We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Davis Rempe; Tolga Birdal; Yongheng Zhao; Zan Gojcic; Srinath Sridhar; Leonidas J. Guibas; | |
| 1149 | Deep Automodulators Highlight: We introduce a new category of generative autoencoders called automodulators. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ari Heljakka; Yuxin Hou; Juho Kannala; Arno Solin; | |
| 1150 | Convolutional Tensor-Train LSTM For Spatio-Temporal Learning Highlight: In this paper, we propose a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiahao Su; Wonmin Byeon; Jean Kossaifi; Furong Huang; Jan Kautz; Anima Anandkumar; | |
| 1151 | The Potts-Ising Model For Discrete Multivariate Data Highlight: We introduce a variation on the Potts model that allows for general categorical marginals and Ising-type multivariate dependence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zahra Razaee; Arash Amini; | |
| 1152 | Interpretable Multi-timescale Models For Predicting FMRI Responses To Continuous Natural Speech Highlight: In this work we construct interpretable multi-timescale representations by forcing individual units in an LSTM LM to integrate information over specific temporal scales. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shailee Jain; Vy Vo; Shivangi Mahto; Amanda LeBel; Javier S. Turek; Alexander Huth; | |
| 1153 | Group-Fair Online Allocation In Continuous Time Highlight: In order to address these applications, we consider continuous-time online learning problem with fairness considerations, and present a novel framework based on continuous-time utility maximization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Semih Cayci; Swati Gupta; Atilla Eryilmaz; | |
| 1154 | Decentralized TD Tracking With Linear Function Approximation And Its Finite-Time Analysis Highlight: The present contribution deals with decentralized policy evaluation in multi-agent Markov decision processes using temporal-difference (TD) methods with linear function approximation for scalability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gang Wang; Songtao Lu; Georgios Giannakis; Gerald Tesauro; Jian Sun; | |
| 1155 | Understanding Gradient Clipping In Private SGD: A Geometric Perspective Highlight: We first demonstrate how gradient clipping can prevent SGD from converging to a stationary point. We then provide a theoretical analysis on private SGD with gradient clipping. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiangyi Chen; Steven Z. Wu; Mingyi Hong; | |
| 1156 | O(n) Connections Are Expressive Enough: Universal Approximability Of Sparse Transformers Highlight: In this paper, we address these questions and provide a unifying framework that captures existing sparse attention models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chulhee Yun; Yin-Wen Chang; Srinadh Bhojanapalli; Ankit Singh Rawat; Sashank Reddi; Sanjiv Kumar; | |
| 1157 | Identifying Signal And Noise Structure In Neural Population Activity With Gaussian Process Factor Models Highlight: To learn the parameters of our model, we introduce a Fourier-domain black box variational inference method that quickly identifies smooth latent structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stephen Keeley; Mikio Aoi; Yiyi Yu; Spencer Smith; Jonathan W. Pillow; | |
| 1158 | Equivariant Networks For Hierarchical Structures Highlight: More generally, we show that any equivariant map for the hierarchy has this form. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Renhao Wang; Marjan Albooyeh; Siamak Ravanbakhsh; | |
| 1159 | MinMax Methods For Optimal Transport And Beyond: Regularization, Approximation And Numerics Highlight: We study MinMax solution methods for a general class of optimization problems related to (and including) optimal transport. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luca De Gennaro Aquino; Stephan Eckstein; | |
| 1160 | A Discrete Variational Recurrent Topic Model Without The Reparametrization Trick Highlight: We show how to learn a neural topic model with discrete random variables—one that explicitly models each word’s assigned topic—using neural variational inference that does not rely on stochastic backpropagation to handle the discrete variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mehdi Rezaee; Francis Ferraro; | |
| 1161 | Transferable Graph Optimizers For ML Compilers Highlight: To address these limitations, we propose an end-to-end, transferable deep reinforcement learning method for computational graph optimization (GO), based on a scalable sequential attention mechanism over an inductive graph neural network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yanqi Zhou; Sudip Roy; Amirali Abdolrashidi; Daniel Wong; Peter Ma; Qiumin Xu; Hanxiao Liu; Phitchaya Phothilimtha; Shen Wang; Anna Goldie; Azalia Mirhoseini; James Laudon; | |
| 1162 | Learning With Operator-valued Kernels In Reproducing Kernel Krein Spaces Highlight: In this work, we consider operator-valued kernels which might not be necessarily positive definite. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Akash Saha; Balamurugan Palaniappan; | |
| 1163 | Learning Bounds For Risk-sensitive Learning Highlight: In this paper, we propose to study the generalization properties of risk-sensitive learning schemes whose optimand is described via optimized certainty equivalents (OCE): our general scheme can handle various known risks, e.g., the entropic risk, mean-variance, and conditional value-at-risk, as special cases. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jaeho Lee; Sejun Park; Jinwoo Shin; | |
| 1164 | Simplifying Hamiltonian And Lagrangian Neural Networks Via Explicit Constraints Highlight: We introduce a series of challenging chaotic and extended-body systems, including systems with $N$-pendulums, spring coupling, magnetic fields, rigid rotors, and gyroscopes, to push the limits of current approaches. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Marc Finzi; Ke Alexander Wang; Andrew Gordon Wilson; | |
| 1165 | Beyond Accuracy: Quantifying Trial-by-trial Behaviour Of CNNs And Humans By Measuring Error Consistency Highlight: Here we introduce trial-by-trial error consistency, a quantitative analysis for measuring whether two decision making systems systematically make errors on the same inputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Robert Geirhos; Kristof Meding; Felix A. Wichmann; | |
| 1166 | Provably Efficient Reinforcement Learning With Kernel And Neural Function Approximations Highlight: To address such a challenge, focusing on the episodic setting where the action-value functions are represented by a kernel function or over-parametrized neural network, we propose the first provable RL algorithm with both polynomial runtime and sample complexity, without additional assumptions on the data-generating model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhuoran Yang; Chi Jin; Zhaoran Wang; Mengdi Wang; Michael Jordan; | |
| 1167 | Constant-Expansion Suffices For Compressed Sensing With Generative Priors Highlight: Our main contribution is to break this strong expansivity assumption, showing that \emph{constant} expansivity suffices to get efficient recovery algorithms, besides it also being information-theoretically necessary. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Constantinos Daskalakis; Dhruv Rohatgi; Emmanouil Zampetakis; | |
| 1168 | RANet: Region Attention Network For Semantic Segmentation Highlight: In this paper, we introduce the \emph{Region Attention Network} (RANet), a novel attention network for modeling the relationship between object regions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dingguo Shen; Yuanfeng Ji; Ping Li; Yi Wang; Di Lin; | |
| 1169 | A Random Matrix Analysis Of Random Fourier Features: Beyond The Gaussian Kernel, A Precise Phase Transition, And The Corresponding Double Descent Highlight: This article characterizes the exact asymptotics of random Fourier feature (RFF) regression, in the realistic setting where the number of data samples $n$, their dimension $p$, and the dimension of feature space $N$ are all large and comparable. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhenyu Liao; Romain Couillet; Michael W. Mahoney; | |
| 1170 | Learning Sparse Codes From Compressed Representations With Biologically Plausible Local Wiring Constraints Highlight: The main contribution of this paper is to leverage recent results on structured random matrices to propose a theoretical neuroscience model of randomized projections for communication between cortical areas that is consistent with the local wiring constraints observed in neuroanatomy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kion Fallah; Adam Willats; Ninghao Liu; Christopher Rozell; | |
| 1171 | Self-Imitation Learning Via Generalized Lower Bound Q-learning Highlight: In this work, we propose a n-step lower bound which generalizes the original return-based lower-bound Q-learning, and introduce a new family of self-imitation learning algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunhao Tang; | |
| 1172 | Private Learning Of Halfspaces: Simplifying The Construction And Reducing The Sample Complexity Highlight: We present a differentially private learner for halfspaces over a finite grid $G$ in $\R^d$ with sample complexity $\approx d^{2.5}\cdot 2^{\log^*|G|}$, which improves the state-of-the-art result of [Beimel et al., COLT 2019] by a $d^2$ factor. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haim Kaplan; Yishay Mansour; Uri Stemmer; Eliad Tsfadia; | |
| 1173 | Directional Pruning Of Deep Neural Networks Highlight: In the light of the fact that the stochastic gradient descent (SGD) often finds a flat minimum valley in the training loss, we propose a novel directional pruning method which searches for a sparse minimizer in or close to that flat region. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shih-Kang Chao; Zhanyu Wang; Yue Xing; Guang Cheng; | code |
| 1174 | Smoothly Bounding User Contributions In Differential Privacy Highlight: For a better trade-off between utility and privacy guarantee, we propose a method which smoothly bounds user contributions by setting appropriate weights on data points and apply it to estimating the mean/quantiles, linear regression, and empirical risk minimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alessandro Epasto; Mohammad Mahdian; Jieming Mao; Vahab Mirrokni; Lijie Ren; | |
| 1175 | Accelerating Training Of Transformer-Based Language Models With Progressive Layer Dropping Highlight: In this work, we propose a method based on progressive layer dropping that speeds the training of Transformer-based language models, not at the cost of excessive hardware resources but from model architecture change and training technique boosted efficiency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minjia Zhang; Yuxiong He; | |
| 1176 | Online Planning With Lookahead Policies Highlight: In this we devise a multi-step greedy RTDP algorithm, which we call $h$-RTDP, that replaces the 1-step greedy policy with a $h$-step lookahead policy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yonathan Efroni; Mohammad Ghavamzadeh; Shie Mannor; | |
| 1177 | Learning Deep Attribution Priors Based On Prior Knowledge Highlight: Here, we propose the deep attribution prior (DAPr) framework to exploit such information to overcome the limitations of attribution methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ethan Weinberger; Joseph Janizek; Su-In Lee; | |
| 1178 | Using Noise To Probe Recurrent Neural Network Structure And Prune Synapses Highlight: Here we suggest that noise could play a functional role in synaptic pruning, allowing the brain to probe network structure and determine which synapses are redundant. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eli Moore; Rishidev Chaudhuri; | |
| 1179 | NanoFlow: Scalable Normalizing Flows With Sublinear Parameter Complexity Highlight: Hence, we propose an efficient parameter decomposition method and the concept of flow indication embedding, which are key missing components that enable density estimation from a single neural network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sang-gil Lee; Sungwon Kim; Sungroh Yoon; | |
| 1180 | Group Knowledge Transfer: Federated Learning Of Large CNNs At The Edge Highlight: We train CNNs designed based on ResNet-56 and ResNet-110 using three distinct datasets (CIFAR-10, CIFAR-100, and CINIC-10) and their non-IID variants. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaoyang He; Murali Annavaram; Salman Avestimehr; | code |
| 1181 | Neural FFTs For Universal Texture Image Synthesis Highlight: In this work, inspired by the repetitive nature of texture patterns, we find that texture synthesis can be viewed as (local) \textit{upsampling} in the Fast Fourier Transform (FFT) domain. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Morteza Mardani; Guilin Liu; Aysegul Dundar; Shiqiu Liu; Andrew Tao; Bryan Catanzaro; | |
| 1182 | Graph Cross Networks With Vertex Infomax Pooling Highlight: We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maosen Li; Siheng Chen; Ya Zhang; Ivor Tsang; | |
| 1183 | Instance-optimality In Differential Privacy Via Approximate Inverse Sensitivity Mechanisms Highlight: We study and provide instance-optimal algorithms in differential privacy by extending and approximating the inverse sensitivity mechanism. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hilal Asi; John C. Duchi; | |
| 1184 | Calibration Of Shared Equilibria In General Sum Partially Observable Markov Games Highlight: This paper aims at i) formally understanding equilibria reached by such agents, and ii) matching emergent phenomena of such equilibria to real-world targets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nelson Vadori; Sumitra Ganesh; Prashant Reddy; Manuela Veloso; | |
| 1185 | MOPO: Model-based Offline Policy Optimization Highlight: In this paper, we observe that an existing model-based RL algorithm on its own already produces significant gains in the offline setting, as compared to model-free approaches, despite not being designed for this setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianhe Yu; Garrett Thomas; Lantao Yu; Stefano Ermon; James Y. Zou; Sergey Levine; Chelsea Finn; Tengyu Ma; | |
| 1186 | Building Powerful And Equivariant Graph Neural Networks With Structural Message-passing Highlight: We address this problem and propose a powerful and equivariant message-passing framework based on two ideas: first, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cl�ment Vignac; Andreas Loukas; Pascal Frossard; | |
| 1187 | Efficient Model-Based Reinforcement Learning Through Optimistic Policy Search And Planning Highlight: In this paper, we propose a practical optimistic exploration algorithm (H-UCRL). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sebastian Curi; Felix Berkenkamp; Andreas Krause; | |
| 1188 | Practical Low-Rank Communication Compression In Decentralized Deep Learning Highlight: We introduce a simple algorithm that directly compresses the model differences between neighboring workers using low-rank linear compressors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thijs Vogels; Sai Praneeth Karimireddy; Martin Jaggi; | |
| 1189 | Mutual Exclusivity As A Challenge For Deep Neural Networks Highlight: In this paper, we investigate whether or not vanilla neural architectures have an ME bias, demonstrating that they lack this learning assumption. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kanishk Gandhi; Brenden M. Lake; | |
| 1190 | 3D Shape Reconstruction From Vision And Touch Highlight: In this paper, we study this problem and present an effective chart-based approach to multi-modal shape understanding which encourages a similar fusion vision and touch information. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edward Smith; Roberto Calandra; Adriana Romero; Georgia Gkioxari; David Meger; Jitendra Malik; Michal Drozdzal; | |
| 1191 | GradAug: A New Regularization Method For Deep Neural Networks Highlight: We propose a new regularization method to alleviate over-fitting in deep neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
TAOJIANNAN YANG; Sijie Zhu; Chen Chen; | code |
| 1192 | An Equivalence Between Loss Functions And Non-Uniform Sampling In Experience Replay Highlight: We show that any loss function evaluated with non-uniformly sampled data can be transformed into another uniformly sampled loss function with the same expected gradient. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Scott Fujimoto; David Meger; Doina Precup; | |
| 1193 | Learning Utilities And Equilibria In Non-Truthful Auctions Highlight: We give almost matching (up to polylog factors) lower bound on the sample complexity for learning utilities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hu Fu; Tao Lin; | |
| 1194 | Rational Neural Networks Highlight: We consider neural networks with rational activation functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicolas Boulle; Yuji Nakatsukasa; Alex Townsend; | |
| 1195 | DISK: Learning Local Features With Policy Gradient Highlight: We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveraging principles from Reinforcement Learning (RL), optimizing end-to-end for a high number of correct feature matches. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michal Tyszkiewicz; Pascal Fua; Eduard Trulls; | |
| 1196 | Transfer Learning Via $\ell_1$ Regularization Highlight: We propose a method for transferring knowledge from a source domain to a target domain via $\ell_1$ regularization in high dimension. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Masaaki Takada; Hironori Fujisawa; | |
| 1197 | GOCor: Bringing Globally Optimized Correspondence Volumes Into Your Neural Network Highlight: We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Prune Truong; Martin Danelljan; Luc V. Gool; Radu Timofte; | |
| 1198 | Deep Inverse Q-learning With Constraints Highlight: In this work, we introduce a novel class of algorithms that only needs to solve the MDP underlying the demonstrated behavior once to recover the expert policy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gabriel Kalweit; Maria Huegle; Moritz Werling; Joschka Boedecker; | |
| 1199 | Optimistic Dual Extrapolation For Coherent Non-monotone Variational Inequalities Highlight: In this paper, we propose {\em optimistic dual extrapolation (OptDE)}, a method that only performs {\em one} gradient evaluation per iteration. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaobing Song; Zhengyuan Zhou; Yichao Zhou; Yong Jiang; Yi Ma; | |
| 1200 | Prediction With Corrupted Expert Advice Highlight: We revisit the fundamental problem of prediction with expert advice, in a setting where the environment is benign and generates losses stochastically, but the feedback observed by the learner is subject to a moderate adversarial corruption. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Idan Amir; Idan Attias; Tomer Koren; Yishay Mansour; Roi Livni; | |
| 1201 | Human Parsing Based Texture Transfer From Single Image To 3D Human Via Cross-View Consistency Highlight: This paper proposes a human parsing based texture transfer model via cross-view consistency learning to generate the texture of 3D human body from a single image. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fang Zhao; Shengcai Liao; Kaihao Zhang; Ling Shao; | |
| 1202 | Knowledge Augmented Deep Neural Networks For Joint Facial Expression And Action Unit Recognition Highlight: This paper proposes to systematically capture their dependencies and incorporate them into a deep learning framework for joint facial expression recognition and action unit detection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zijun Cui; Tengfei Song; Yuru Wang; Qiang Ji; | |
| 1203 | Point Process Models For Sequence Detection In High-dimensional Neural Spike Trains Highlight: We address each of these shortcomings by developing a point process model that characterizes fine-scale sequences at the level of individual spikes and represents sequence occurrences as a small number of marked events in continuous time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Williams; Anthony Degleris; Yixin Wang; Scott Linderman; | |
| 1204 | Adversarial Attacks On Linear Contextual Bandits Highlight: In this paper, we study several attack scenarios and show that a malicious agent can force a linear contextual bandit algorithm to pull any desired arm T ? o(T) times over a horizon of T steps, while applying adversarial modifications to either rewards or contexts with a cumulative cost that only grow logarithmically as O(log T). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Evrard Garcelon; Baptiste Roziere; Laurent Meunier; Jean Tarbouriech; Olivier Teytaud; Alessandro Lazaric; Matteo Pirotta; | |
| 1205 | Meta-Consolidation For Continual Learning Highlight: In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joseph K J; Vineeth Nallure Balasubramanian; | |
| 1206 | Organizing Recurrent Network Dynamics By Task-computation To Enable Continual Learning Highlight: Here, we develop a novel learning rule designed to minimize interference between sequentially learned tasks in recurrent networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lea Duncker; Laura Driscoll; Krishna V. Shenoy; Maneesh Sahani; David Sussillo; | |
| 1207 | Lifelong Policy Gradient Learning Of Factored Policies For Faster Training Without Forgetting Highlight: We provide a novel method for lifelong policy gradient learning that trains lifelong function approximators directly via policy gradients, allowing the agent to benefit from accumulated knowledge throughout the entire training process. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jorge Mendez; Boyu Wang; Eric Eaton; | |
| 1208 | Kernel Methods Through The Roof: Handling Billions Of Points Efficiently Highlight: Towards this end, we designed a preconditioned gradient solver for kernel methods exploiting both GPU acceleration and parallelization with multiple GPUs, implementing out-of-core variants of common linear algebra operations to guarantee optimal hardware utilization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Giacomo Meanti; Luigi Carratino; Lorenzo Rosasco; Alessandro Rudi; | |
| 1209 | Spike And Slab Variational Bayes For High Dimensional Logistic Regression Highlight: We study a mean-field spike and slab VB approximation of widely used Bayesian model selection priors in sparse high-dimensional logistic regression. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kolyan Ray; Botond Szabo; Gabriel Clara; | |
| 1210 | Maximum-Entropy Adversarial Data Augmentation For Improved Generalization And Robustness Highlight: In this paper, we propose a novel and effective regularization term for adversarial data augmentation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Long Zhao; Ting Liu; Xi Peng; Dimitris Metaxas; | |
| 1211 | Fast Geometric Learning With Symbolic Matrices Highlight: We present an extension for standard machine learning frameworks that provides comprehensive support for this abstraction on CPUs and GPUs: our toolbox combines a versatile, transparent user interface with fast runtimes and low memory usage. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jean Feydy; Joan Glaun�s; Benjamin Charlier; Michael Bronstein; | |
| 1212 | MESA: Boost Ensemble Imbalanced Learning With MEta-SAmpler Highlight: In this paper, we introduce a novel ensemble IL framework named MESA. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhining Liu; Pengfei Wei; Jing Jiang; Wei Cao; Jiang Bian; Yi Chang; | code |
| 1213 | CoinPress: Practical Private Mean And Covariance Estimation Highlight: We present simple differentially private estimators for the parameters of multivariate sub-Gaussian data that are accurate at small sample sizes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sourav Biswas; Yihe Dong; Gautam Kamath; Jonathan Ullman; | |
| 1214 | Planning With General Objective Functions: Going Beyond Total Rewards Highlight: In this paper, based on techniques in sketching algorithms, we propose a novel planning algorithm in deterministic systems which deals with a large class of objective functions of the form $f(r_1, r_2, … r_H)$ that are of interest to practical applications. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruosong Wang; Peilin Zhong; Simon S. Du; Russ R. Salakhutdinov; Lin Yang; | |
| 1215 | Scattering GCN: Overcoming Oversmoothness In Graph Convolutional Networks Highlight: Here, we propose to augment conventional GCNs with geometric scattering transforms and residual convolutions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yimeng Min; Frederik Wenkel; Guy Wolf; | |
| 1216 | KFC: A Scalable Approximation Algorithm For $k$-center Fair Clustering Highlight: In this paper, we study the problem of fair clustering on the $k-$center objective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Elfarouk Harb; Ho Shan Lam; | |
| 1217 | Leveraging Predictions In Smoothed Online Convex Optimization Via Gradient-based Algorithms Highlight: To address this question, we introduce a gradient-based online algorithm, Receding Horizon Inexact Gradient (RHIG), and analyze its performance by dynamic regrets in terms of the temporal variation of the environment and the prediction errors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingying Li; Na Li; | |
| 1218 | Learning The Linear Quadratic Regulator From Nonlinear Observations Highlight: We introduce a new algorithm, RichID, which learns a near-optimal policy for the RichLQR with sample complexity scaling only with the dimension of the latent state space and the capacity of the decoder function class. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zakaria Mhammedi; Dylan J. Foster; Max Simchowitz; Dipendra Misra; Wen Sun; Akshay Krishnamurthy; Alexander Rakhlin; John Langford; | |
| 1219 | Reconciling Modern Deep Learning With Traditional Optimization Analyses: The Intrinsic Learning Rate Highlight: The current paper highlights other ways in which behavior of normalized nets departs from traditional viewpoints, and then initiates a formal framework for studying their mathematics via suitable adaptation of the conventional framework namely, modeling SGD-induced training trajectory via a suitable stochastic differential equation (SDE) with a noise term that captures gradient noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhiyuan Li; Kaifeng Lyu; Sanjeev Arora; | |
| 1220 | Scalable Graph Neural Networks Via Bidirectional Propagation Highlight: In this paper, we present GBP, a scalable GNN that utilizes a localized bidirectional propagation process from both the feature vector and the training/testing nodes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ming Chen; Zhewei Wei; Bolin Ding; Yaliang Li; Ye Yuan; Xiaoyong Du; Ji-Rong Wen; | |
| 1221 | Distribution Aligning Refinery Of Pseudo-label For Imbalanced Semi-supervised Learning Highlight: To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from the biased model, and develop a simple algorithm, named Distribution Aligning Refinery of Pseudo-label (DARP) that solves it provably and efficiently. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jaehyung Kim; Youngbum Hur; Sejun Park; Eunho Yang; Sung Ju Hwang; Jinwoo Shin; | |
| 1222 | Assisted Learning: A Framework For Multi-Organization Learning Highlight: In this work, we introduce the Assisted Learning framework for organizations to assist each other in supervised learning tasks without revealing any organization’s algorithm, data, or even task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xun Xian; Xinran Wang; Jie Ding; Reza Ghanadan; | |
| 1223 | The Strong Screening Rule For SLOPE Highlight: We develop a screening rule for SLOPE by examining its subdifferential and show that this rule is a generalization of the strong rule for the lasso. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Johan Larsson; Malgorzata Bogdan; Jonas Wallin; | |
| 1224 | STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks Highlight: In this paper, we develop a new temporal logic-based learning framework, STLnet, which guides the RNN learning process with auxiliary knowledge of model properties, and produces a more robust model for improved future predictions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Meiyi Ma; Ji Gao; Lu Feng; John Stankovic; | |
| 1225 | Election Coding For Distributed Learning: Protecting SignSGD Against Byzantine Attacks Highlight: This paper proposes Election Coding, a coding-theoretic framework to guarantee Byzantine-robustness for distributed learning algorithms based on signed stochastic gradient descent (SignSGD) that minimizes the worker-master communication load. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jy-yong Sohn; Dong-Jun Han; Beongjun Choi; Jaekyun Moon; | |
| 1226 | Reducing Adversarially Robust Learning To Non-Robust PAC Learning Highlight: We study the problem of reducing adversarially robust learning to standard PAC learning, i.e. the complexity of learning adversarially robust predictors using access to only a black-box non-robust learner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Omar Montasser; Steve Hanneke; Nati Srebro; | |
| 1227 | Top-k Training Of GANs: Improving GAN Performance By Throwing Away Bad Samples Highlight: We introduce a simple (one line of code) modification to the Generative Adversarial Network (GAN) training algorithm that materially improves results with no increase in computational cost. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Samarth Sinha; Zhengli Zhao; Anirudh Goyal ALIAS PARTH GOYAL; Colin A. Raffel; Augustus Odena; | |
| 1228 | Black-Box Optimization With Local Generative Surrogates Highlight: We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sergey Shirobokov; Vladislav Belavin; Michael Kagan; Andrei Ustyuzhanin; Atilim Gunes Baydin; | |
| 1229 | Efficient Generation Of Structured Objects With Constrained Adversarial Networks Highlight: As a remedy, we propose Constrained Adversarial Networks (CANs), an extension of GANs in which the constraints are embedded into the model during training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luca Di Liello; Pierfrancesco Ardino; Jacopo Gobbi; Paolo Morettin; Stefano Teso; Andrea Passerini; | |
| 1230 | Hard Example Generation By Texture Synthesis For Cross-domain Shape Similarity Learning Highlight: In the paper, we identify the source of the poor performance and propose a practical solution to this problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huan Fu; Shunming Li; Rongfei Jia; Mingming Gong; Binqiang Zhao; Dacheng Tao; | code |
| 1231 | Recovery Of Sparse Linear Classifiers From Mixture Of Responses Highlight: We look at a hitherto unstudied problem of query complexity upper bound of recovering all the hyperplanes, especially for the case when the hyperplanes are sparse. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Venkata Gandikota; Arya Mazumdar; Soumyabrata Pal; | |
| 1232 | Efficient Distance Approximation For Structured High-Dimensional Distributions Via Learning Highlight: Specifically, we present algorithms for the following problems (where dTV is the total variation distance): Given sample access to two Bayesian networks P1 and P2 over known directed acyclic graphs G1 and G2 having n nodes and bounded in-degree, approximate dTV(P1, P2) to within additive error ? using poly(n, 1/?) samples and time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arnab Bhattacharyya; Sutanu Gayen; Kuldeep S Meel; N. V. Vinodchandran; | |
| 1233 | A Single Recipe For Online Submodular Maximization With Adversarial Or Stochastic Constraints Highlight: In this paper, we consider an online optimization problem in which the reward functions are DR-submodular, and in addition to maximizing the total reward, the sequence of decisions must satisfy some convex constraints on average. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Omid Sadeghi; Prasanna Raut; Maryam Fazel; | |
| 1234 | Learning Sparse Prototypes For Text Generation Highlight: In this paper, we propose a novel generative model that automatically learns a sparse prototype support set that, nonetheless, achieves strong language modeling performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junxian He; Taylor Berg-Kirkpatrick; Graham Neubig; | |
| 1235 | Implicit Rank-Minimizing Autoencoder Highlight: In this work, the rank of the covariance matrix of the codes is implicitly minimized by relying on the fact that gradient descent learning in multi-layer linear networks leads to minimum-rank solutions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Li Jing; Jure Zbontar; yann lecun; | |
| 1236 | Storage Efficient And Dynamic Flexible Runtime Channel Pruning Via Deep Reinforcement Learning Highlight: In this paper, we propose a deep reinforcement learning (DRL) based framework to efficiently perform runtime channel pruning on convolutional neural networks (CNNs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianda Chen; Shangyu Chen; Sinno Jialin Pan; | |
| 1237 | Task-Oriented Feature Distillation Highlight: In this paper, we propose a novel distillation method named task-oriented feature distillation (TOFD) where the transformation is convolutional layers that are trained in a data-driven manner by task loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Linfeng Zhang; Yukang Shi; Zuoqiang Shi; Kaisheng Ma; Chenglong Bao; | |
| 1238 | Entropic Causal Inference: Identifiability And Finite Sample Results Highlight: In this paper, we prove a variant of their conjecture. Namely, we show that for almost all causal models where the exogenous variable has entropy that does not scale with the number of states of the observed variables, the causal direction is identifiable from observational data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Spencer Compton; Murat Kocaoglu; Kristjan Greenewald; Dmitriy Katz; | |
| 1239 | Rewriting History With Inverse RL: Hindsight Inference For Policy Improvement Highlight: In this paper we show that inverse RL is a principled mechanism for reusing experience across tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ben Eysenbach; XINYANG GENG; Sergey Levine; Russ R. Salakhutdinov; | |
| 1240 | Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis Highlight: In this work, we develop a variance reduction scheme for the two time-scale TDC algorithm in the off-policy setting and analyze its non-asymptotic convergence rate over both i.i.d.\ and Markovian samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shaocong Ma; Yi Zhou; Shaofeng Zou; | |
| 1241 | AdaTune: Adaptive Tensor Program Compilation Made Efficient Highlight: In this paper, we present a new method, called AdaTune, that significantly reduces the optimization time of tensor programs for high-performance deep learning inference. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Menghao Li; Minjia Zhang; Chi Wang; Mingqin Li; | |
| 1242 | When Do Neural Networks Outperform Kernel Methods? Highlight: Building on these results, we present the spiked covariates model that can capture in a unified framework both behaviors observed in earlier works. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Behrooz Ghorbani; Song Mei; Theodor Misiakiewicz; Andrea Montanari; | |
| 1243 | STEER : Simple Temporal Regularization For Neural ODE Highlight: In this paper we propose a new regularization technique: randomly sampling the end time of the ODE during training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arnab Ghosh; Harkirat Behl; Emilien Dupont; Philip Torr; Vinay Namboodiri; | |
| 1244 | A Variational Approach For Learning From Positive And Unlabeled Data Highlight: In this paper, we introduce a variational principle for PU learning that allows us to quantitatively evaluate the modeling error of the Bayesian classi?er directly from given data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hui Chen; Fangqing Liu; Yin Wang; Liyue Zhao; Hao Wu; | |
| 1245 | Efficient Clustering Based On A Unified View Of $K$-means And Ratio-cut Highlight: Firstly, a unified framework of k-means and ratio-cut is revisited, and a novel and efficient clustering algorithm is then proposed based on this framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shenfei Pei; Feiping Nie; Rong Wang; Xuelong Li; | |
| 1246 | Recurrent Switching Dynamical Systems Models For Multiple Interacting Neural Populations Highlight: To tackle this challenge, we develop recurrent switching linear dynamical systems models for multiple populations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joshua Glaser; Matthew Whiteway; John P. Cunningham; Liam Paninski; Scott Linderman; | |
| 1247 | Coresets Via Bilevel Optimization For Continual Learning And Streaming Highlight: In this work, we propose a novel coreset construction via cardinality-constrained bilevel optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zal�n Borsos; Mojmir Mutny; Andreas Krause; | |
| 1248 | Generalized Independent Noise Condition For Estimating Latent Variable Causal Graphs Highlight: To this end, in this paper, we consider Linear, Non-Gaussian Latent variable Models (LiNGLaMs), in which latent confounders are also causally related, and propose a Generalized Independent Noise (GIN) condition to estimate such latent variable graphs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Feng Xie; Ruichu Cai; Biwei Huang; Clark Glymour; Zhifeng Hao; Kun Zhang; | |
| 1249 | Understanding And Exploring The Network With Stochastic Architectures Highlight: In this work, we decouple the training of a network with stochastic architectures (NSA) from NAS and provide a first systematical investigation on it as a stand-alone problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhijie Deng; Yinpeng Dong; Shifeng Zhang; Jun Zhu; | |
| 1250 | All-or-nothing Statistical And Computational Phase Transitions In Sparse Spiked Matrix Estimation Highlight: We prove explicit low-dimensional variational formulas for the asymptotic mutual information between the spike and the observed noisy matrix and analyze the approximate message passing algorithm in the sparse regime. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
jean barbier; Nicolas Macris; Cynthia Rush; | |
| 1251 | Deep Evidential Regression Highlight: In this paper, we propose a novel method for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order to learn both aleatoric and epistemic uncertainty. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Amini; Wilko Schwarting; Ava Soleimany; Daniela Rus; | |
| 1252 | Analytical Probability Distributions And Exact Expectation-Maximization For Deep Generative Networks Highlight: We exploit the Continuous Piecewise Affine property of modern DGNs to derive their posterior and marginal distributions as well as the latter’s first two moments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Randall Balestriero; Sebastien PARIS; Richard Baraniuk; | |
| 1253 | Bayesian Pseudocoresets Highlight: We address both of these issues with a single unified solution, Bayesian pseudocoresets — a small weighted collection of synthetic "pseudodata"—along with a variational optimization method to select both pseudodata and weights. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dionysis Manousakas; Zuheng Xu; Cecilia Mascolo; Trevor Campbell; | |
| 1254 | See, Hear, Explore: Curiosity Via Audio-Visual Association Highlight: In this paper, we introduce an alternative form of curiosity that rewards novel associations between different senses. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Victoria Dean; Shubham Tulsiani; Abhinav Gupta; | code |
| 1255 | Adversarial Training Is A Form Of Data-dependent Operator Norm Regularization Highlight: We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kevin Roth; Yannic Kilcher; Thomas Hofmann; | |
| 1256 | A Biologically Plausible Neural Network For Slow Feature Analysis Highlight: In this work, starting from an SFA objective, we derive an SFA algorithm, called Bio-SFA, with a biologically plausible neural network implementation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Lipshutz; Charles Windolf; Siavash Golkar; Dmitri Chklovskii; | |
| 1257 | Learning Feature Sparse Principal Subspace Highlight: This paper presents new algorithms to solve the feature-sparsity constrained PCA problem (FSPCA), which performs feature selection and PCA simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lai Tian; Feiping Nie; Rong Wang; Xuelong Li; | |
| 1258 | Online Adaptation For Consistent Mesh Reconstruction In The Wild Highlight: This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xueting Li; Sifei Liu; Shalini De Mello; Kihwan Kim; Xiaolong Wang; Ming-Hsuan Yang; Jan Kautz; | |
| 1259 | Online Learning With Dynamics: A Minimax Perspective Highlight: We consider the problem of online learning with dynamics, where a learner interacts with a stateful environment over multiple rounds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kush Bhatia; Karthik Sridharan; | |
| 1260 | Learning To Select Best Forecast Tasks For Clinical Outcome Prediction Highlight: To address this challenge, we propose a method to automatically select from a large set of auxiliary tasks which yield a representation most useful to the target task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuan Xue; Nan Du; Anne Mottram; Martin Seneviratne; Andrew M. Dai; | |
| 1261 | Stochastic Optimization With Heavy-Tailed Noise Via Accelerated Gradient Clipping Highlight: In this paper, we propose a new accelerated stochastic first-order method called clipped-SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in stochastic gradients and derive the first high-probability complexity bounds for this method closing the gap in the theory of stochastic optimization with heavy-tailed noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eduard Gorbunov; Marina Danilova; Alexander Gasnikov; | |
| 1262 | Adaptive Experimental Design With Temporal Interference: A Maximum Likelihood Approach Highlight: Remarkably, in our setting, using a novel application of classical martingale analysis of Markov chains via Poisson’s equation, we characterize efficient designs via a succinct convex optimization problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peter W. Glynn; Ramesh Johari; Mohammad Rasouli; | |
| 1263 | From Trees To Continuous Embeddings And Back: Hyperbolic Hierarchical Clustering Highlight: In this work, we provide the first continuous relaxation of Dasgupta’s discrete optimization problem with provable quality guarantees. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ines Chami; Albert Gu; Vaggos Chatziafratis; Christopher R�; | |
| 1264 | The Autoencoding Variational Autoencoder Highlight: Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No’; a (nominally trained) VAE does not necessarily amortize inference for typical samples that it is capable of generating. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Taylan Cemgil; Sumedh Ghaisas; Krishnamurthy Dvijotham; Sven Gowal; Pushmeet Kohli; | |
| 1265 | A Fair Classifier Using Kernel Density Estimation Highlight: In this work, we develop a kernel density estimation trick to quantify fairness measures that capture the degree of the irrelevancy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jaewoong Cho; Gyeongjo Hwang; Changho Suh; | |
| 1266 | A Randomized Algorithm To Reduce The Support Of Discrete Measures Highlight: We give a simple geometric characterization of barycenters via negative cones and derive a randomized algorithm that computes this new measure by “greedy geometric sampling”. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Francesco Cosentino; Harald Oberhauser; Alessandro Abate; | code |
| 1267 | Distributionally Robust Federated Averaging Highlight: In this paper, we study communication efficient distributed algorithms for distributionally robust federated learning via periodic averaging with adaptive sampling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuyang Deng; Mohammad Mahdi Kamani; Mehrdad Mahdavi; | |
| 1268 | Sharp Uniform Convergence Bounds Through Empirical Centralization Highlight: We introduce the use of empirical centralization to derive novel practical, probabilistic, sample-dependent bounds to the Supremum Deviation (SD) of empirical means of functions in a family from their expectations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cyrus Cousins; Matteo Riondato; | |
| 1269 | COBE: Contextualized Object Embeddings From Narrated Instructional Video Highlight: Instead of relying on manually-labeled data for this task, we propose a new framework for learning Contextualized OBject Embeddings (COBE) from automatically-transcribed narrations of instructional videos. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gedas Bertasius; Lorenzo Torresani; | |
| 1270 | Knowledge Transfer In Multi-Task Deep Reinforcement Learning For Continuous Control Highlight: In this paper, we present a Knowledge Transfer based Multi-task Deep Reinforcement Learning framework (KTM-DRL) for continuous control, which enables a single DRL agent to achieve expert-level performance in multiple different tasks by learning from task-specific teachers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhiyuan Xu; Kun Wu; Zhengping Che; Jian Tang; Jieping Ye; | |
| 1271 | Finite Versus Infinite Neural Networks: An Empirical Study Highlight: We perform a careful, thorough, and large scale empirical study of the correspondence between wide neural networks and kernel methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jaehoon Lee; Samuel Schoenholz; Jeffrey Pennington; Ben Adlam; Lechao Xiao; Roman Novak; Jascha Sohl-Dickstein; | |
| 1272 | Supermasks In Superposition Highlight: We present the Supermasks in Superposition (SupSup) model, capable of sequentially learning thousands of tasks without catastrophic forgetting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mitchell Wortsman; Vivek Ramanujan; Rosanne Liu; Aniruddha Kembhavi; Mohammad Rastegari; Jason Yosinski; Ali Farhadi; | |
| 1273 | Nonasymptotic Guarantees For Spiked Matrix Recovery With Generative Priors Highlight: In this work, we study an alternative prior where the low-rank component is in the range of a trained generative network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jorio Cocola; Paul Hand; Vlad Voroninski; | |
| 1274 | Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition Highlight: We propose a model-free algorithm UCB-ADVANTAGE and prove that it achieves \tilde{O}(\sqrt{H^2 SAT}) regret where T=KH and K is the number of episodes to play. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zihan Zhang; Yuan Zhou; Xiangyang Ji; | |
| 1275 | Learning To Incentivize Other Learning Agents Highlight: Observing that humans often provide incentives to influence others’ behavior, we propose to equip each RL agent in a multi-agent environment with the ability to give rewards directly to other agents, using a learned incentive function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiachen Yang; Ang Li; Mehrdad Farajtabar; Peter Sunehag; Edward Hughes; Hongyuan Zha; | |
| 1276 | Displacement-Invariant Matching Cost Learning For Accurate Optical Flow Estimation Highlight: This paper proposes a novel solution that is able to bypass the requirement of building a 5D feature volume while still allowing the network to learn suitable matching costs from data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianyuan Wang; Yiran Zhong; Yuchao Dai; Kaihao Zhang; Pan Ji; Hongdong Li; | code |
| 1277 | Distributionally Robust Local Non-parametric Conditional Estimation Highlight: To alleviate these issues, we propose a new distributionally robust estimator that generates non-parametric local estimates by minimizing the worst-case conditional expected loss over all adversarial distributions in a Wasserstein ambiguity set. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Viet Anh Nguyen; Fan Zhang; Jose Blanchet; Erick Delage; Yinyu Ye; | |
| 1278 | Robust Multi-Object Matching Via Iterative Reweighting Of The Graph Connection Laplacian Highlight: We propose an efficient and robust iterative solution to the multi-object matching problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunpeng Shi; Shaohan Li; Gilad Lerman; | |
| 1279 | Meta-Gradient Reinforcement Learning With An Objective Discovered Online Highlight: In this work, we propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network, solely from interactive experience with its environment. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhongwen Xu; Hado P. van Hasselt; Matteo Hessel; Junhyuk Oh; Satinder Singh; David Silver; | |
| 1280 | Learning Strategy-Aware Linear Classifiers Highlight: We address the question of repeatedly learning linear classifiers against agents who are \emph{strategically} trying to \emph{game} the deployed classifiers, and we use the \emph{Stackelberg regret} to measure the performance of our algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yiling Chen; Yang Liu; Chara Podimata; | |
| 1281 | Upper Confidence Primal-Dual Reinforcement Learning For CMDP With Adversarial Loss Highlight: In this work, we propose a new \emph{upper confidence primal-dual} algorithm, which only requires the trajectories sampled from the transition model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuang Qiu; Xiaohan Wei; Zhuoran Yang; Jieping Ye; Zhaoran Wang; | |
| 1282 | Calibrating Deep Neural Networks Using Focal Loss Highlight: We provide a thorough analysis of the factors causing miscalibration, and use the insights we glean from this to justify the empirically excellent performance of focal loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jishnu Mukhoti; Viveka Kulharia; Amartya Sanyal; Stuart Golodetz; Philip Torr; Puneet Dokania; | code |
| 1283 | Optimizing Mode Connectivity Via Neuron Alignment Highlight: We propose a more general framework to investigate the effect of symmetry on landscape connectivity by accounting for the weight permutations of the networks being connected. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Norman Tatro; Pin-Yu Chen; Payel Das; Igor Melnyk; Prasanna Sattigeri; Rongjie Lai; | |
| 1284 | Information Theoretic Regret Bounds For Online Nonlinear Control Highlight: This work studies the problem of sequential control in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known Reproducing Kernel Hilbert Space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sham Kakade; Akshay Krishnamurthy; Kendall Lowrey; Motoya Ohnishi; Wen Sun; | |
| 1285 | A Kernel Test For Quasi-independence Highlight: In this paper, we propose a nonparametric statistical test of quasi-independence. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tamara Fernandez; Wenkai Xu; Marc Ditzhaus; Arthur Gretton; | |
| 1286 | First Order Constrained Optimization In Policy Space Highlight: We propose a novel approach called First Order Constrained Optimization in Policy Space (FOCOPS) which maximizes an agent’s overall reward while ensuring the agent satisfies a set of cost constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yiming Zhang; Quan Vuong; Keith Ross; | |
| 1287 | Learning Augmented Energy Minimization Via Speed Scaling Highlight: Inspired by recent work on learning-augmented online algorithms, we propose an algorithm which incorporates predictions in a black-box manner and outperforms any online algorithm if the accuracy is high, yet maintains provable guarantees if the prediction is very inaccurate. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Etienne Bamas; Andreas Maggiori; Lars Rohwedder; Ola Svensson; | |
| 1288 | Exploiting MMD And Sinkhorn Divergences For Fair And Transferable Representation Learning Highlight: In this work we measure fairness according to demographic parity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luca Oneto; Michele Donini; Giulia Luise; Carlo Ciliberto; Andreas Maurer; Massimiliano Pontil; | |
| 1289 | Deep Rao-Blackwellised Particle Filters For Time Series Forecasting Highlight: We propose a Monte Carlo objective that leverages the conditional linearity by computing the corresponding conditional expectations in closed-form and a suitable proposal distribution that is factorised similarly to the optimal proposal distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Richard Kurle; Syama Sundar Rangapuram; Emmanuel de B�zenac; Stephan G�nnemann; Jan Gasthaus; | |
| 1290 | Why Are Adaptive Methods Good For Attention Models? Highlight: In this paper, we provide empirical and theoretical evidence that a heavy-tailed distribution of the noise in stochastic gradients is one cause of SGD’s poor performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jingzhao Zhang; Sai Praneeth Karimireddy; Andreas Veit; Seungyeon Kim; Sashank Reddi; Sanjiv Kumar; Suvrit Sra; | |
| 1291 | Neural Sparse Representation For Image Restoration Highlight: Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuchen Fan; Jiahui Yu; Yiqun Mei; Yulun Zhang; Yun Fu; Ding Liu; Thomas S. Huang; | |
| 1292 | Boosting First-Order Methods By Shifting Objective: New Schemes With Faster Worst-Case Rates Highlight: We propose a new methodology to design first-order methods for unconstrained strongly convex problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaiwen Zhou; Anthony Man-Cho So; James Cheng; | |
| 1293 | Robust Sequence Submodular Maximization Highlight: In this paper, we study a new problem of robust sequence submodular maximization with cardinality constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gamal Sallam; Zizhan Zheng; Jie Wu; Bo Ji; | |
| 1294 | Certified Monotonic Neural Networks Highlight: In this work, we propose to certify the monotonicity of the general piece-wise linear neural networks by solving a mixed integer linear programming problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xingchao Liu; Xing Han; Na Zhang; Qiang Liu; | |
| 1295 | System Identification With Biophysical Constraints: A Circuit Model Of The Inner Retina Highlight: Here, we present a computational model of temporal processing in the inner retina, including inhibitory feedback circuits and realistic synaptic release mechanisms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cornelius Schr�der; David Klindt; Sarah Strauss; Katrin Franke; Matthias Bethge; Thomas Euler; Philipp Berens; | |
| 1296 | Efficient Algorithms For Device Placement Of DNN Graph Operators Highlight: In this paper, we identify and isolate the structured optimization problem at the core of device placement of DNN operators, for both inference and training, especially in modern pipelined settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jakub M. Tarnawski; Amar Phanishayee; Nikhil Devanur; Divya Mahajan; Fanny Nina Paravecino; | |
| 1297 | Active Invariant Causal Prediction: Experiment Selection Through Stability Highlight: In this work we propose a new active learning (i.e. experiment selection) framework (A-ICP) based on Invariant Causal Prediction (ICP) (Peters et al. 2016). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Juan Gamella; Christina Heinze-Deml; | |
| 1298 | BOSS: Bayesian Optimization Over String Spaces Highlight: This article develops a Bayesian optimization (BO) method which acts directly over raw strings, proposing the first uses of string kernels and genetic algorithms within BO loops. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Henry Moss; David Leslie; Daniel Beck; Javier Gonzalez; Paul Rayson; | |
| 1299 | Model Interpretability Through The Lens Of Computational Complexity Highlight: We make a step towards such a theory by studying whether folklore interpretability claims have a correlate in terms of computational complexity theory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pablo Barcel�; Mika�l Monet; Jorge P�rez; Bernardo Subercaseaux; | |
| 1300 | Markovian Score Climbing: Variational Inference With KL(p||q) Highlight: This paper develops a simple algorithm for reliably minimizing the inclusive KL using stochastic gradients with vanishing bias. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christian Naesseth; Fredrik Lindsten; David Blei; | |
| 1301 | Improved Analysis Of Clipping Algorithms For Non-convex Optimization Highlight: In this paper, we bridge the gap by presenting a general framework to study the clipping algorithms, which also takes momentum methods into consideration. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bohang Zhang; Jikai Jin; Cong Fang; Liwei Wang; | |
| 1302 | Bias No More: High-probability Data-dependent Regret Bounds For Adversarial Bandits And MDPs Highlight: We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chung-Wei Lee; Haipeng Luo; Chen-Yu Wei; Mengxiao Zhang; | |
| 1303 | A Ranking-based, Balanced Loss Function Unifying Classification And Localisation In Object Detection Highlight: We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kemal Oksuz; Baris Can Cam; Emre Akbas; Sinan Kalkan; | code |
| 1304 | StratLearner: Learning A Strategy For Misinformation Prevention In Social Networks Highlight: In this paper, we consider such a setting and study the misinformation prevention problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guangmo Tong; | |
| 1305 | A Unified Switching System Perspective And Convergence Analysis Of Q-Learning Algorithms Highlight: This paper develops a novel and unified framework to analyze the convergence of a large family of Q-learning algorithms from the switching system perspective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Donghwan Lee; Niao He; | |
| 1306 | Kernel Alignment Risk Estimator: Risk Prediction From Training Data Highlight: We study the risk (i.e. generalization error) of Kernel Ridge Regression (KRR) for a kernel K with ridge ?>0 and i.i.d. observations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arthur Jacot; Berfin Simsek; Francesco Spadaro; Clement Hongler; Franck Gabriel; | |
| 1307 | Calibrating CNNs For Lifelong Learning Highlight: We present an approach for lifelong/continual learning of convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when moving from one task to the other. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pravendra Singh; Vinay Kumar Verma; Pratik Mazumder; Lawrence Carin; Piyush Rai; | |
| 1308 | Online Convex Optimization Over Erdos-Renyi Random Networks Highlight: The work studies how node-to-node communications over an Erd\H{o}s-R\’enyi random network influence distributed online convex optimization, which is vital in solving large-scale machine learning in antagonistic or changing environments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jinlong Lei; Peng Yi; Yiguang Hong; Jie Chen; Guodong Shi; | |
| 1309 | Robustness Of Bayesian Neural Networks To Gradient-Based Attacks Highlight: In this paper, we analyse the geometry of adversarial attacks in the large-data, overparametrized limit for Bayesian Neural Networks (BNNs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ginevra Carbone; Matthew Wicker; Luca Laurenti; Andrea Patane'; Luca Bortolussi; Guido Sanguinetti; | |
| 1310 | Parametric Instance Classification For Unsupervised Visual Feature Learning Highlight: This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yue Cao; Zhenda Xie; Bin Liu; Yutong Lin; Zheng Zhang; Han Hu; | code |
| 1311 | Sparse Weight Activation Training Highlight: In this work, we propose a novel CNN training algorithm called Sparse Weight Activation Training (SWAT). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Md Aamir Raihan; Tor Aamodt; | code |
| 1312 | Collapsing Bandits And Their Application To Public Health Intervention Highlight: We propose and study Collapsing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when an arm is played, the state is fully observed, thus“collapsing” any uncertainty, but when an arm is passive, no observation is made, thus allowing uncertainty to evolve. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aditya Mate; Jackson Killian; Haifeng Xu; Andrew Perrault; Milind Tambe; | code |
| 1313 | Neural Sparse Voxel Fields Highlight: In this work, we introduce Neural Sparse Voxel Fields (NSVF), a new neural scene representation for fast and high-quality free-viewpoint rendering. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lingjie Liu; Jiatao Gu; Kyaw Zaw Lin; Tat-Seng Chua; Christian Theobalt; | |
| 1314 | A Flexible Framework For Designing Trainable Priors With Adaptive Smoothing And Game Encoding Highlight: We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems, and whose architectures are derived from an optimization algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bruno Lecouat; Jean Ponce; Julien Mairal; | |
| 1315 | The Discrete Gaussian For Differential Privacy Highlight: With these shortcomings in mind, we introduce and analyze the discrete Gaussian in the context of differential privacy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cl�ment L. Canonne; Gautam Kamath; Thomas Steinke; | |
| 1316 | Robust Sub-Gaussian Principal Component Analysis And Width-Independent Schatten Packing Highlight: We develop two methods for the following fundamental statistical task: given an $\eps$-corrupted set of $n$ samples from a $d$-dimensional sub-Gaussian distribution, return an approximate top eigenvector of the covariance matrix. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arun Jambulapati; Jerry Li; Kevin Tian; | |
| 1317 | Adaptive Importance Sampling For Finite-Sum Optimization And Sampling With Decreasing Step-Sizes Highlight: In this work, we build on this framework and propose a simple and efficient algorithm for adaptive importance sampling for finite-sum optimization and sampling with decreasing step-sizes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ayoub El Hanchi; David Stephens; | |
| 1318 | Learning Efficient Task-dependent Representations With Synaptic Plasticity Highlight: Here we construct a stochastic recurrent neural circuit model that can learn efficient, task-specific sensory codes using a novel form of reward-modulated Hebbian synaptic plasticity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Colin Bredenberg; Eero Simoncelli; Cristina Savin; | |
| 1319 | A Contour Stochastic Gradient Langevin Dynamics Algorithm For Simulations Of Multi-modal Distributions Highlight: We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei Deng; Guang Lin; Faming Liang; | |
| 1320 | Error Bounds Of Imitating Policies And Environments Highlight: In this paper, we firstly analyze the value gap between the expert policy and imitated policies by two imitation methods, behavioral cloning and generative adversarial imitation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tian Xu; Ziniu Li; Yang Yu; | |
| 1321 | Disentangling Human Error From Ground Truth In Segmentation Of Medical Images Highlight: In this work, we present a method for jointly learning, from purely noisy observations alone, the reliability of individual annotators and the true segmentation label distributions, using two coupled CNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Le Zhang; Ryutaro Tanno; Moucheng Xu; Chen Jin; Joseph Jacob; Olga Cicarrelli; Frederik Barkhof; Daniel Alexander; | code |
| 1322 | Consequences Of Misaligned AI Highlight: The contributions of our paper are as follows: 1) we propose a novel model of an incomplete principal—agent problem from artificial intelligence; 2) we provide necessary and sufficient conditions under which indefinitely optimizing for any incomplete proxy objective leads to arbitrarily low overall utility; and 3) we show how modifying the setup to allow reward functions that reference the full state or allowing the principal to update the proxy objective over time can lead to higher utility solutions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simon Zhuang; Dylan Hadfield-Menell; | |
| 1323 | Promoting Coordination Through Policy Regularization In Multi-Agent Deep Reinforcement Learning Highlight: We propose two policy regularization methods: TeamReg, which is based on inter-agent action predictability and CoachReg that relies on synchronized behavior selection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julien Roy; Paul Barde; F�lix Harvey; Derek Nowrouzezahrai; Chris Pal; | |
| 1324 | Emergent Reciprocity And Team Formation From Randomized Uncertain Social Preferences Highlight: In this work, we show evidence of emergent direct reciprocity, indirect reciprocity and reputation, and team formation when training agents with randomized uncertain social preferences (RUSP), a novel environment augmentation that expands the distribution of environments agents play in. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bowen Baker; | |
| 1325 | Hitting The High Notes: Subset Selection For Maximizing Expected Order Statistics Highlight: We consider the fundamental problem of selecting $k$ out of $n$ random variables in a way that the expected highest or second-highest value is maximized. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aranyak Mehta; Uri Nadav; Alexandros Psomas; Aviad Rubinstein; | |
| 1326 | Towards Scale-Invariant Graph-related Problem Solving By Iterative Homogeneous GNNs Highlight: Taking the perspective of synthesizing graph theory programs, we propose several extensions to address the issue. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hao Tang; Zhiao Huang; Jiayuan Gu; Bao-Liang Lu; Hao Su; | |
| 1327 | Regret Bounds Without Lipschitz Continuity: Online Learning With Relative-Lipschitz Losses Highlight: In this work, we consider OCO for relative Lipschitz and relative strongly convex functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yihan Zhou; Victor Sanches Portella; Mark Schmidt; Nicholas Harvey; | |
| 1328 | The Lottery Ticket Hypothesis For Pre-trained BERT Networks Highlight: In this work, we combine these observations to assess whether such trainable, transferrable subnetworks exist in pre-trained BERT models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianlong Chen; Jonathan Frankle; Shiyu Chang; Sijia Liu; Yang Zhang; Zhangyang Wang; Michael Carbin; | code |
| 1329 | Label-Aware Neural Tangent Kernel: Toward Better Generalization And Local Elasticity Highlight: In this paper, we introduce a novel approach from the perspective of \emph{label-awareness} to reduce this gap for the NTK. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuxiao Chen; Hangfeng He; Weijie Su; | |
| 1330 | Beyond Perturbations: Learning Guarantees With Arbitrary Adversarial Test Examples Highlight: We present a transductive learning algorithm that takes as input training examples from a distribution P and arbitrary (unlabeled) test examples, possibly chosen by an adversary. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shafi Goldwasser; Adam Tauman Kalai; Yael Kalai; Omar Montasser; | |
| 1331 | AdvFlow: Inconspicuous Black-box Adversarial Attacks Using Normalizing Flows Highlight: In this paper, we introduce AdvFlow: a novel black-box adversarial attack method on image classifiers that exploits the power of normalizing flows to model the density of adversarial examples around a given target image. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hadi Mohaghegh Dolatabadi; Sarah Erfani; Christopher Leckie; | |
| 1332 | Few-shot Image Generation With Elastic Weight Consolidation Highlight: Crucially, we regularize the changes of the weights during this adaptation, in order to best preserve the information of the source dataset, while fitting the target. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yijun Li; Richard Zhang; Jingwan (Cynthia) Lu; Eli Shechtman; | |
| 1333 | On The Expressiveness Of Approximate Inference In Bayesian Neural Networks Highlight: We study the quality of common variational methods in approximating the Bayesian predictive distribution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andrew Foong; David Burt; Yingzhen Li; Richard Turner; | |
| 1334 | Non-Crossing Quantile Regression For Distributional Reinforcement Learning Highlight: To address these issues, we introduce a general DRL framework by using non-crossing quantile regression to ensure the monotonicity constraint within each sampled batch, which can be incorporated with any well-known DRL algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fan Zhou; Jianing Wang; Xingdong Feng; | |
| 1335 | Dark Experience For General Continual Learning: A Strong, Simple Baseline Highlight: We address it through mixing rehearsal with knowledge distillation and regularization; our simple baseline, Dark Experience Replay, matches the network’s logits sampled throughout the optimization trajectory, thus promoting consistency with its past. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pietro Buzzega; Matteo Boschini; Angelo Porrello; Davide Abati; SIMONE CALDERARA; | |
| 1336 | Learning To Utilize Shaping Rewards: A New Approach Of Reward Shaping Highlight: In this paper, we consider the problem of adaptively utilizing a given shaping reward function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yujing Hu; Weixun Wang; Hangtian Jia; Yixiang Wang; Yingfeng Chen; Jianye Hao; Feng Wu; Changjie Fan; | |
| 1337 | Neural Encoding With Visual Attention Highlight: Using concurrent eye-tracking and functional Magnetic Resonance Imaging (fMRI) recordings from a large cohort of human subjects watching movies, we first demonstrate that leveraging gaze information, in the form of attentional masking, can significantly improve brain response prediction accuracy in a neural encoding model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Meenakshi Khosla; Gia Ngo; Keith Jamison; Amy Kuceyeski; Mert Sabuncu; | |
| 1338 | On The Linearity Of Large Non-linear Models: When And Why The Tangent Kernel Is Constant Highlight: The goal of this work is to shed light on the remarkable phenomenon of "transition to linearity" of certain neural networks as their width approaches infinity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chaoyue Liu; Libin Zhu; Mikhail Belkin; | |
| 1339 | PLLay: Efficient Topological Layer Based On Persistent Landscapes Highlight: In this work, we show differentiability with respect to layer inputs, for a general persistent homology with arbitrary filtration. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kwangho Kim; Jisu Kim; Manzil Zaheer; Joon Kim; Frederic Chazal; Larry Wasserman; | |
| 1340 | Decentralized Langevin Dynamics For Bayesian Learning Highlight: Motivated by decentralized approaches to machine learning, we propose a collaborative Bayesian learning algorithm taking the form of decentralized Langevin dynamics in a non-convex setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anjaly Parayil; He Bai; Jemin George; Prudhvi Gurram; | |
| 1341 | Shared Space Transfer Learning For Analyzing Multi-site FMRI Data Highlight: This paper proposes the Shared Space Transfer Learning (SSTL) as a novel transfer learning (TL) approach that can functionally align homogeneous multi-site fMRI datasets, and so improve the prediction performance in every site. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Muhammad Yousefnezhad; Alessandro Selvitella; Daoqiang Zhang; Andrew Greenshaw; Russell Greiner; | |
| 1342 | The Diversified Ensemble Neural Network Highlight: In this paper, we propose a principled ensemble technique by constructing the so-called diversified ensemble layer to combine multiple networks as individual modules. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shaofeng Zhang; Meng Liu; Junchi Yan; | |
| 1343 | Inductive Quantum Embedding Highlight: We start by reformulating the original QE problem to allow for the induction. On the way, we also underscore some interesting analytic and geometric properties of the solution and leverage them to design a faster training scheme. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Santosh Kumar Srivastava; Dinesh Khandelwal; Dhiraj Madan; Dinesh Garg; Hima Karanam; L Venkata Subramaniam; | |
| 1344 | Variational Bayesian Unlearning Highlight: This paper studies the problem of approximately unlearning a Bayesian model from a small subset of the training data to be erased. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Quoc Phong Nguyen; Bryan Kian Hsiang Low; Patrick Jaillet; | |
| 1345 | Batched Coarse Ranking In Multi-Armed Bandits Highlight: We study both the fixed budget and fixed confidence variants in MAB, and propose algorithms and prove impossibility results which together give almost tight tradeoffs between the total number of arms pulls and the number of policy changes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nikolai Karpov; Qin Zhang; | |
| 1346 | Understanding And Improving Fast Adversarial Training Highlight: Based on this observation, we propose a new regularization method, GradAlign, that prevents catastrophic overfitting by explicitly maximizing the gradient alignment inside the perturbation set and improves the quality of the FGSM solution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maksym Andriushchenko; Nicolas Flammarion; | code |
| 1347 | Coded Sequential Matrix Multiplication For Straggler Mitigation Highlight: In this work, we consider a sequence of $J$ matrix multiplication jobs which needs to be distributed by a master across multiple worker nodes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nikhil Krishnan Muralee Krishnan; Seyederfan Hosseini; Ashish Khisti; | |
| 1348 | Attack Of The Tails: Yes, You Really Can Backdoor Federated Learning Highlight: A range of FL backdoor attacks have been introduced in the literature, but also methods to defend against them, and it is currently an open question whether FL systems can be tailored to be robust against backdoors. In this work, we provide evidence to the contrary. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongyi Wang; Kartik Sreenivasan; Shashank Rajput; Harit Vishwakarma; Saurabh Agarwal; Jy-yong Sohn; Kangwook Lee; Dimitris Papailiopoulos; | |
| 1349 | Certifiably Adversarially Robust Detection Of Out-of-Distribution Data Highlight: In this paper, we are aiming for certifiable worst case guarantees for OOD detection by enforcing not only low confidence at the OOD point but also in an $l_\infty$-ball around it. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julian Bitterwolf; Alexander Meinke; Matthias Hein; | |
| 1350 | Domain Generalization Via Entropy Regularization Highlight: To ensure the conditional invariance of learned features, we propose an entropy regularization term that measures the dependency between the learned features and the class labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shanshan Zhao; Mingming Gong; Tongliang Liu; Huan Fu; Dacheng Tao; | code |
| 1351 | Bayesian Meta-Learning For The Few-Shot Setting Via Deep Kernels Highlight: Following the recognition that meta-learning is implementing learning in a multi-level model, we present a Bayesian treatment for the meta-learning inner loop through the use of deep kernels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Massimiliano Patacchiola; Jack Turner; Elliot J. Crowley; Michael O'Boyle; Amos J. Storkey; | |
| 1352 | Skeleton-bridged Point Completion: From Global Inference To Local Adjustment Highlight: To this end, we propose a skeleton-bridged point completion network (SK-PCN) for shape completion. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yinyu Nie; Yiqun Lin; Xiaoguang Han; Shihui Guo; Jian Chang; Shuguang Cui; Jian.J Zhang; | |
| 1353 | Compressing Images By Encoding Their Latent Representations With Relative Entropy Coding Highlight: As an alternative, we propose a novel method, Relative Entropy Coding (REC), that can directly encode the latent representation with codelength close to the relative entropy for single images, supported by our empirical results obtained on the Cifar10, ImageNet32 and Kodak datasets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gergely Flamich; Marton Havasi; Jos� Miguel Hern�ndez-Lobato; | |
| 1354 | Improved Guarantees For K-means++ And K-means++ Parallel Highlight: In this paper, we study k-means++ and k-means||, the two most popular algorithms for the classic k-means clustering problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Konstantin Makarychev; Aravind Reddy; Liren Shan; | |
| 1355 | Sparse Spectrum Warped Input Measures For Nonstationary Kernel Learning Highlight: We establish a general form of explicit, input-dependent, measure-valued warpings for learning nonstationary kernels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Anthony Tompkins; Rafael Oliveira; Fabio T. Ramos; | |
| 1356 | An Efficient Adversarial Attack For Tree Ensembles Highlight: We study the problem of efficient adversarial attacks on tree based ensembles such as gradient boosting decision trees (GBDTs) and random forests (RFs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chong Zhang; Huan Zhang; Cho-Jui Hsieh; | |
| 1357 | Learning Continuous System Dynamics From Irregularly-Sampled Partial Observations Highlight: To tackle the above challenge, we present LG-ODE, a latent ordinary differential equation generative model for modeling multi-agent dynamic system with known graph structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zijie Huang; Yizhou Sun; Wei Wang; | |
| 1358 | Online Bayesian Persuasion Highlight: In this paper, we relax this assumption through an online learning framework in which the sender faces a receiver with unknown type. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matteo Castiglioni; Andrea Celli; Alberto Marchesi; Nicola Gatti; | |
| 1359 | Robust Pre-Training By Adversarial Contrastive Learning Highlight: Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations that are consistent under both data augmentations and adversarial perturbations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziyu Jiang; Tianlong Chen; Ting Chen; Zhangyang Wang; | code |
| 1360 | Random Walk Graph Neural Networks Highlight: In this paper, we propose a more intuitive and transparent architecture for graph-structured data, so-called Random Walk Graph Neural Network (RWNN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Giannis Nikolentzos; Michalis Vazirgiannis; | |
| 1361 | Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods With Variable Stepsize Scaling Highlight: To overcome this failure, we investigate a double stepsize extragradient algorithm where the exploration step evolves at a more aggressive time-scale compared to the update step. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu-Guan Hsieh; Franck Iutzeler; J�r�me Malick; Panayotis Mertikopoulos; | |
| 1362 | Fast And Accurate $k$-means++ Via Rejection Sampling Highlight: In this paper, we present such a near linear time algorithm for $k$-means++ seeding. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vincent Cohen-Addad; Silvio Lattanzi; Ashkan Norouzi-Fard; Christian Sohler; Ola Svensson; | |
| 1363 | Variational Amodal Object Completion Highlight: In this paper, we propose a variational generative framework for amodal completion, referred to as AMODAL-VAE, which does not require any amodal labels at training time, as it is able to utilize widely available object instance masks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huan Ling; David Acuna; Karsten Kreis; Seung Wook Kim; Sanja Fidler; | |
| 1364 | When Counterpoint Meets Chinese Folk Melodies Highlight: In this paper, we propose a reinforcement learning-based system, named FolkDuet, towards the online countermelody generation for Chinese folk melodies. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nan Jiang; Sheng Jin; Zhiyao Duan; Changshui Zhang; | |
| 1365 | Sub-linear Regret Bounds For Bayesian Optimisation In Unknown Search Spaces Highlight: To this end, we propose a novel BO algorithm which expands (and shifts) the search space over iterations based on controlling the expansion rate thought a \emph{hyperharmonic series}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hung Tran-The; Sunil Gupta; Santu Rana; Huong Ha; Svetha Venkatesh; | |
| 1366 | Universal Domain Adaptation Through Self Supervision Highlight: We propose a more universally applicable domain adaptation approach that can handle arbitrary category shift, called Domain Adaptative Neighborhood Clustering via Entropy optimization (DANCE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kuniaki Saito; Donghyun Kim; Stan Sclaroff; Kate Saenko; | |
| 1367 | Patch2Self: Denoising Diffusion MRI With Self-Supervised Learning? Highlight: We introduce a self-supervised learning method for denoising DWI data, Patch2Self, which uses the entire volume to learn a full-rank locally linear denoiser for that volume. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shreyas Fadnavis; Joshua Batson; Eleftherios Garyfallidis; | |
| 1368 | Stochastic Normalization Highlight: In this paper, we take an alternative approach by refactoring the widely used Batch Normalization (BN) module to mitigate over-fitting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhi Kou; Kaichao You; Mingsheng Long; Jianmin Wang; | |
| 1369 | Constrained Episodic Reinforcement Learning In Concave-convex And Knapsack Settings Highlight: We propose an algorithm for tabular episodic reinforcement learning with constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kiant� Brantley; Miro Dudik; Thodoris Lykouris; Sobhan Miryoosefi; Max Simchowitz; Aleksandrs Slivkins; Wen Sun; | |
| 1370 | On Learning Ising Models Under Huber's Contamination Model Highlight: In such a setup, we aim to design statistically optimal estimators in a high-dimensional scaling in which the number of nodes p, the number of edges k and the maximal node degree d are allowed to increase to infinity as a function of the sample size n. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adarsh Prasad; Vishwak Srinivasan; Sivaraman Balakrishnan; Pradeep Ravikumar; | |
| 1371 | Cross-validation Confidence Intervals For Test Error Highlight: This work develops central limit theorems for cross-validation and consistent estimators of the asymptotic variance under weak stability conditions on the learning algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pierre Bayle; Alexandre Bayle; Lucas Janson; Lester Mackey; | |
| 1372 | DeepSVG: A Hierarchical Generative Network For Vector Graphics Animation Highlight: In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexandre Carlier; Martin Danelljan; Alexandre Alahi; Radu Timofte; | code |
| 1373 | Bayesian Attention Modules Highlight: In this paper, we propose a scalable stochastic version of attention that is easy to implement and optimize. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xinjie Fan; Shujian Zhang; Bo Chen; Mingyuan Zhou; | |
| 1374 | Robustness Analysis Of Non-Convex Stochastic Gradient Descent Using Biased Expectations Highlight: This work proposes a novel analysis of stochastic gradient descent (SGD) for non-convex and smooth optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kevin Scaman; Cedric Malherbe; | |
| 1375 | SoftFlow: Probabilistic Framework For Normalizing Flow On Manifolds Highlight: In this paper, we propose SoftFlow, a probabilistic framework for training normalizing flows on manifolds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hyeongju Kim; Hyeonseung Lee; Woo Hyun Kang; Joun Yeop Lee; Nam Soo Kim; | |
| 1376 | A Meta-learning Approach To (re)discover Plasticity Rules That Carve A Desired Function Into A Neural Network Highlight: Here, we present an alternative approach that uses meta-learning to discover plausible synaptic plasticity rules. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Basile Confavreux; Friedemann Zenke; Everton Agnes; Timothy Lillicrap; Tim Vogels; | |
| 1377 | Greedy Optimization Provably Wins The Lottery: Logarithmic Number Of Winning Tickets Is Enough Highlight: This paper provides one answer to this question by proposing a greedy optimization based pruning method. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mao Ye; Lemeng Wu; Qiang Liu; | |
| 1378 | Path Integral Based Convolution And Pooling For Graph Neural Networks Highlight: Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zheng Ma; Junyu Xuan; Yu Guang Wang; Ming Li; Pietro Li�; | |
| 1379 | Estimating The Effects Of Continuous-valued Interventions Using Generative Adversarial Networks Highlight: In this paper, we tackle this problem by building on a modification of the generative adversarial networks (GANs) framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ioana Bica; James Jordon; Mihaela van der Schaar; | |
| 1380 | Latent Dynamic Factor Analysis Of High-Dimensional Neural Recordings Highlight: We designed and implemented a novel method, Latent Dynamic Factor Analysis of High-dimensional time series (LDFA-H), which combines (a) a new approach to estimating the covariance structure among high-dimensional time series (for the observed variables) and (b) a new extension of probabilistic CCA to dynamic time series (for the latent variables). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Heejong Bong; Zongge Liu; Zhao Ren; Matthew Smith; Valerie Ventura; Kass E. Robert; | |
| 1381 | Conditioning And Processing: Techniques To Improve Information-Theoretic Generalization Bounds Highlight: In this paper, a probabilistic graphical representation of this approach is adopted and two general techniques to improve the bounds are introduced, namely conditioning and processing. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hassan Hafez-Kolahi; Zeinab Golgooni; Shohreh Kasaei; Mahdieh Soleymani; | |
| 1382 | Bongard-LOGO: A New Benchmark For Human-Level Concept Learning And Reasoning Highlight: Inspired by the original one hundred BPs, we propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weili Nie; Zhiding Yu; Lei Mao; Ankit B. Patel; Yuke Zhu; Anima Anandkumar; | |
| 1383 | GAN Memory With No Forgetting Highlight: Motivated by that, we propose a GAN memory for lifelong learning, which is capable of remembering a stream of datasets via generative processes, with \emph{no} forgetting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yulai Cong; Miaoyun Zhao; Jianqiao Li; Sijia Wang; Lawrence Carin; | code |
| 1384 | Deep Reinforcement Learning With Stacked Hierarchical Attention For Text-based Games Highlight: In this work, we aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunqiu Xu; Meng Fang; Ling Chen; Yali Du; Joey Tianyi Zhou; Chengqi Zhang; | |
| 1385 | Gaussian Gated Linear Networks Highlight: We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Budden; Adam Marblestone; Eren Sezener; Tor Lattimore; Gregory Wayne; Joel Veness; | |
| 1386 | Node Classification On Graphs With Few-Shot Novel Labels Via Meta Transformed Network Embedding Highlight: To cope with this problem, we propose a novel Meta Transformed Network Embedding framework (MetaTNE), which consists of three modules: (1) A \emph{structural module} provides each node a latent representation according to the graph structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lin Lan; Pinghui Wang; Xuefeng Du; Kaikai Song; Jing Tao; Xiaohong Guan; | |
| 1387 | Online Fast Adaptation And Knowledge Accumulation (OSAKA): A New Approach To Continual Learning Highlight: We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Massimo Caccia; Pau Rodriguez; Oleksiy Ostapenko; Fabrice Normandin; Min Lin; Lucas Page-Caccia; Issam Hadj Laradji; Irina Rish; Alexandre Lacoste; David V�zquez; Laurent Charlin; | |
| 1388 | Convex Optimization Based On Global Lower Second-order Models Highlight: In this work, we present new second-order algorithms for composite convex optimization, called Contracting-domain Newton methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nikita Doikov; Yurii Nesterov; | |
| 1389 | Simultaneously Learning Stochastic And Adversarial Episodic MDPs With Known Transition Highlight: Analyzing such a regularizer and deriving a particular self-bounding regret guarantee is our key technical contribution and might be of independent interest. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tiancheng Jin; Haipeng Luo; | |
| 1390 | Relative Gradient Optimization Of The Jacobian Term In Unsupervised Deep Learning Highlight: Deep density models have been widely used for this task, but their maximum likelihood based training requires estimating the log-determinant of the Jacobian and is computationally expensive, thus imposing a trade-off between computation and expressive power. In this work, we propose a new approach for exact training of such neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luigi Gresele; Giancarlo Fissore; Adri�n Javaloy; Bernhard Sch�lkopf; Aapo Hyvarinen; | |
| 1391 | Self-Supervised Visual Representation Learning From Hierarchical Grouping Highlight: We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiao Zhang; Michael Maire; | |
| 1392 | Optimal Variance Control Of The Score-Function Gradient Estimator For Importance-Weighted Bounds Highlight: This paper introduces novel results for the score-function gradient estimator of the importance-weighted variational bound (IWAE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Valentin Li�vin; Andrea Dittadi; Anders Christensen; Ole Winther; | |
| 1393 | Explicit Regularisation In Gaussian Noise Injections Highlight: We study the regularisation induced in neural networks by Gaussian noise injections (GNIs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Camuto; Matthew Willetts; Umut Simsekli; Stephen J. Roberts; Chris C. Holmes; | |
| 1394 | Numerically Solving Parametric Families Of High-Dimensional Kolmogorov Partial Differential Equations Via Deep Learning Highlight: We present a deep learning algorithm for the numerical solution of parametric families of high-dimensional linear Kolmogorov partial differential equations (PDEs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julius Berner; Markus Dablander; Philipp Grohs; | |
| 1395 | Finite-Time Analysis For Double Q-learning Highlight: In this paper, we provide the first non-asymptotic (i.e., finite-time) analysis for double Q-learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huaqing Xiong; Lin Zhao; Yingbin Liang; Wei Zhang; | |
| 1396 | Learning To Detect Objects With A 1 Megapixel Event Camera Highlight: The main reasons for this performance gap are: the lower spatial resolution of event sensors, compared to frame cameras; the lack of large-scale training datasets; the absence of well established deep learning architectures for event-based processing. In this paper, we address all these problems in the context of an event-based object detection task. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Etienne Perot; Pierre de Tournemire; Davide Nitti; Jonathan Masci; Amos Sironi; | |
| 1397 | End-to-End Learning And Intervention In Games Highlight: In this paper, we provide a unified framework for learning and intervention in games. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiayang Li; Jing Yu; Yu Nie; Zhaoran Wang; | |
| 1398 | Least Squares Regression With Markovian Data: Fundamental Limits And Algorithms Highlight: Instead, we propose an algorithm based on experience replay–a popular reinforcement learning technique–that achieves a significantly better error rate. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dheeraj Nagaraj; Xian Wu; Guy Bresler; Prateek Jain; Praneeth Netrapalli; | |
| 1399 | Predictive Coding In Balanced Neural Networks With Noise, Chaos And Delays Highlight: To discover such principles, we introduce an analytically tractable model of balanced predictive coding, in which the degree of balance and the degree of weight disorder can be dissociated unlike in previous balanced network models, and we develop a mean-field theory of coding accuracy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Kadmon; Jonathan Timcheck; Surya Ganguli; | |
| 1400 | Interpolation Technique To Speed Up Gradients Propagation In Neural ODEs Highlight: We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Talgat Daulbaev; Alexandr Katrutsa; Larisa Markeeva; Julia Gusak; Andrzej Cichocki; Ivan Oseledets; | |
| 1401 | On The Equivalence Between Online And Private Learnability Beyond Binary Classification Highlight: We investigate whether this equivalence extends to multi-class classification and regression. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Young Jung; Baekjin Kim; Ambuj Tewari; | |
| 1402 | AViD Dataset: Anonymized Videos From Diverse Countries Highlight: We introduce a new public video dataset for action recognition: Anonymized Videos from Diverse countries (AViD). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
AJ Piergiovanni; Michael Ryoo; | code |
| 1403 | Probably Approximately Correct Constrained Learning Highlight: To tackle these problems, we develop a generalization theory of constrained learning based on the probably approximately correct (PAC) learning framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luiz Chamon; Alejandro Ribeiro; | |
| 1404 | RATT: Recurrent Attention To Transient Tasks For Continual Image Captioning Highlight: In this paper we take a systematic look at continual learning of LSTM-based models for image captioning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Riccardo Del Chiaro; Bartlomiej Twardowski; Andrew Bagdanov; Joost van de Weijer; | |
| 1405 | Decisions, Counterfactual Explanations And Strategic Behavior Highlight: In this paper, our goal is to find policies and counterfactual explanations that are optimal in terms of utility in such a strategic setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stratis Tsirtsis; Manuel Gomez Rodriguez; | |
| 1406 | Hierarchical Patch VAE-GAN: Generating Diverse Videos From A Single Sample Highlight: We introduce a novel patch-based variational autoencoder (VAE) which allows for a much greater diversity in generation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shir Gur; Sagie Benaim; Lior Wolf; | code |
| 1407 | A Feasible Level Proximal Point Method For Nonconvex Sparse Constrained Optimization Highlight: In this paper, we study a new model consisting of a general convex or nonconvex objectives and a variety of continuous nonconvex sparsity-inducing constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Digvijay Boob; Qi Deng; Guanghui Lan; Yilin Wang; | |
| 1408 | Reservoir Computing Meets Recurrent Kernels And Structured Transforms Highlight: Our contributions are threefold: a) We rigorously establish the recurrent kernel limit of Reservoir Computing and prove its convergence. b) We test our models on chaotic time series prediction, a classic but challenging benchmark in Reservoir Computing, and show how the Recurrent Kernel is competitive and computationally efficient when the number of data points remains moderate. c) When the number of samples is too large, we leverage the success of structured Random Features for kernel approximation by introducing Structured Reservoir Computing. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Dong; Ruben Ohana; Mushegh Rafayelyan; Florent Krzakala; | |
| 1409 | Comprehensive Attention Self-Distillation For Weakly-Supervised Object Detection Highlight: To address the above issues, we propose a Comprehensive Attention Self-Distillation (CASD) training approach for WSOD. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zeyi Huang; Yang Zou; B. V. K. Vijaya Kumar; Dong Huang; | |
| 1410 | Linear Dynamical Systems As A Core Computational Primitive Highlight: Running nonlinear RNNs for T steps takes O(T) time. Our construction, called LDStack, approximately runs them in O(log T) parallel time, and obtains arbitrarily low error via repetition. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shiva Kaul; | |
| 1411 | Ratio Trace Formulation Of Wasserstein Discriminant Analysis Highlight: We reformulate the Wasserstein Discriminant Analysis (WDA) as a ratio trace problem and present an eigensolver-based algorithm to compute the discriminative subspace of WDA. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hexuan Liu; Yunfeng Cai; You-Lin Chen; Ping Li; | |
| 1412 | PAC-Bayes Analysis Beyond The Usual Bounds Highlight: Specifically, we present a basic PAC-Bayes inequality for stochastic kernels, from which one may derive extensions of various known PAC-Bayes bounds as well as novel bounds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Omar Rivasplata; Ilja Kuzborskij; Csaba Szepesvari; John Shawe-Taylor; | |
| 1413 | Few-shot Visual Reasoning With Meta-Analogical Contrastive Learning Highlight: In this work, we propose to solve such a few-shot (or low-shot) abstract visual reasoning problem by resorting to \emph{analogical reasoning}, which is a unique human ability to identify structural or relational similarity between two sets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Youngsung Kim; Jinwoo Shin; Eunho Yang; Sung Ju Hwang; | |
| 1414 | MPNet: Masked And Permuted Pre-training For Language Understanding Highlight: In this paper, we propose MPNet, a novel pre-training method that inherits the advantages of BERT and XLNet and avoids their limitations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaitao Song; Xu Tan; Tao Qin; Jianfeng Lu; Tie-Yan Liu; | |
| 1415 | Reinforcement Learning With Feedback Graphs Highlight: We study RL in the tabular MDP setting where the agent receives additional observations per step in the form of transitions samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christoph Dann; Yishay Mansour; Mehryar Mohri; Ayush Sekhari; Karthik Sridharan; | |
| 1416 | Zap Q-Learning With Nonlinear Function Approximation Highlight: This paper introduces a new framework for analysis of a more general class of recursive algorithms known as stochastic approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuhang Chen; Adithya M Devraj; Fan Lu; Ana Busic; Sean Meyn; | |
| 1417 | Lipschitz-Certifiable Training With A Tight Outer Bound Highlight: In this study, we propose a fast and scalable certifiable training algorithm based on Lipschitz analysis and interval arithmetic. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sungyoon Lee; Jaewook Lee; Saerom Park; | code |
| 1418 | Fast Adaptive Non-Monotone Submodular Maximization Subject To A Knapsack Constraint Highlight: We present a simple randomized greedy algorithm that achieves a $5.83$ approximation and runs in $O(n \log n)$ time, i.e., at least a factor $n$ faster than other state-of-the-art algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Georgios Amanatidis; Federico Fusco; Philip Lazos; Stefano Leonardi; Rebecca Reiffenh�user; | |
| 1419 | Conformal Symplectic And Relativistic Optimization Highlight: Here we study structure-preserving discretizations for a certain class of dissipative (conformal) Hamiltonian systems, allowing us to analyze the symplectic structure of both Nesterov and heavy ball, besides providing several new insights into these methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guilherme Starvaggi Franca; Jeremias Sulam; Daniel Robinson; Rene Vidal; | |
| 1420 | Bayes Consistency Vs. H-Consistency: The Interplay Between Surrogate Loss Functions And The Scoring Function Class Highlight: However, follow-up work has suggested this framework can be of limited value when studying H-consistency; in particular, concerns have been raised that even when the data comes from an underlying linear model, minimizing certain convex calibrated surrogates over linear scoring functions fails to recover the true model (Long and Servedio, 2013). In this paper, we investigate this apparent conundrum. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mingyuan Zhang; Shivani Agarwal; | |
| 1421 | Inverting Gradients – How Easy Is It To Break Privacy In Federated Learning? Highlight: However, by exploiting a magnitude-invariant loss along with optimization strategies based on adversarial attacks, we show that is is actually possible to faithfully reconstruct images at high resolution from the knowledge of their parameter gradients, and demonstrate that such a break of privacy is possible even for trained deep networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonas Geiping; Hartmut Bauermeister; Hannah Dr�ge; Michael Moeller; | |
| 1422 | Dynamic Allocation Of Limited Memory Resources In Reinforcement Learning Highlight: In this article, we propose a dynamical framework to maximize expected reward under constraints of limited resources, which we implement with a cost function that penalizes precise representations of action-values in memory, each of which may vary in its precision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nisheet Patel; Luigi Acerbi; Alexandre Pouget; | |
| 1423 | CryptoNAS: Private Inference On A ReLU Budget Highlight: This paper makes the observation that existing models are ill-suited for PI and proposes a novel NAS method, named CryptoNAS, for finding and tailoring models to the needs of PI. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zahra Ghodsi; Akshaj Kumar Veldanda; Brandon Reagen; Siddharth Garg; | |
| 1424 | A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm Highlight: This paper introduces a novel EM algorithm, called {\tt SPIDER-EM}, for inference from a training set of size $n$, $n \gg 1$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gersende Fort; Eric Moulines; Hoi-To Wai; | |
| 1425 | CHIP: A Hawkes Process Model For Continuous-time Networks With Scalable And Consistent Estimation Highlight: We propose the Community Hawkes Independent Pairs (CHIP) generative model for such networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Makan Arastuie; Subhadeep Paul; Kevin Xu; | |
| 1426 | SAC: Accelerating And Structuring Self-Attention Via Sparse Adaptive Connection Highlight: In this paper, we present a method for accelerating and structuring self-attentions: Sparse Adaptive Connection (SAC). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaoya Li; Yuxian Meng; Mingxin Zhou; Qinghong Han; Fei Wu; Jiwei Li; | |
| 1427 | Design Space For Graph Neural Networks Highlight: Our approach features three key innovations: (1) A general GNN design space; (2) a GNN task space with a similarity metric, so that for a given novel task/dataset, we can quickly identify/transfer the best performing architecture; (3) an efficient and effective design space evaluation method which allows insights to be distilled from a huge number of model-task combinations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiaxuan You; Zhitao Ying; Jure Leskovec; | |
| 1428 | HiFi-GAN: Generative Adversarial Networks For Efficient And High Fidelity Speech Synthesis Highlight: In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jungil Kong; Jaehyeon Kim; Jaekyoung Bae; | |
| 1429 | Unbalanced Sobolev Descent Highlight: We introduce Unbalanced Sobolev Descent (USD), a particle descent algorithm for transporting a high dimensional source distribution to a target distribution that does not necessarily have the same mass. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Youssef Mroueh; Mattia Rigotti; | |
| 1430 | Identifying Mislabeled Data Using The Area Under The Margin Ranking Highlight: This paper introduces a new method to identify such samples and mitigate their impact when training neural networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Geoff Pleiss; Tianyi Zhang; Ethan Elenberg; Kilian Q. Weinberger; | |
| 1431 | Combining Deep Reinforcement Learning And Search For Imperfect-Information Games Highlight: This paper presents ReBeL, a general framework for self-play reinforcement learning and search that provably converges to a Nash equilibrium in any two-player zero-sum game. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Noam Brown; Anton Bakhtin; Adam Lerer; Qucheng Gong; | |
| 1432 | High-Throughput Synchronous Deep RL Highlight: To combine the advantages of both methods we propose High-Throughput Synchronous Deep Reinforcement Learning (HTS-RL). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Iou-Jen Liu; Raymond Yeh; Alexander Schwing; | |
| 1433 | Contrastive Learning With Adversarial Examples Highlight: This paper addresses the problem, by introducing a new family of adversarial examples for constrastive learning and using these examples to define a new adversarial training algorithm for SSL, denoted as CLAE. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chih-Hui Ho; Nuno Nvasconcelos; | |
| 1434 | Mixed Hamiltonian Monte Carlo For Mixed Discrete And Continuous Variables Highlight: In this paper, we propose mixed HMC (M-HMC) as a general framework to address this limitation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guangyao Zhou; | |
| 1435 | Adversarial Sparse Transformer For Time Series Forecasting Highlight: To solve these issues, in this paper, we propose a new time series forecasting model — Adversarial Sparse Transformer (AST), based on Generated Adversarial Networks (GANs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sifan Wu; Xi Xiao; Qianggang Ding; Peilin Zhao; Ying Wei; Junzhou Huang; | |
| 1436 | The Surprising Simplicity Of The Early-Time Learning Dynamics Of Neural Networks Highlight: In this work, we show that these common perceptions can be completely false in the early phase of learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei Hu; Lechao Xiao; Ben Adlam; Jeffrey Pennington; | |
| 1437 | CLEARER: Multi-Scale Neural Architecture Search For Image Restoration Highlight: Different from the existing labor-intensive handcrafted architecture design paradigms, we present a novel method, termed as multi-sCaLe nEural ARchitecture sEarch for image Restoration (CLEARER), which is a speci?cally designed neural architecture search (NAS) for image restoration. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuanbiao Gou; Boyun Li; Zitao Liu; Songfan Yang; Xi Peng; | code |
| 1438 | Hierarchical Gaussian Process Priors For Bayesian Neural Network Weights Highlight: To this end, this paper introduces two innovations: (i) a Gaussian process-based hierarchical model for network weights based on unit embeddings that can flexibly encode correlated weight structures, and (ii) input-dependent versions of these weight priors that can provide convenient ways to regularize the function space through the use of kernels defined on contextual inputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Theofanis Karaletsos; Thang D. Bui; | |
| 1439 | Compositional Explanations Of Neurons Highlight: We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts that closely approximate neuron behavior. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jesse Mu; Jacob Andreas; | |
| 1440 | Calibrated Reliable Regression Using Maximum Mean Discrepancy Highlight: In this paper, we are concerned with getting well-calibrated predictions in regression tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Peng Cui; Wenbo Hu; Jun Zhu; | |
| 1441 | Directional Convergence And Alignment In Deep Learning Highlight: In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in direction, with an immediate corollary that network predictions, training errors, and the margin distribution also converge. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziwei Ji; Matus Telgarsky; | |
| 1442 | Functional Regularization For Representation Learning: A Unified Theoretical Perspective Highlight: We propose a discriminative theoretical framework for analyzing the sample complexity of these approaches, which generalizes the framework of (Balcan and Blum, 2010) to allow learnable regularization functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siddhant Garg; Yingyu Liang; | |
| 1443 | Provably Efficient Online Hyperparameter Optimization With Population-Based Bandits Highlight: In this work, we introduce the first provably efficient PBT-style algorithm, Population-Based Bandits (PB2). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jack Parker-Holder; Vu Nguyen; Stephen J. Roberts; | |
| 1444 | Understanding Global Feature Contributions With Additive Importance Measures Highlight: We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ian Covert; Scott M. Lundberg; Su-In Lee; | |
| 1445 | Online Non-Convex Optimization With Imperfect Feedback Highlight: We consider the problem of online learning with non-convex losses. In terms of feedback, we assume that the learner observes – or otherwise constructs – an inexact model for the loss function encountered at each stage, and we propose a mixed-strategy learning policy based on dual averaging. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Am�lie H�liou; Matthieu Martin; Panayotis Mertikopoulos; Thibaud Rahier; | |
| 1446 | Co-Tuning For Transfer Learning Highlight: To \textit{fully} transfer pre-trained models, we propose a two-step framework named \textbf{Co-Tuning}: (i) learn the relationship between source categories and target categories from the pre-trained model and calibrated predictions; (ii) target labels (one-hot labels), as well as source labels (probabilistic labels) translated by the category relationship, collaboratively supervise the fine-tuning process. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaichao You; Zhi Kou; Mingsheng Long; Jianmin Wang; | |
| 1447 | Multifaceted Uncertainty Estimation For Label-Efficient Deep Learning Highlight: We present a novel multi-source uncertainty prediction approach that enables deep learning (DL) models to be actively trained with much less labeled data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weishi Shi; Xujiang Zhao; Feng Chen; Qi Yu; | |
| 1448 | Continuous Surface Embeddings Highlight: In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Natalia Neverova; David Novotny; Marc Szafraniec; Vasil Khalidov; Patrick Labatut; Andrea Vedaldi; | |
| 1449 | Succinct And Robust Multi-Agent Communication With Temporal Message Control Highlight: In this paper, we present \textit{Temporal Message Control} (TMC), a simple yet effective approach for achieving succinct and robust communication in MARL. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sai Qian Zhang; Qi Zhang; Jieyu Lin; | |
| 1450 | Big Bird: Transformers For Longer Sequences Highlight: To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Manzil Zaheer; Guru Guruganesh; Kumar Avinava Dubey; Joshua Ainslie; Chris Alberti; Santiago Ontanon; Philip Pham; Anirudh Ravula; Qifan Wang; Li Yang; Amr Ahmed; | |
| 1451 | Neural Execution Engines: Learning To Execute Subroutines Highlight: To address the issue, we propose a learned conditional masking mechanism, which enables the model to strongly generalize far outside of its training range with near-perfect accuracy on a variety of algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yujun Yan; Kevin Swersky; Danai Koutra; Parthasarathy Ranganathan; Milad Hashemi; | |
| 1452 | Random Reshuffling: Simple Analysis With Vast Improvements Highlight: We argue through theory and experiments that the new variance type gives an additional justification of the superior performance of RR. To go beyond strong convexity, we present several results for non-strongly convex and non-convex objectives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Konstantin Mishchenko; Ahmed Khaled Ragab Bayoumi; Peter Richtarik; | |
| 1453 | Long-Horizon Visual Planning With Goal-Conditioned Hierarchical Predictors Highlight: In this work we propose a framework for visual prediction and planning that is able to overcome both of these limitations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Karl Pertsch; Oleh Rybkin; Frederik Ebert; Shenghao Zhou; Dinesh Jayaraman; Chelsea Finn; Sergey Levine; | |
| 1454 | Statistical Optimal Transport Posed As Learning Kernel Embedding Highlight: This work takes the novel approach of posing statistical OT as that of learning the transport plan’s kernel mean embedding from sample based estimates of marginal embeddings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Saketha Nath Jagarlapudi; Pratik Kumar Jawanpuria; | |
| 1455 | Dual-Resolution Correspondence Networks Highlight: In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xinghui Li; Kai Han; Shuda Li; Victor Prisacariu; | |
| 1456 | Advances In Black-Box VI: Normalizing Flows, Importance Weighting, And Optimization Highlight: In this paper, we postulate that black-box VI is best addressed through a careful combination of numerous algorithmic components. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Abhinav Agrawal; Daniel R. Sheldon; Justin Domke; | |
| 1457 | F-Divergence Variational Inference Highlight: This paper introduces the f-divergence variational inference (f-VI) that generalizes variational inference to all f-divergences. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Neng Wan; Dapeng Li; NAIRA HOVAKIMYAN; | |
| 1458 | Unfolding Recurrence By Green�s Functions For Optimized Reservoir Computing Highlight: The purpose of this work is to present a solvable recurrent network model that links to feed forward networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sandra Nestler; Christian Keup; David Dahmen; Matthieu Gilson; Holger Rauhut; Moritz Helias; | |
| 1459 | The Dilemma Of TriHard Loss And An Element-Weighted TriHard Loss For Person Re-Identification Highlight: Several methods to alleviate the dilemma are designed and tested. In the meanwhile, an element-weighted TriHard loss is emphatically proposed to enlarge the distance between partial elements of feature vectors selectively which represent the different characteristics between anchors and hard negative samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yihao Lv; Youzhi Gu; Liu Xinggao; | |
| 1460 | Disentangling By Subspace Diffusion Highlight: We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Pfau; Irina Higgins; Alex Botev; S�bastien Racani�re; | |
| 1461 | Towards Neural Programming Interfaces Highlight: We recast the problem of controlling natural language generation as that of learning to interface with a pretrained language model, just as Application Programming Interfaces (APIs) control the behavior of programs by altering hyperparameters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zachary Brown; Nathaniel Robinson; David Wingate; Nancy Fulda; | |
| 1462 | Discovering Symbolic Models From Deep Learning With Inductive Biases Highlight: We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Miles Cranmer; Alvaro Sanchez Gonzalez; Peter Battaglia; Rui Xu; Kyle Cranmer; David Spergel; Shirley Ho; | |
| 1463 | Real World Games Look Like Spinning Tops Highlight: This paper investigates the geometrical properties of real world games (e.g. Tic-Tac-Toe, Go, StarCraft II). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wojciech M. Czarnecki; Gauthier Gidel; Brendan Tracey; Karl Tuyls; Shayegan Omidshafiei; David Balduzzi; Max Jaderberg; | |
| 1464 | Cooperative Heterogeneous Deep Reinforcement Learning Highlight: In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Han Zheng; Pengfei Wei; Jing Jiang; Guodong Long; Qinghua Lu; Chengqi Zhang; | |
| 1465 | Mitigating Forgetting In Online Continual Learning Via Instance-Aware Parameterization Highlight: To mitigate this, we leverage the concept of instance awareness in the neural network, where each data instance is classified by a path in the network searched by the controller from a meta-graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hung-Jen Chen; An-Chieh Cheng; Da-Cheng Juan; Wei Wei; Min Sun; | |
| 1466 | ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration From An Infinite Pool Highlight: Inspired by this idea, we introduce ImpatientCapsAndRuns, which quickly discards less promising configurations, significantly speeding up the search procedure compared to previous algorithms with theoretical guarantees, while still achieving optimal runtime up to logarithmic factors under mild assumptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gellert Weisz; Andr�s Gy�rgy; Wei-I Lin; Devon Graham; Kevin Leyton-Brown; Csaba Szepesvari; Brendan Lucier; | |
| 1467 | Dense Correspondences Between Human Bodies Via Learning Transformation Synchronization On Graphs Highlight: We introduce an approach for establishing dense correspondences between partial scans of human models and a complete template model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiangru Huang; Haitao Yang; Etienne Vouga; Qixing Huang; | |
| 1468 | Reasoning About Uncertainties In Discrete-Time Dynamical Systems Using Polynomial Forms Highlight: In this paper, we propose polynomial forms to represent distributions of state variables over time for discrete-time stochastic dynamical systems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sriram Sankaranarayanan; Yi Chou; Eric Goubault; Sylvie Putot; | |
| 1469 | Applications Of Common Entropy For Causal Inference Highlight: To efficiently compute common entropy, we propose an iterative algorithm that can be used to discover the trade-off between the entropy of the latent variable and the conditional mutual information of the observed variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Murat Kocaoglu; Sanjay Shakkottai; Alexandros G. Dimakis; Constantine Caramanis; Sriram Vishwanath; | |
| 1470 | SGD With Shuffling: Optimal Rates Without Component Convexity And Large Epoch Requirements Highlight: Specifically, depending on how the indices of the finite-sum are shuffled, we consider the RandomShuffle (shuffle at the beginning of each epoch) and SingleShuffle (shuffle only once) algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kwangjun Ahn; Chulhee Yun; Suvrit Sra; | |
| 1471 | Unsupervised Joint K-node Graph Representations With Compositional Energy-Based Models Highlight: We propose MHM-GNN, an inductive unsupervised graph representation approach that combines joint k-node representations with energy-based models (hypergraph Markov networks) and GNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Leonardo Cotta; Carlos H. C. Teixeira; Ananthram Swami; Bruno Ribeiro; | |
| 1472 | Neural Manifold Ordinary Differential Equations Highlight: In this paper, we study normalizing flows on manifolds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aaron Lou; Derek Lim; Isay Katsman; Leo Huang; Qingxuan Jiang; Ser Nam Lim; Christopher M. De Sa; | |
| 1473 | CO-Optimal Transport Highlight: To circumvent this limitation, we propose a novel OT problem, named COOT for CO-Optimal Transport, that simultaneously optimizes two transport maps between both samples and features, contrary to other approaches that either discard the individual features by focusing on pairwise distances between samples or need to model explicitly the relations between them. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vayer Titouan; Ievgen Redko; R�mi Flamary; Nicolas Courty; | |
| 1474 | Continuous Meta-Learning Without Tasks Highlight: In this work, we enable the application of generic meta-learning algorithms to settings where this task segmentation is unavailable, such as continual online learning with unsegmented time series data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
James Harrison; Apoorva Sharma; Chelsea Finn; Marco Pavone; | |
| 1475 | A Mathematical Theory Of Cooperative Communication Highlight: Through a connection to the theory of optimal transport, we establishing a mathematical framework for cooperative communication. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pei Wang; Junqi Wang; Pushpi Paranamana; Patrick Shafto; | |
| 1476 | Penalized Langevin Dynamics With Vanishing Penalty For Smooth And Log-concave Targets Highlight: We study the problem of sampling from a probability distribution on $\mathbb R^p$ defined via a convex and smooth potential function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Avetik Karagulyan; Arnak Dalalyan; | |
| 1477 | Learning Invariances In Neural Networks From Training Data Highlight: We show how to learn invariances by parameterizing a distribution over augmentations and optimizing the training loss simultaneously with respect to the network parameters and augmentation parameters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gregory Benton; Marc Finzi; Pavel Izmailov; Andrew Gordon Wilson; | |
| 1478 | A Finite-Time Analysis Of Two Time-Scale Actor-Critic Methods Highlight: In this work, we provide a non-asymptotic analysis for two time-scale actor-critic methods under non-i.i.d. setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yue Wu; Weitong ZHANG; Pan Xu; Quanquan Gu; | |
| 1479 | Pruning Filter In Filter Highlight: To converge the strength of both methods, we propose to prune the filter in the filter. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fanxu Meng; Hao Cheng; Ke Li; Huixiang Luo; Xiaowei Guo; Guangming Lu; Xing Sun; | |
| 1480 | Learning To Mutate With Hypergradient Guided Population Highlight: In this study, we propose a hyperparameter mutation (HPM) algorithm to explicitly consider a learnable trade-off between using global and local search, where we adopt a population of student models to simultaneously explore the hyperparameter space guided by hypergradient and leverage a teacher model to mutate the underperforming students by exploiting the top ones. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhiqiang Tao; Yaliang Li; Bolin Ding; Ce Zhang; Jingren Zhou; Yun Fu; | |
| 1481 | A Convex Optimization Formulation For Multivariate Regression Highlight: In this article, we propose a convex optimization formulation for high-dimensional multivariate linear regression under a general error covariance structure. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunzhang Zhu; | |
| 1482 | Online Meta-Critic Learning For Off-Policy Actor-Critic Methods Highlight: In this paper, we introduce a flexible and augmented meta-critic that observes the learning process and meta-learns an additional loss for the actor that accelerates and improves actor-critic learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wei Zhou; Yiying Li; Yongxin Yang; Huaimin Wang; Timothy Hospedales; | |
| 1483 | The All-or-Nothing Phenomenon In Sparse Tensor PCA Highlight: We study the statistical problem of estimating a rank-one sparse tensor corrupted by additive gaussian noise, a Gaussian additive model also known as sparse tensor PCA. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Niles-Weed; Ilias Zadik; | |
| 1484 | Synthesize, Execute And Debug: Learning To Repair For Neural Program Synthesis Highlight: In this work, we propose SED, a neural program generation framework that incorporates synthesis, execution, and debugging stages. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kavi Gupta; Peter Ebert Christensen; Xinyun Chen; Dawn Song; | |
| 1485 | ARMA Nets: Expanding Receptive Field For Dense Prediction Highlight: In this work, we propose to replace any traditional convolutional layer with an autoregressive moving-average (ARMA) layer, a novel module with an adjustable receptive field controlled by the learnable autoregressive coefficients. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiahao Su; Shiqi Wang; Furong Huang; | |
| 1486 | Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations Highlight: We propose a novel multi-objective Bayesian optimization algorithm that iteratively selects the best batch of samples to be evaluated in parallel. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mina Konakovic Lukovic; Yunsheng Tian; Wojciech Matusik; | code |
| 1487 | SOLOv2: Dynamic And Fast Instance Segmentation Highlight: In this work, we design a simple, direct, and fast framework for instance segmentation with strong performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xinlong Wang; Rufeng Zhang; Tao Kong; Lei Li; Chunhua Shen; | code |
| 1488 | Robust Recovery Via Implicit Bias Of Discrepant Learning Rates For Double Over-parameterization Highlight: This paper shows that with a {\em double over-parameterization} for both the low-rank matrix and sparse corruption, gradient descent with {\em discrepant learning rates} provably recovers the underlying matrix even without prior knowledge on neither rank of the matrix nor sparsity of the corruption. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chong You; Zhihui Zhu; Qing Qu; Yi Ma; | |
| 1489 | Axioms For Learning From Pairwise Comparisons Highlight: We show that a large class of random utility models (including the Thurstone–Mosteller Model), when estimated using the MLE, satisfy a Pareto efficiency condition. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ritesh Noothigattu; Dominik Peters; Ariel D. Procaccia; | |
| 1490 | Continuous Regularized Wasserstein Barycenters Highlight: Leveraging a new dual formulation for the regularized Wasserstein barycenter problem, we introduce a stochastic algorithm that constructs a continuous approximation of the barycenter. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lingxiao Li; Aude Genevay; Mikhail Yurochkin; Justin M. Solomon; | |
| 1491 | Spectral Temporal Graph Neural Network For Multivariate Time-series Forecasting Highlight: In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Defu Cao; Yujing Wang; Juanyong Duan; Ce Zhang; Xia Zhu; Congrui Huang; Yunhai Tong; Bixiong Xu; Jing Bai; Jie Tong; Qi Zhang; | |
| 1492 | Online Multitask Learning With Long-Term Memory Highlight: We provide an algorithm that predicts on each trial in time linear in the number of hypotheses when the hypothesis class is finite. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mark Herbster; Stephen Pasteris; Lisa Tse; | |
| 1493 | Fewer Is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies Highlight: In this paper, we propose a novel Proxy-based deep Graph Metric Learning (ProxyGML) approach from the perspective of graph classification, which uses fewer proxies yet achieves better comprehensive performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuehua Zhu; Muli Yang; Cheng Deng; Wei Liu; | code |
| 1494 | Adaptive Graph Convolutional Recurrent Network For Traffic Forecasting Highlight: In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while pre-defined graph is avoidable. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
LEI BAI; Lina Yao; Can Li; Xianzhi Wang; Can Wang; | |
| 1495 | On Reward-Free Reinforcement Learning With Linear Function Approximation Highlight: In this work, we give both positive and negative results for reward-free RL with linear function approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruosong Wang; Simon S. Du; Lin Yang; Russ R. Salakhutdinov; | |
| 1496 | Robustness Of Community Detection To Random Geometric Perturbations Highlight: We consider the stochastic block model where connection between vertices is perturbed by some latent (and unobserved) random geometric graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sandrine Peche; Vianney Perchet; | |
| 1497 | Learning Outside The Black-Box: The Pursuit Of Interpretable Models Highlight: This paper proposes an algorithm that produces a continuous global interpretation of any given continuous black-box function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Crabbe; Yao Zhang; William Zame; Mihaela van der Schaar; | |
| 1498 | Breaking Reversibility Accelerates Langevin Dynamics For Non-Convex Optimization Highlight: We study two variants that are based on non-reversible Langevin diffusions: the underdamped Langevin dynamics (ULD) and the Langevin dynamics with a non-symmetric drift (NLD). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xuefeng GAO; Mert Gurbuzbalaban; Lingjiong Zhu; | |
| 1499 | Robust Large-margin Learning In Hyperbolic Space Highlight: In this paper, we present, to our knowledge, the first theoretical guarantees for learning a classifier in hyperbolic rather than Euclidean space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Melanie Weber; Manzil Zaheer; Ankit Singh Rawat; Aditya K. Menon; Sanjiv Kumar; | |
| 1500 | Replica-Exchange Nos\'e-Hoover Dynamics For Bayesian Learning On Large Datasets Highlight: In this paper, we present a new practical method for Bayesian learning that can rapidly draw representative samples from complex posterior distributions with multiple isolated modes in the presence of mini-batch noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rui Luo; Qiang Zhang; Yaodong Yang; Jun Wang; | |
| 1501 | Adversarially Robust Few-Shot Learning: A Meta-Learning Approach Highlight: The goal of our work is to produce networks which both perform well at few-shot classification tasks and are simultaneously robust to adversarial examples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Micah Goldblum; Liam Fowl; Tom Goldstein; | |
| 1502 | Neural Anisotropy Directions Highlight: In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guillermo Ortiz-Jimenez; Apostolos Modas; Seyed-Mohsen Moosavi-Dezfooli; Pascal Frossard; | |
| 1503 | Digraph Inception Convolutional Networks Highlight: In this paper, we theoretically extend spectral-based graph convolution to digraphs and derive a simplified form using personalized PageRank. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zekun Tong; Yuxuan Liang; Changsheng Sun; Xinke Li; David Rosenblum; Andrew Lim; | |
| 1504 | PAC-Bayesian Bound For The Conditional Value At Risk Highlight: This paper presents a generalization bound for learning algorithms that minimize the $\textsc{CVaR}$ of the empirical loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zakaria Mhammedi; Benjamin Guedj; Robert C. Williamson; | |
| 1505 | Stochastic Stein Discrepancies Highlight: To address this deficiency, we show that stochastic Stein discrepancies (SSDs) based on subsampled approximations of the Stein operator inherit the convergence control properties of standard SDs with probability 1. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jackson Gorham; Anant Raj; Lester Mackey; | |
| 1506 | On The Role Of Sparsity And DAG Constraints For Learning Linear DAGs Highlight: In this paper, we study the asymptotic role of the sparsity and DAG constraints for learning DAG models in the linear Gaussian and non-Gaussian cases, and investigate their usefulness in the finite sample regime. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ignavier Ng; AmirEmad Ghassami; Kun Zhang; | |
| 1507 | Cream Of The Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search Highlight: To alleviate this problem, we present a simple yet effective architecture distillation method. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Houwen Peng; Hao Du; Hongyuan Yu; QI LI; Jing Liao; Jianlong Fu; | code |
| 1508 | Fair Multiple Decision Making Through Soft Interventions Highlight: In this paper, we propose an approach that learns multiple classifiers and achieves fairness for all of them simultaneously, by treating each decision model as a soft intervention and inferring the post-intervention distributions to formulate the loss function as well as the fairness constraints. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaowei Hu; Yongkai Wu; Lu Zhang; Xintao Wu; | |
| 1509 | Representation Learning For Integrating Multi-domain Outcomes To Optimize Individualized Treatment Highlight: To address these challenges, we propose an integrated learning framework that can simultaneously learn patients’ underlying mental states and recommend optimal treatments for each individual. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuan Chen; Donglin Zeng; Tianchen Xu; Yuanjia Wang; | |
| 1510 | Learning To Play No-Press Diplomacy With Best Response Policy Iteration Highlight: We propose a simple yet effective approximate best response operator, designed to handle large combinatorial action spaces and simultaneous moves. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thomas Anthony; Tom Eccles; Andrea Tacchetti; J�nos Kram�r; Ian Gemp; Thomas Hudson; Nicolas Porcel; Marc Lanctot; Julien Perolat; Richard Everett; Satinder Singh; Thore Graepel; Yoram Bachrach; | |
| 1511 | Inverse Learning Of Symmetries Highlight: We propose to learn the symmetry transformation with a model consisting of two latent subspaces, where the first subspace captures the target and the second subspace the remaining invariant information. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mario Wieser; Sonali Parbhoo; Aleksander Wieczorek; Volker Roth; | |
| 1512 | DiffGCN: Graph Convolutional Networks Via Differential Operators And Algebraic Multigrid Pooling Highlight: In this work we propose novel approaches for graph convolution, pooling and unpooling, inspired from finite differences and algebraic multigrid frameworks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Moshe Eliasof; Eran Treister; | |
| 1513 | Distributed Newton Can Communicate Less And Resist Byzantine Workers Highlight: We propose an iterative approximate Newton-type algorithm, where the worker machines communicate \emph{only once} per iteration with the central machine. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Avishek Ghosh; Raj Kumar Maity; Arya Mazumdar; | |
| 1514 | Efficient Nonmyopic Bayesian Optimization Via One-Shot Multi-Step Trees Highlight: In this paper, we provide the first efficient implementation of general multi-step lookahead Bayesian optimization, formulated as a sequence of nested optimization problems within a multi-step scenario tree. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shali Jiang; Daniel Jiang; Maximilian Balandat; Brian Karrer; Jacob Gardner; Roman Garnett; | |
| 1515 | Effective Diversity In Population Based Reinforcement Learning Highlight: In this paper, we introduce an approach to optimize all members of a population simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jack Parker-Holder; Aldo Pacchiano; Krzysztof M. Choromanski; Stephen J. Roberts; | |
| 1516 | Elastic-InfoGAN: Unsupervised Disentangled Representation Learning In Class-Imbalanced Data Highlight: We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Utkarsh Ojha; Krishna Kumar Singh; Cho-Jui Hsieh; Yong Jae Lee; | |
| 1517 | Direct Policy Gradients: Direct Optimization Of Policies In Discrete Action Spaces Highlight: We show how to combine these techniques to yield a reinforcement learning algorithm that approximates a policy gradient by finding trajectories that optimize a random objective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guy Lorberbom; Chris J. Maddison; Nicolas Heess; Tamir Hazan; Daniel Tarlow; | |
| 1518 | Hybrid Models For Learning To Branch Highlight: In this work, we ask two key questions. First, in a more realistic setting where only a CPU is available, is the GNN model still competitive? Second, can we devise an alternate computationally inexpensive model that retains the predictive power of the GNN architecture? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Prateek Gupta; Maxime Gasse; Elias Khalil; Pawan Mudigonda; Andrea Lodi; Yoshua Bengio; | code |
| 1519 | WoodFisher: Efficient Second-Order Approximation For Neural Network Compression Highlight: Our work considers this question, examines the accuracy of existing approaches, and proposes a method called WoodFisher to compute a faithful and efficient estimate of the inverse Hessian. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sidak Pal Singh; Dan Alistarh; | |
| 1520 | Bi-level Score Matching For Learning Energy-based Latent Variable Models Highlight: This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bi-level optimization problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fan Bao; Chongxuan LI; Taufik Xu; Hang Su; Jun Zhu; Bo Zhang; | |
| 1521 | Counterfactual Contrastive Learning For Weakly-Supervised Vision-Language Grounding Highlight: In this paper, we propose a novel Counterfactual Contrastive Learning (CCL) to develop sufficient contrastive training between counterfactual positive and negative results, which are based on robust and destructive counterfactual transformations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhu Zhang; Zhou Zhao; Zhijie Lin; jieming zhu; Xiuqiang He; | |
| 1522 | Decision Trees As Partitioning Machines To Characterize Their Generalization Properties Highlight: We introduce the notion of partitioning function, and we relate it to the growth function and to the VC dimension. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jean-Samuel Leboeuf; Fr�d�ric LeBlanc; Mario Marchand; | |
| 1523 | Learning To Prove Theorems By Learning To Generate Theorems Highlight: To address this limitation, we propose to learn a neural generator that automatically synthesizes theorems and proofs for the purpose of training a theorem prover. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mingzhe Wang; Jia Deng; | |
| 1524 | 3D Self-Supervised Methods For Medical Imaging Highlight: In this work, we leverage these techniques, and we propose 3D versions for five different self-supervised methods, in the form of proxy tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aiham Taleb; Winfried Loetzsch; Noel Danz; Julius Severin; Thomas Gaertner; Benjamin Bergner; Christoph Lippert; | |
| 1525 | Bayesian Filtering Unifies Adaptive And Non-adaptive Neural Network Optimization Methods Highlight: We formulate the problem of neural network optimization as Bayesian filtering, where the observations are backpropagated gradients. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Laurence Aitchison; | |
| 1526 | Worst-Case Analysis For Randomly Collected Data Highlight: We introduce a framework for statistical estimation that leverages knowledge of how samples are collected but makes no distributional assumptions on the data values. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Justin Chen; Gregory Valiant; Paul Valiant; | |
| 1527 | Truthful Data Acquisition Via Peer Prediction Highlight: We consider the problem of purchasing data for machine learning or statistical estimation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yiling Chen; Yiheng Shen; Shuran Zheng; | |
| 1528 | Learning Robust Decision Policies From Observational Data Highlight: In this paper, we develop a method for learning policies that reduce tails of the cost distribution at a specified level and, moreover, provide a statistically valid bound on the cost of each decision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Muhammad Osama; Dave Zachariah; Peter Stoica; | |
| 1529 | Byzantine Resilient Distributed Multi-Task Learning Highlight: In this paper, we present an approach for Byzantine resilient distributed multi-task learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiani Li; Waseem Abbas; Xenofon Koutsoukos; | |
| 1530 | Reinforcement Learning In Factored MDPs: Oracle-Efficient Algorithms And Tighter Regret Bounds For The Non-Episodic Setting Highlight: We propose two near-optimal and oracle-efficient algorithms for FMDPs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziping Xu; Ambuj Tewari; | |
| 1531 | Improving Model Calibration With Accuracy Versus Uncertainty Optimization Highlight: We propose an optimization method that leverages the relationship between accuracy and uncertainty as an anchor for uncertainty calibration. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ranganath Krishnan; Omesh Tickoo; | |
| 1532 | The Convolution Exponential And Generalized Sylvester Flows Highlight: This paper introduces a new method to build linear flows, by taking the exponential of a linear transformation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emiel Hoogeboom; Victor Garcia Satorras; Jakub Tomczak; Max Welling; | |
| 1533 | An Improved Analysis Of Stochastic Gradient Descent With Momentum Highlight: In this work, we show that SGDM converges as fast as SGD for smooth objectives under both strongly convex and nonconvex settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yanli Liu; Yuan Gao; Wotao Yin; | |
| 1534 | Precise Expressions For Random Projections: Low-rank Approximation And Randomized Newton Highlight: We exploit recent developments in the spectral analysis of random matrices to develop novel techniques that provide provably accurate expressions for the expected value of random projection matrices obtained via sketching. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michal Derezinski; Feynman T. Liang; Zhenyu Liao; Michael W. Mahoney; | |
| 1535 | The MAGICAL Benchmark For Robust Imitation Highlight: This paper presents the MAGICAL benchmark suite, which permits systematic evaluation of generalisation by quantifying robustness to different kinds of distribution shift that an IL algorithm is likely to encounter in practice. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sam Toyer; Rohin Shah; Andrew Critch; Stuart Russell; | code |
| 1536 | X-CAL: Explicit Calibration For Survival Analysis Highlight: We develop explicit calibration (X-CAL), which turns D-CALIBRATION into a differentiable objective that can be used in survival modeling alongside maximum likelihood estimation and other objectives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mark Goldstein; Xintian Han; Aahlad Manas Puli; Adler Perotte ; Rajesh Ranganath; | |
| 1537 | Decentralized Accelerated Proximal Gradient Descent Highlight: In this paper, we study the decentralized composite optimization problem with a non-smooth regularization term. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haishan Ye; Ziang Zhou; Luo Luo; Tong Zhang; | |
| 1538 | Making Non-Stochastic Control (Almost) As Easy As Stochastic Highlight: In this paper, we show that the same regret rate (against a suitable benchmark) is attainable even in the considerably more general non-stochastic control model, where the system is driven by \emph{arbitrary adversarial} noise \citep{agarwal2019online}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Max Simchowitz; | |
| 1539 | BERT Loses Patience: Fast And Robust Inference With Early Exit Highlight: In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model (PLM). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wangchunshu Zhou; Canwen Xu; Tao Ge; Julian McAuley; Ke Xu; Furu Wei; | |
| 1540 | Optimal And Practical Algorithms For Smooth And Strongly Convex Decentralized Optimization Highlight: We propose two new algorithms for this decentralized optimization problem and equip them with complexity guarantees. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dmitry Kovalev; Adil SALIM; Peter Richtarik; | |
| 1541 | BAIL: Best-Action Imitation Learning For Batch Deep Reinforcement Learning Highlight: We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xinyue Chen; Zijian Zhou; Zheng Wang; Che Wang; Yanqiu Wu; Keith Ross; | |
| 1542 | Regularizing Towards Permutation Invariance In Recurrent Models Highlight: We show that RNNs can be regularized towards permutation invariance, and that this can result in compact models, as compared to non-recursive architectures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edo Cohen-Karlik; Avichai Ben David; Amir Globerson; | |
| 1543 | What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes Highlight: We present a novel form of explanation for Reinforcement Learning, based around the notion of intended outcome. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Herman Ho-Man Yau; Chris Russell; Simon Hadfield; | |
| 1544 | Batch Normalization Provably Avoids Ranks Collapse For Randomly Initialised Deep Networks Highlight: In this work we highlight the fact that batch normalization is an effective strategy to avoid rank collapse for both linear and ReLU networks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hadi Daneshmand; Jonas Kohler; Francis Bach; Thomas Hofmann; Aurelien Lucchi; | |
| 1545 | Choice Bandits Highlight: We propose an algorithm for choice bandits, termed Winner Beats All (WBA), with distribution dependent $O(\log T)$ regret bound under all these choice models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arpit Agarwal; Nicholas Johnson; Shivani Agarwal; | |
| 1546 | What If Neural Networks Had SVDs? Highlight: We present an algorithm that is fast enough to speed up several matrix operations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Mathiasen; Frederik Hvilsh�j; Jakob R�dsgaard J�rgensen; Anshul Nasery; Davide Mottin; | |
| 1547 | A Matrix Chernoff Bound For Markov Chains And Its Application To Co-occurrence Matrices Highlight: We prove a Chernoff-type bound for sums of matrix-valued random variables sampled via a regular (aperiodic and irreducible) finite Markov chain. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiezhong Qiu; Chi Wang; Ben Liao; Richard Peng; Jie Tang; | |
| 1548 | CoMIR: Contrastive Multimodal Image Representation For Registration Highlight: We propose contrastive coding to learn shared, dense image representations, referred to as CoMIRs (Contrastive Multimodal Image Representations). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicolas Pielawski; Elisabeth Wetzer; Johan �fverstedt; Jiahao Lu; Carolina W�hlby; Joakim Lindblad; Natasa Sladoje; | code |
| 1549 | Ensuring Fairness Beyond The Training Data Highlight: In this work, we develop classifiers that are fair not only with respect to the training distribution but also for a class of distributions that are weighted perturbations of the training samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Debmalya Mandal; Samuel Deng; Suman Jana; Jeannette Wing; Daniel J. Hsu; | |
| 1550 | How Do Fair Decisions Fare In Long-term Qualification? Highlight: In this work, we study the dynamics of population qualification and algorithmic decisions under a partially observed Markov decision problem setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xueru Zhang; Ruibo Tu; Yang Liu; mingyan liu; Hedvig Kjellstrom; Kun Zhang; Cheng Zhang; | |
| 1551 | Pre-training Via Paraphrasing Highlight: We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mike Lewis; Marjan Ghazvininejad; Gargi Ghosh; Armen Aghajanyan; Sida Wang; Luke Zettlemoyer; | |
| 1552 | GCN Meets GPU: Decoupling �When To Sample� From �How To Sample� Highlight: By decoupling the frequency of sampling from the sampling strategy, we propose LazyGCN, a general yet effective framework that can be integrated with any sampling strategy to substantially improve the training time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Morteza Ramezani; Weilin Cong; Mehrdad Mahdavi; Anand Sivasubramaniam; Mahmut Kandemir; | |
| 1553 | Continual Learning Of A Mixed Sequence Of Similar And Dissimilar Tasks Highlight: This paper proposes such a technique to learn both types of tasks in the same network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zixuan Ke; Bing Liu; Xingchang Huang; | |
| 1554 | All Your Loss Are Belong To Bayes Highlight: In this paper, we rely on a broader view of proper composite losses and a recent construct from information geometry, source functions, whose fitting alleviates constraints faced by canonical links. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christian Walder; Richard Nock; | |
| 1555 | HAWQ-V2: Hessian Aware Trace-Weighted Quantization Of Neural Networks Highlight: Here, we present HAWQ-V2 which addresses these shortcomings. For (i), we theoretically prove that the right sensitivity metric is the average Hessian trace, instead of just top Hessian eigenvalue. For (ii), we develop a Pareto frontier based method for automatic bit precision selection of different layers without any manual intervention. For (iii), we develop the first Hessian based analysis for mixed-precision activation quantization, which is very beneficial for object detection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhen Dong; Zhewei Yao; Daiyaan Arfeen; Amir Gholami; Michael W. Mahoney; Kurt Keutzer; | |
| 1556 | Sample-Efficient Reinforcement Learning Of Undercomplete POMDPs Highlight: In particular, we present a sample-efficient algorithm, OOM-UCB, for episodic finite undercomplete POMDPs, where the number of observations is larger than the number of latent states and where exploration is essential for learning, thus distinguishing our results from prior works. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chi Jin; Sham Kakade; Akshay Krishnamurthy; Qinghua Liu; | |
| 1557 | Non-Convex SGD Learns Halfspaces With Adversarial Label Noise Highlight: We study the problem of agnostically learning homogeneous halfspaces in the distribution-specific PAC model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilias Diakonikolas; Vasilis Kontonis; Christos Tzamos; Nikos Zarifis; | |
| 1558 | A Tight Lower Bound And Efficient Reduction For Swap Regret Highlight: Besides, we present a computationally efficient reduction method that converts no-external-regret algorithms to no-swap-regret algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shinji Ito; | |
| 1559 | DisCor: Corrective Feedback In Reinforcement Learning Via Distribution Correction Highlight: In this paper, we study how RL methods based on bootstrapping-based Q-learning can suffer from a pathological interaction between function approximation and the data distribution used to train the Q-function: with standard supervised learning, online data collection should induce corrective feedback, where new data corrects mistakes in old predictions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aviral Kumar; Abhishek Gupta; Sergey Levine; | |
| 1560 | OTLDA: A Geometry-aware Optimal Transport Approach For Topic Modeling Highlight: We present an optimal transport framework for learning topics from textual data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Viet Huynh; He Zhao; Dinh Phung; | |
| 1561 | Measuring Robustness To Natural Distribution Shifts In Image Classification Highlight: We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rohan Taori; Achal Dave; Vaishaal Shankar; Nicholas Carlini; Benjamin Recht; Ludwig Schmidt; | |
| 1562 | Can I Trust My Fairness Metric? Assessing Fairness With Unlabeled Data And Bayesian Inference Highlight: We propose a general Bayesian framework that can augment labeled data with unlabeled data to produce more accurate and lower-variance estimates compared to methods based on labeled data alone. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Disi Ji; Padhraic Smyth; Mark Steyvers; | |
| 1563 | RandAugment: Practical Automated Data Augmentation With A Reduced Search Space Highlight: In this work, we rethink the process of designing automated data augmentation strategies. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ekin Dogus Cubuk; Barret Zoph; Jon Shlens; Quoc Le; | |
| 1564 | Asymptotic Normality And Confidence Intervals For Derivatives Of 2-layers Neural Network In The Random Features Model Highlight: We show that a weighted average of the derivatives of the trained NN at the observed data is asymptotically normal, in a setting with Lipschitz activation functions in a linear regression response with Gaussian features under possibly non-linear perturbations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yiwei Shen; Pierre C Bellec; | |
| 1565 | DisARM: An Antithetic Gradient Estimator For Binary Latent Variables Highlight: We show that ARM can be improved by analytically integrating out the randomness introduced by the augmentation process, guaranteeing substantial variance reduction. Our estimator, DisARM, is simple to implement and has the same computational cost as ARM. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhe Dong; Andriy Mnih; George Tucker; | |
| 1566 | Variational Inference For Graph Convolutional Networks In The Absence Of Graph Data And Adversarial Settings Highlight: We propose a framework that lifts the capabilities of graph convolutional networks (GCNs) to scenarios where no input graph is given and increases their robustness to adversarial attacks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pantelis Elinas; Edwin V. Bonilla; Louis Tiao; | |
| 1567 | Supervised Contrastive Learning Highlight: In this work, we extend the self-supervised batch contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Prannay Khosla; Piotr Teterwak; Chen Wang; Aaron Sarna; Yonglong Tian; Phillip Isola; Aaron Maschinot; Ce Liu; Dilip Krishnan; | code |
| 1568 | Learning Optimal Representations With The Decodable Information Bottleneck Highlight: We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yann Dubois; Douwe Kiela; David J. Schwab; Ramakrishna Vedantam; | |
| 1569 | Meta-trained Agents Implement Bayes-optimal Agents Highlight: Inspired by ideas from theoretical computer science, we show that meta-learned and Bayes-optimal agents not only behave alike, but they even share a similar computational structure, in the sense that one agent system can approximately simulate the other. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vladimir Mikulik; Gr�goire Del�tang; Tom McGrath; Tim Genewein; Miljan Martic; Shane Legg; Pedro Ortega; | |
| 1570 | Learning Agent Representations For Ice Hockey Highlight: We introduce a novel player representation via player generation framework where a variational encoder embeds player information with latent variables. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guiliang Liu; Oliver Schulte; Pascal Poupart; Mike Rudd; Mehrsan Javan; | |
| 1571 | Weak Form Generalized Hamiltonian Learning Highlight: We present a method for learning generalized Hamiltonian decompositions of ordinary differential equations given a set of noisy time series measurements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kevin Course; Trefor Evans; Prasanth Nair; | |
| 1572 | Neural Non-Rigid Tracking Highlight: We introduce a novel, end-to-end learnable, differentiable non-rigid tracker that enables state-of-the-art non-rigid reconstruction by a learned robust optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aljaz Bozic; Pablo Palafox; Michael Zollh�fer; Angela Dai; Justus Thies; Matthias Niessner; | |
| 1573 | Collegial Ensembles Highlight: In this work, we investigate a form of over-parameterization achieved through ensembling, where we define collegial ensembles (CE) as the aggregation of multiple independent models with identical architectures, trained as a single model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Etai Littwin; Ben Myara; Sima Sabah; Joshua Susskind; Shuangfei Zhai; Oren Golan; | |
| 1574 | ICNet: Intra-saliency Correlation Network For Co-Saliency Detection Highlight: In this paper, we propose an Intra-saliency Correlation Network (ICNet) to extract intra-saliency cues from the single image saliency maps (SISMs) predicted by any off-the-shelf SOD method, and obtain inter-saliency cues by correlation techniques. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wen-Da Jin; Jun Xu; Ming-Ming Cheng; Yi Zhang; Wei Guo; | code |
| 1575 | Improved Variational Bayesian Phylogenetic Inference With Normalizing Flows Highlight: In this paper, we propose a new type of VBPI, VBPI-NF, as a first step to empower phylogenetic posterior estimation with deep learning techniques. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Cheng Zhang; | |
| 1576 | Deep Metric Learning With Spherical Embedding Highlight: In this paper, we first investigate the effect of the embedding norm for deep metric learning with angular distance, and then propose a spherical embedding constraint (SEC) to regularize the distribution of the norms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dingyi Zhang; Yingming Li; Zhongfei Zhang; | |
| 1577 | Preference-based Reinforcement Learning With Finite-Time Guarantees Highlight: If preferences are stochastic, and the preference probability relates to the hidden reward values, we present algorithms for PbRL, both with and without a simulator, that are able to identify the best policy up to accuracy $\varepsilon$ with high probability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yichong Xu; Ruosong Wang; Lin Yang; Aarti Singh; Artur Dubrawski; | |
| 1578 | AdaBelief Optimizer: Adapting Stepsizes By The Belief In Observed Gradients Highlight: We propose AdaBelief to simultaneously achieve three goals: fast convergence as in adaptive methods, good generalization as in SGD, and training stability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Juntang Zhuang; Tommy Tang; Yifan Ding; Sekhar C. Tatikonda; Nicha Dvornek; Xenophon Papademetris; James Duncan; | |
| 1579 | Interpretable Sequence Learning For Covid-19 Forecasting Highlight: We propose a novel approach that integrates machine learning into compartmental disease modeling (e.g., SEIR) to predict the progression of COVID-19. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sercan Arik; Chun-Liang Li; Jinsung Yoon; Rajarishi Sinha; Arkady Epshteyn; Long Le; Vikas Menon; Shashank Singh; Leyou Zhang; Martin Nikoltchev; Yash Sonthalia; Hootan Nakhost; Elli Kanal; Tomas Pfister; | |
| 1580 | Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding Highlight: Under this less pessimistic model of one-decision confounding, we propose an efficient loss-minimization-based procedure for computing worst-case bounds, and prove its statistical consistency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongseok Namkoong; Ramtin Keramati; Steve Yadlowsky; Emma Brunskill; | |
| 1581 | Modern Hopfield Networks And Attention For Immune Repertoire Classification Highlight: In this work, we present our novel method DeepRC that integrates transformer-like attention, or equivalently modern Hopfield networks, into deep learning architectures for massive MIL such as immune repertoire classification. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Widrich; Bernhard Sch�fl; Milena Pavlovic; Hubert Ramsauer; Lukas Gruber; Markus Holzleitner; Johannes Brandstetter; Geir Kjetil Sandve; Victor Greiff; Sepp Hochreiter; G�nter Klambauer; | code |
| 1582 | One Ring To Rule Them All: Certifiably Robust Geometric Perception With Outliers Highlight: We propose the first general and practical framework to design certifiable algorithms for robust geometric perception in the presence of a large amount of outliers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Heng Yang; Luca Carlone; | |
| 1583 | Task-Robust Model-Agnostic Meta-Learning Highlight: We present an algorithm to solve the proposed min-max problem, and show that it converges to an $\epsilon$-accurate point at the optimal rate of $\mathcal{O}(1/\epsilon^2)$ in the convex setting and to an $(\epsilon, \delta)$-stationary point at the rate of $\mathcal{O}(\max\{1/\epsilon^5, 1/\delta^5\})$ in nonconvex settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Liam Collins; Aryan Mokhtari; Sanjay Shakkottai; | |
| 1584 | R-learning In Actor-critic Model Offers A Biologically Relevant Mechanism For Sequential Decision-making Highlight: In this work, we build interpretable deep actor-critic models to show that R-learning – a reinforcement learning (RL) approach balancing short-term and long-term rewards – is consistent with the way real-life agents may learn making stay-or-leave decisions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sergey Shuvaev; Sarah Starosta; Duda Kvitsiani; Adam Kepecs; Alexei Koulakov; | |
| 1585 | Revisiting Frank-Wolfe For Polytopes: Strict Complementarity And Sparsity Highlight: We then revisit the addition of a strict complementarity assumption already considered in Wolfe’s classical book \cite{Wolfe1970}, and prove that under this condition, the Frank-Wolfe method with away-steps and line-search converges linearly with rate that depends explicitly only on the dimension of the optimal face, hence providing a significant improvement in case the optimal solution is sparse. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dan Garber; | |
| 1586 | Fast Convergence Of Langevin Dynamics On Manifold: Geodesics Meet Log-Sobolev Highlight: Our work generalizes the results of \cite{VW19} where f is defined on a manifold M rather than Rn. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiao Wang; Qi Lei; Ioannis Panageas; | |
| 1587 | Tensor Completion Made Practical Highlight: In this paper we introduce a new variant of alternating minimization, which in turn is inspired by understanding how the progress measures that guide convergence of alternating minimization in the matrix setting need to be adapted to the tensor setting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Allen Liu; Ankur Moitra; | |
| 1588 | Optimization And Generalization Analysis Of Transduction Through Gradient Boosting And Application To Multi-scale Graph Neural Networks Highlight: In this study, we derive the optimization and generalization guarantees of transductive learning algorithms that include multi-scale GNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kenta Oono; Taiji Suzuki; | code |
| 1589 | Content Provider Dynamics And Coordination In Recommendation Ecosystems Highlight: In this work, we investigate the dynamics of content creation using a game-theoretic lens. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Omer Ben-Porat; Itay Rosenberg; Moshe Tennenholtz; | |
| 1590 | Almost Surely Stable Deep Dynamics Highlight: We introduce a method for learning provably stable deep neural network based dynamic models from observed data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nathan Lawrence; Philip Loewen; Michael Forbes; Johan Backstrom; Bhushan Gopaluni; | |
| 1591 | Experimental Design For MRI By Greedy Policy Search Highlight: We propose to learn experimental design strategies for accelerated MRI with policy gradient methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tim Bakker; Herke van Hoof; Max Welling; | |
| 1592 | Expert-Supervised Reinforcement Learning For Offline Policy Learning And Evaluation Highlight: To overcome these issues, we propose an Expert-Supervised RL (ESRL) framework which uses uncertainty quantification for offline policy learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Aaron Sonabend; Junwei Lu; Leo Anthony Celi; Tianxi Cai; Peter Szolovits; | |
| 1593 | ColdGANs: Taming Language GANs With Cautious Sampling Strategies Highlight: In this work, we show how the most popular sampling method results in unstable training for language GANs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thomas Scialom; Paul-Alexis Dray; Sylvain Lamprier; Benjamin Piwowarski; Jacopo Staiano; | |
| 1594 | Hedging In Games: Faster Convergence Of External And Swap Regrets Highlight: We consider the setting where players run the Hedge algorithm or its optimistic variant \cite{syrgkanis2015fast} to play an n-action game repeatedly for T rounds. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xi Chen; Binghui Peng; | |
| 1595 | The Origins And Prevalence Of Texture Bias In Convolutional Neural Networks Highlight: By taking less aggressive random crops at training time and applying simple, naturalistic augmentation (color distortion, noise, and blur), we train models that classify ambiguous images by shape a majority of the time, and outperform baselines on out-of-distribution test sets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Katherine Hermann; Ting Chen; Simon Kornblith; | |
| 1596 | Time-Reversal Symmetric ODE Network Highlight: In this paper, we propose a novel loss function that measures how well our ordinary differential equation (ODE) networks comply with this time-reversal symmetry; it is formally defined by the discrepancy in the time evolutions of ODE networks between forward and backward dynamics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
In Huh; Eunho Yang; Sung Ju Hwang; Jinwoo Shin; | |
| 1597 | Provable Overlapping Community Detection In Weighted Graphs Highlight: In this paper, we provide a provable method to detect overlapping communities in weighted graphs without explicitly making the pure nodes assumption. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jimit Majmudar; Stephen Vavasis; | |
| 1598 | Fast Unbalanced Optimal Transport On A Tree Highlight: This study examines the time complexities of the unbalanced optimal transport problems from an algorithmic perspective for the first time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ryoma Sato; Makoto Yamada; Hisashi Kashima; | |
| 1599 | Acceleration With A Ball Optimization Oracle Highlight: Perhaps surprisingly, this is not optimal: we design an accelerated algorithm which attains an epsilon-approximate minimizer with roughly r^{-2/3} \log(1/epsilon) oracle queries, and give a matching lower bound. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yair Carmon; Arun Jambulapati; Qijia Jiang; Yujia Jin; Yin Tat Lee; Aaron Sidford; Kevin Tian; | |
| 1600 | Avoiding Side Effects By Considering Future Tasks Highlight: To alleviate the burden on the reward designer, we propose an algorithm to automatically generate an auxiliary reward function that penalizes side effects. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Victoria Krakovna; Laurent Orseau; Richard Ngo; Miljan Martic; Shane Legg; | |
| 1601 | Handling Missing Data With Graph Representation Learning Highlight: Here we propose GRAPE, a framework for feature imputation as well as label prediction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiaxuan You; Xiaobai Ma; Yi Ding; Mykel J. Kochenderfer; Jure Leskovec; | |
| 1602 | Improving Auto-Augment Via Augmentation-Wise Weight Sharing Highlight: In this paper, we dive into the dynamics of augmented training of the model. This inspires us to design a powerful and efficient proxy task based on the Augmentation-Wise Weight Sharing (AWS) to form a fast yet accurate evaluation process in an elegant way. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Keyu Tian; CHEN LIN; Ming Sun; Luping Zhou; Junjie Yan; Wanli Ouyang; | |
| 1603 | MMA Regularization: Decorrelating Weights Of Neural Networks By Maximizing The Minimal Angles Highlight: Inspired by the well-known Tammes problem, we propose a novel diversity regularization method to address this issue, which makes the normalized weight vectors of neurons or filters distributed on a hypersphere as uniformly as possible, through maximizing the minimal pairwise angles (MMA). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhennan Wang; Canqun Xiang; Wenbin Zou; Chen Xu; | code |
| 1604 | HRN: A Holistic Approach To One Class Learning Highlight: This paper proposes an entirely different approach based on a novel regularization, called holistic regularization (or H-regularization), which enables the system to consider the data holistically, not to produce a model that biases towards some features. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenpeng Hu; Mengyu Wang; Qi Qin; Jinwen Ma; Bing Liu; | |
| 1605 | The Generalized Lasso With Nonlinear Observations And Generative Priors Highlight: In this paper, we study the problem of signal estimation from noisy non-linear measurements when the unknown $n$-dimensional signal is in the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhaoqiang Liu; Jonathan Scarlett; | |
| 1606 | Fair Regression Via Plug-in Estimator And Recalibration With Statistical Guarantees Highlight: We study the problem of learning an optimal regression function subject to a fairness constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Evgenii Chzhen; Christophe Denis; Mohamed Hebiri; Luca Oneto; Massimiliano Pontil; | |
| 1607 | Modeling Shared Responses In Neuroimaging Studies Through MultiView ICA Highlight: We propose a novel MultiView Independent Component Analysis (ICA) model for group studies, where data from each subject are modeled as a linear combination of shared independent sources plus noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hugo Richard; Luigi Gresele; Aapo Hyvarinen; Bertrand Thirion; Alexandre Gramfort; Pierre Ablin; | |
| 1608 | Efficient Planning In Large MDPs With Weak Linear Function Approximation Highlight: We consider the planning problem in MDPs using linear value function approximation with only weak requirements: low approximation error for the optimal value function, and a small set of “core” states whose features span those of other states. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Roshan Shariff; Csaba Szepesvari; | |
| 1609 | Efficient Learning Of Generative Models Via Finite-Difference Score Matching Highlight: To improve computing efficiency, we rewrite the SM objective and its variants in terms of directional derivatives, and present a generic strategy to efficiently approximate any-order directional derivative with finite difference~(FD). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianyu Pang; Taufik Xu; Chongxuan LI; Yang Song; Stefano Ermon; Jun Zhu; | |
| 1610 | Semialgebraic Optimization For Lipschitz Constants Of ReLU Networks Highlight: We introduce a semidefinite programming hierarchy to estimate the global and local Lipschitz constant of a multiple layer deep neural network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tong Chen; Jean B. Lasserre; Victor Magron; Edouard Pauwels; | |
| 1611 | Linear-Sample Learning Of Low-Rank Distributions Highlight: For all of them, we show that learning $k\times k$, rank-$r$, matrices to normalized $L_1$ distance $\epsilon$ requires $\Omega(\frac{kr}{\epsilon^2})$ samples, and propose an algorithm that uses ${\cal O}(\frac{kr}{\epsilon^2}\log^2\frac r\epsilon)$ samples, a number linear in the high dimension, and nearly linear in the, typically low, rank. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ayush Jain; Alon Orlitsky; | |
| 1612 | Transferable Calibration With Lower Bias And Variance In Domain Adaptation Highlight: In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ximei Wang; Mingsheng Long; Jianmin Wang; Michael Jordan; | |
| 1613 | Generalization Bound Of Globally Optimal Non-convex Neural Network Training: Transportation Map Estimation By Infinite Dimensional Langevin Dynamics Highlight: We introduce a new theoretical framework to analyze deep learning optimization with connection to its generalization error. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Taiji Suzuki; | |
| 1614 | Online Bayesian Goal Inference For Boundedly Rational Planning Agents Highlight: Here we present an architecture capable of inferring an agent’s goals online from both optimal and non-optimal sequences of actions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tan Zhi-Xuan; Jordyn Mann; Tom Silver; Josh Tenenbaum; Vikash Mansinghka; | |
| 1615 | BayReL: Bayesian Relational Learning For Multi-omics Data Integration Highlight: In this paper, we develop a novel Bayesian representation learning method that infers the relational interactions across multi-omics data types. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ehsan Hajiramezanali; Arman Hasanzadeh; Nick Duffield; Krishna Narayanan; Xiaoning Qian; | |
| 1616 | Weakly Supervised Deep Functional Maps For Shape Matching Highlight: Furthermore, we propose a novel framework designed for both full-to-full as well as partial to full shape matching that achieves state of the art results on several benchmark datasets outperforming, even the fully supervised methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Abhishek Sharma; Maks Ovsjanikov; | code |
| 1617 | Domain Adaptation With Conditional Distribution Matching And Generalized Label Shift Highlight: In this paper, we propose a new assumption, \textit{generalized label shift} ($\glsa$), to improve robustness against mismatched label distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Remi Tachet des Combes; Han Zhao; Yu-Xiang Wang; Geoffrey J. Gordon; | code |
| 1618 | Rethinking The Value Of Labels For Improving Class-Imbalanced Learning Highlight: We demonstrate, theoretically and empirically, that class-imbalanced learning can significantly benefit in both semi-supervised and self-supervised manners. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuzhe Yang; Zhi Xu; | code |
| 1619 | Provably Robust Metric Learning Highlight: In this paper, we show that existing metric learning algorithms, which focus on boosting the clean accuracy, can result in metrics that are less robust than the Euclidean distance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lu Wang; Xuanqing Liu; Jinfeng Yi; Yuan Jiang; Cho-Jui Hsieh; | |
| 1620 | Iterative Deep Graph Learning For Graph Neural Networks: Better And Robust Node Embeddings Highlight: In this paper, we propose an end-to-end graph learning framework, namely \textbf{I}terative \textbf{D}eep \textbf{G}raph \textbf{L}earning (\alg), for jointly and iteratively learning graph structure and graph embedding. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yu Chen; Lingfei Wu; Mohammed Zaki; | |
| 1621 | COPT: Coordinated Optimal Transport On Graphs Highlight: We introduce COPT, a novel distance metric between graphs defined via an optimization routine, computing a coordinated pair of optimal transport maps simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yihe Dong; Will Sawin; | |
| 1622 | No Subclass Left Behind: Fine-Grained Robustness In Coarse-Grained Classification Problems Highlight: We propose GEORGE, a method to both measure and mitigate hidden stratification even when subclass labels are unknown. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nimit Sohoni; Jared Dunnmon; Geoffrey Angus; Albert Gu; Christopher R�; | |
| 1623 | Model Rubik�s Cube: Twisting Resolution, Depth And Width For TinyNets Highlight: This paper aims to explore the twisting rules for obtaining deep neural networks with minimum model sizes and computational costs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kai Han; Yunhe Wang; Qiulin Zhang; Wei Zhang; Chunjing XU; Tong Zhang; | code |
| 1624 | Self-Adaptive Training: Beyond Empirical Risk Minimization Highlight: In this paper, we observe that model predictions can substantially benefit the training process: self-adaptive training significantly mitigates the overfitting issue and improves generalization over ERM under both random and adversarial noises. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lang Huang; Chao Zhang; Hongyang Zhang; | |
| 1625 | Effective Dimension Adaptive Sketching Methods For Faster Regularized Least-Squares Optimization Highlight: We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Lacotte; Mert Pilanci; | |
| 1626 | Near-Optimal Comparison Based Clustering Highlight: We theoretically show that our approach can exactly recover a planted clustering using a near-optimal number of passive comparisons. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Micha�l Perrot; Pascal Esser; Debarghya Ghoshdastidar; | |
| 1627 | Multi-Task Temporal Shift Attention Networks For On-Device Contactless Vitals Measurement Highlight: We present a video-based and on-device optical cardiopulmonary vital sign measurement approach. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xin Liu; Josh Fromm; Shwetak Patel; Daniel McDuff; | |
| 1628 | A New Convergent Variant Of Q-learning With Linear Function Approximation Highlight: In this work, we identify a novel set of conditions that ensure convergence with probability 1 of Q-learning with linear function approximation, by proposing a two time-scale variation thereof. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Diogo Carvalho; Francisco S. Melo; Pedro Santos; | |
| 1629 | TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation Highlight: To improve the sample efficiency and reduce the variance of REINFORCE, we propose a novel approach, TaylorGAN, which augments the gradient estimation by off-policy update and the first-order Taylor expansion. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chun-Hsing Lin; Siang-Ruei Wu; Hung-yi Lee; Yun-Nung Chen; | |
| 1630 | Neural Networks With Small Weights And Depth-Separation Barriers Highlight: In this paper, we focus on feedforward ReLU networks, and prove fundamental barriers to proving such results beyond depth $4$, by reduction to open problems and natural-proof barriers in circuit complexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gal Vardi; Ohad Shamir; | |
| 1631 | Untangling Tradeoffs Between Recurrence And Self-attention In Artificial Neural Networks Highlight: In this work, we present a formal analysis of how self-attention affects gradient propagation in recurrent networks, and prove that it mitigates the problem of vanishing gradients when trying to capture long-term dependencies by establishing concrete bounds for gradient norms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Giancarlo Kerg; Bhargav Kanuparthi; Anirudh Goyal ALIAS PARTH GOYAL; Kyle Goyette; Yoshua Bengio; Guillaume Lajoie; | |
| 1632 | Dual-Free Stochastic Decentralized Optimization With Variance Reduction Highlight: In this work, we introduce a Decentralized stochastic algorithm with Variance Reduction called DVR. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hadrien Hendrikx; Francis Bach; Laurent Massouli�; | |
| 1633 | Online Learning In Contextual Bandits Using Gated Linear Networks Highlight: We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eren Sezener; Marcus Hutter; David Budden; Jianan Wang; Joel Veness; | |
| 1634 | Throughput-Optimal Topology Design For Cross-Silo Federated Learning Highlight: In this paper we define the problem of topology design for cross-silo federated learning using the theory of max-plus linear systems to compute the system throughput—number of communication rounds per time unit. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Othmane MARFOQ; CHUAN XU; Giovanni Neglia; Richard Vidal; | |
| 1635 | Quantized Variational Inference Highlight: We present Quantized Variational Inference, a new algorithm for Evidence Lower Bound minimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amir Dib; | |
| 1636 | Asymptotically Optimal Exact Minibatch Metropolis-Hastings Highlight: In this paper, we study \emph{minibatch MH} methods, which instead use subsamples to enable scaling. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ruqi Zhang; A. Feder Cooper; Christopher M. De Sa; | |
| 1637 | Learning Search Space Partition For Black-box Optimization Using Monte Carlo Tree Search Highlight: In this paper, we coin LA-MCTS that extends LaNAS to other domains. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Linnan Wang; Rodrigo Fonseca; Yuandong Tian; | |
| 1638 | Feature Shift Detection: Localizing Which Features Have Shifted Via Conditional Distribution Tests Highlight: Thus, we first define a formalization of this problem as multiple conditional distribution hypothesis tests and propose both non-parametric and parametric statistical tests. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sean Kulinski; Saurabh Bagchi; David I. Inouye; | |
| 1639 | Unifying Activation- And Timing-based Learning Rules For Spiking Neural Networks Highlight: In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jinseok Kim; Kyungsu Kim; Jae-Joon Kim; | |
| 1640 | Space-Time Correspondence As A Contrastive Random Walk Highlight: This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Allan Jabri; Andrew Owens; Alexei Efros; | |
| 1641 | The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting With Minimal Space Highlight: We propose an $(\epsilon,\delta)$-differentially private algorithm that approximates $\dist$ within a factor of $(1\pm\gamma)$, and with additive error of $O(\sqrt{\ln(1/\delta)}/\epsilon)$, using space $O(\ln(\ln(u)/\gamma)/\gamma^2)$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Adam Smith; Shuang Song; Abhradeep Thakurta; | |
| 1642 | Exponential Ergodicity Of Mirror-Langevin Diffusions Highlight: Motivated by the problem of sampling from ill-conditioned log-concave distributions, we give a clean non-asymptotic convergence analysis of mirror-Langevin diffusions as introduced in Zhang et al. (2020). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sinho Chewi; Thibaut Le Gouic; Chen Lu; Tyler Maunu; Philippe Rigollet; Austin Stromme; | |
| 1643 | An Efficient Framework For Clustered Federated Learning Highlight: We propose a new framework dubbed the Iterative Federated Clustering Algorithm (IFCA), which alternately estimates the cluster identities of the users and optimizes model parameters for the user clusters via gradient descent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Avishek Ghosh; Jichan Chung; Dong Yin; Kannan Ramchandran; | |
| 1644 | Autoencoders That Don't Overfit Towards The Identity Highlight: In this paper, we consider linear autoencoders, as they facilitate analytic solutions, and first show that denoising / dropout actually prevents the overfitting towards the identity-function only to the degree that it is penalized by the induced L2-norm regularization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Harald Steck; | |
| 1645 | Polynomial-Time Computation Of Optimal Correlated Equilibria In Two-Player Extensive-Form Games With Public Chance Moves And Beyond Highlight: In this paper we significantly refine this complexity threshold by showing that, in two-player games, an optimal correlated equilibrium can be computed in polynomial time, provided that a certain condition is satisfied. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gabriele Farina; Tuomas Sandholm; | |
| 1646 | Parameterized Explainer For Graph Neural Network Highlight: In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dongsheng Luo; Wei Cheng; Dongkuan Xu; Wenchao Yu; Bo Zong; Haifeng Chen; Xiang Zhang; | |
| 1647 | Recursive Inference For Variational Autoencoders Highlight: In this paper, we consider a different approach of building a mixture inference model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minyoung Kim; Vladimir Pavlovic; | |
| 1648 | Flexible Mean Field Variational Inference Using Mixtures Of Non-overlapping Exponential Families Highlight: Yet, I show that using standard mean field variational inference can fail to produce sensible results for models with sparsity-inducing priors, such as the spike-and-slab. Fortunately, such pathological behavior can be remedied as I show that mixtures of exponential family distributions with non-overlapping support form an exponential family. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeffrey Spence; | |
| 1649 | HYDRA: Pruning Adversarially Robust Neural Networks Highlight: To overcome this challenge, we propose to make pruning techniques aware of the robust training objective and let the training objective guide the search for which connections to prune. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vikash Sehwag; Shiqi Wang; Prateek Mittal; Suman Jana; | |
| 1650 | NVAE: A Deep Hierarchical Variational Autoencoder Highlight: We propose Nouveau VAE (NVAE), a deep hierarchical VAE built for image generation using depth-wise separable convolutions and batch normalization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arash Vahdat; Jan Kautz; | |
| 1651 | Can Temporal-Di?erence And Q-Learning Learn Representation? A Mean-Field Theory Highlight: We aim to answer the following questions: When the function approximator is a neural network, how does the associated feature representation evolve? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yufeng Zhang; Qi Cai; Zhuoran Yang; Yongxin Chen; Zhaoran Wang; | |
| 1652 | What Do Neural Networks Learn When Trained With Random Labels? Highlight: In this paper, we show analytically for convolutional and fully connected networks that an alignment between the principal components of network parameters and data takes place when training with random labels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hartmut Maennel; Ibrahim M. Alabdulmohsin; Ilya O. Tolstikhin; Robert Baldock; Olivier Bousquet; Sylvain Gelly; Daniel Keysers; | |
| 1653 | Counterfactual Prediction For Bundle Treatment Highlight: In this work, we assume the existence of low dimensional latent structure underlying bundle treatment. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hao Zou; Peng Cui; Bo Li; Zheyan Shen; Jianxin Ma; Hongxia Yang; Yue He; | |
| 1654 | Beta Embeddings For Multi-Hop Logical Reasoning In Knowledge Graphs Highlight: Here, we present BetaE, a probabilistic embedding framework for answering arbitrary FOL queries over KGs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongyu Ren; Jure Leskovec; | |
| 1655 | Learning Disentangled Representations And Group Structure Of Dynamical Environments Highlight: Inspired by this formalism, we propose a framework, built upon the theory of group representation, for learning representations of a dynamical environment structured around the transformations that generate its evolution. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Robin Quessard; Thomas Barrett; William Clements; | |
| 1656 | Learning Linear Programs From Optimal Decisions Highlight: We propose a flexible gradient-based framework for learning linear programs from optimal decisions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingcong Tan; Daria Terekhov; Andrew Delong; | |
| 1657 | Wisdom Of The Ensemble: Improving Consistency Of Deep Learning Models Highlight: This paper studies a model behavior in the context of periodic retraining of deployed models where the outputs from successive generations of the models might not agree on the correct labels assigned to the same input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lijing Wang; Dipanjan Ghosh; Maria Gonzalez Diaz; Ahmed Farahat; Mahbubul Alam; Chetan Gupta; Jiangzhuo Chen; Madhav Marathe; | code |
| 1658 | Universal Function Approximation On Graphs Highlight: In this work we produce a framework for constructing universal function approximators on graph isomorphism classes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rickard Gabrielsson; | code |
| 1659 | Accelerating Reinforcement Learning Through GPU Atari Emulation Highlight: We introduce CuLE (CUDA Learning Environment), a CUDA port of the Atari Learning Environment (ALE) which is used for the development of deep reinforcement algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Steven Dalton; iuri frosio; | code |
| 1660 | EvolveGraph: Multi-Agent Trajectory Prediction With Dynamic Relational Reasoning Highlight: In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jiachen Li; Fan Yang; Masayoshi Tomizuka; Chiho Choi; | |
| 1661 | Comparator-Adaptive Convex Bandits Highlight: We study bandit convex optimization methods that adapt to the norm of the comparator, a topic that has only been studied before for its full-information counterpart. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dirk van der Hoeven; Ashok Cutkosky; Haipeng Luo; | |
| 1662 | Model-based Reinforcement Learning For Semi-Markov Decision Processes With Neural ODEs Highlight: We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jianzhun Du; Joseph Futoma; Finale Doshi-Velez; | |
| 1663 | The Adaptive Complexity Of Maximizing A Gross Substitutes Valuation Highlight: In this paper, we study the adaptive complexity of maximizing a monotone gross substitutes function under a cardinality constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ron Kupfer; Sharon Qian; Eric Balkanski; Yaron Singer; | |
| 1664 | A Robust Functional EM Algorithm For Incomplete Panel Count Data Highlight: As a first step, under a missing completely at random assumption (MCAR), we propose a simple yet widely applicable functional EM algorithm to estimate the counting process mean function, which is of central interest to behavioral scientists. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Moreno; Zhenke Wu; Jamie Roslyn Yap; Cho Lam; David Wetter; Inbal Nahum-Shani; Walter Dempsey; James M. Rehg; | |
| 1665 | Graph Stochastic Neural Networks For Semi-supervised Learning Highlight: To improve the rigidness and inflexibility of deterministic classification functions, this paper proposes a novel framework named Graph Stochastic Neural Networks (GSNN), which aims to model the uncertainty of the classification function by simultaneously learning a family of functions, i.e., a stochastic function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haibo Wang; Chuan Zhou; Xin Chen; Jia Wu; Shirui Pan; Jilong Wang; | |
| 1666 | Compositional Zero-Shot Learning Via Fine-Grained Dense Feature Composition Highlight: We propose a feature composition framework that learns to extract attribute-based features from training samples and combines them to construct fine-grained features for unseen classes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dat Huynh; Ehsan Elhamifar; | |
| 1667 | A Benchmark For Systematic Generalization In Grounded Language Understanding Highlight: In this paper, we introduce a new benchmark, gSCAN, for evaluating compositional generalization in situated language understanding. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Laura Ruis; Jacob Andreas; Marco Baroni; Diane Bouchacourt; Brenden M. Lake; | |
| 1668 | Weston-Watkins Hinge Loss And Ordered Partitions Highlight: In this work we introduce a novel discrete loss function for multiclass classification, the ordered partition loss, and prove that the WW-hinge loss is calibrated with respect to this loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yutong Wang; Clayton Scott; | |
| 1669 | Reinforcement Learning With Augmented Data Highlight: To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Misha Laskin; Kimin Lee; Adam Stooke; Lerrel Pinto; Pieter Abbeel; Aravind Srinivas; | |
| 1670 | Towards Minimax Optimal Reinforcement Learning In Factored Markov Decision Processes Highlight: Assuming the factorization is known, we propose two model-based algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yi Tian; Jian Qian; Suvrit Sra; | |
| 1671 | Graduated Assignment For Joint Multi-Graph Matching And Clustering With Application To Unsupervised Graph Matching Network Learning Highlight: In this paper, we resort to a graduated assignment procedure for soft matching and clustering over iterations, whereby the two-way constraint and clustering confidence are modulated by two separate annealing parameters, respectively. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Runzhong Wang; Junchi Yan; Xiaokang Yang; | |
| 1672 | Estimating Training Data Influence By Tracing Gradient Descent Highlight: We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Garima Pruthi; Frederick Liu; Satyen Kale; Mukund Sundararajan; | |
| 1673 | Joint Policy Search For Multi-agent Collaboration With Imperfect Information Highlight: In this paper, we show global changes of game values can be decomposed to policy changes localized at each information set, with a novel term named \emph{policy-change density}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuandong Tian; Qucheng Gong; Yu Jiang; | |
| 1674 | Adversarial Bandits With Corruptions: Regret Lower Bound And No-regret Algorithm Highlight: In this paper, we consider an extended setting in which an attacker sits in-between the environment and the learner, and is endowed with a limited budget to corrupt the reward of the selected arm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
lin yang; Mohammad Hajiesmaili; Mohammad Sadegh Talebi; John C. S. Lui; Wing Shing Wong; | |
| 1675 | Beta R-CNN: Looking Into Pedestrian Detection From Another Perspective Highlight: To eliminate the problem, we propose a novel representation based on 2D beta distribution, named Beta Representation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zixuan Xu; Banghuai Li; Ye Yuan; Anhong Dang; | |
| 1676 | Batch Normalization Biases Residual Blocks Towards The Identity Function In Deep Networks Highlight: We show that this key benefit arises because, at initialization, batch normalization downscales the residual branch relative to the skip connection, by a normalizing factor on the order of the square root of the network depth. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Soham De; Sam Smith; | |
| 1677 | Learning Retrospective Knowledge With Reverse Reinforcement Learning Highlight: We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shangtong Zhang; Vivek Veeriah; Shimon Whiteson; | |
| 1678 | Dialog Without Dialog Data: Learning Visual Dialog Agents From VQA Data Highlight: In this work, we study a setting we call "Dialog without Dialog", which requires agents to develop visually grounded dialog models that can adapt to new tasks without language level supervision. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Cogswell; Jiasen Lu; Rishabh Jain; Stefan Lee; Devi Parikh; Dhruv Batra; | code |
| 1679 | GCOMB: Learning Budget-constrained Combinatorial Algorithms Over Billion-sized Graphs Highlight: While existing techniques have primarily focused on obtaining high-quality solutions, scalability to billion-sized graphs has not been adequately addressed. In addition, the impact of a budget-constraint, which is necessary for many practical scenarios, remains to be studied. In this paper, we propose a framework called GCOMB to bridge these gaps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sahil Manchanda; AKASH MITTAL; Anuj Dhawan; Sourav Medya; Sayan Ranu; Ambuj Singh; | |
| 1680 | A General Large Neighborhood Search Framework For Solving Integer Linear Programs Highlight: We focus on solving integer programs and ground our approach in the large neighborhood search (LNS) paradigm, which iteratively chooses a subset of variables to optimize while leaving the remainder fixed. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jialin Song; ravi lanka; Yisong Yue; Bistra Dilkina; | |
| 1681 | A Theoretical Framework For Target Propagation Highlight: We provide a first solution to this problem through a novel reconstruction loss that improves feedback weight training, while simultaneously introducing architectural flexibility by allowing for direct feedback connections from the output to each hidden layer. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alexander Meulemans; Francesco Carzaniga; Johan Suykens; Jo�o Sacramento; Benjamin F. Grewe; | |
| 1682 | OrganITE: Optimal Transplant Donor Organ Offering Using An Individual Treatment Effect Highlight: In this paper, we introduce OrganITE, an organ-to-patient assignment methodology that assigns organs based not only on its own estimates of the potential outcomes but also on organ scarcity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeroen Berrevoets; James Jordon; Ioana Bica; alexander gimson; Mihaela van der Schaar; | |
| 1683 | The Complete Lasso Tradeoff Diagram Highlight: To address this important problem, we offer the first complete diagram that distinguishes all pairs of FDR and power that can be asymptotically realized by the Lasso from the remaining pairs, in a regime of linear sparsity under random designs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hua Wang; Yachong Yang; Zhiqi Bu; Weijie Su; | |
| 1684 | On The Universality Of Deep Learning Highlight: This paper shows that deep learning, i.e., neural networks trained by SGD, can learn in polytime any function class that can be learned in polytime by some algorithm, including parities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Emmanuel Abbe; Colin Sandon; | |
| 1685 | Regression With Reject Option And Application To KNN Highlight: We investigate the problem of regression where one is allowed to abstain from predicting. We refer to this framework as regression with reject option as an extension of classification with reject option. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ahmed Zaoui; Christophe Denis; Mohamed Hebiri; | |
| 1686 | The Primal-Dual Method For Learning Augmented Algorithms Highlight: In this paper, we extend the primal-dual method for online algorithms in order to incorporate predictions that advise the online algorithm about the next action to take. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Etienne Bamas; Andreas Maggiori; Ola Svensson; | |
| 1687 | FLAMBE: Structural Complexity And Representation Learning Of Low Rank MDPs Highlight: This work focuses on the representation learning question: how can we learn such features? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alekh Agarwal; Sham Kakade; Akshay Krishnamurthy; Wen Sun; | |
| 1688 | A Class Of Algorithms For General Instrumental Variable Models Highlight: In this work, we provide a method for causal effect bounding in continuous distributions, leveraging recent advances in gradient-based methods for the optimization of computationally intractable objective functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Niki Kilbertus; Matt J. Kusner; Ricardo Silva; | |
| 1689 | Black-Box Ripper: Copying Black-box Models Using Generative Evolutionary Algorithms Highlight: In this context, we present a teacher-student framework that can distill the black-box (teacher) model into a student model with minimal accuracy loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Antonio Barbalau; Adrian Cosma; Radu Tudor Ionescu; Marius Popescu; | code |
| 1690 | Bayesian Optimization Of Risk Measures Highlight: We propose a family of novel Bayesian optimization algorithms that exploit the structure of the objective function to substantially improve sampling efficiency. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sait Cakmak; Raul Astudillo Marban; Peter Frazier; Enlu Zhou; | |
| 1691 | TorsionNet: A Reinforcement Learning Approach To Sequential Conformer Search Highlight: We present TorsionNet, an efficient sequential conformer search technique based on reinforcement learning under the rigid rotor approximation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tarun Gogineni; Ziping Xu; Exequiel Punzalan; Runxuan Jiang; Joshua Kammeraad; Ambuj Tewari; Paul Zimmerman; | |
| 1692 | GRAF: Generative Radiance Fields For 3D-Aware Image Synthesis Highlight: In this paper, we propose a generative model for radiance fields which have recently proven successful for novel view synthesis of a single scene. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Katja Schwarz; Yiyi Liao; Michael Niemeyer; Andreas Geiger; | |
| 1693 | PIE-NET: Parametric Inference Of Point Cloud Edges Highlight: We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiaogang Wang; Yuelang Xu; Kai Xu; Andrea Tagliasacchi; Bin Zhou; Ali Mahdavi-Amiri; Hao Zhang; | |
| 1694 | A Simple Language Model For Task-Oriented Dialogue Highlight: SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ehsan Hosseini-Asl; Bryan McCann; Chien-Sheng Wu; Semih Yavuz; Richard Socher; | |
| 1695 | A Continuous-Time Mirror Descent Approach To Sparse Phase Retrieval Highlight: We analyze continuous-time mirror descent applied to sparse phase retrieval, which is the problem of recovering sparse signals from a set of magnitude-only measurements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fan Wu; Patrick Rebeschini; | |
| 1696 | Confidence Sequences For Sampling Without Replacement Highlight: We present a suite of tools for designing \textit{confidence sequences} (CS) for $\theta^\star$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ian Waudby-Smith; Aaditya Ramdas; | |
| 1697 | A Mean-field Analysis Of Two-player Zero-sum Games Highlight: To address this limitation, we parametrize mixed strategies as mixtures of particles, whose positions and weights are updated using gradient descent-ascent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Carles Domingo-Enrich; Samy Jelassi; Arthur Mensch; Grant Rotskoff; Joan Bruna; | |
| 1698 | Leap-Of-Thought: Teaching Pre-Trained Models To Systematically Reason Over Implicit Knowledge Highlight: In this work, we provide a first demonstration that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alon Talmor; Oyvind Tafjord; Peter Clark; Yoav Goldberg; Jonathan Berant; | |
| 1699 | Pipeline PSRO: A Scalable Approach For Finding Approximate Nash Equilibria In Large Games Highlight: We introduce Pipeline PSRO (P2SRO), the first scalable PSRO-based method for finding approximate Nash equilibria in large zero-sum imperfect-information games. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Stephen Mcaleer; J.B. Lanier; Roy Fox; Pierre Baldi; | code |
| 1700 | Improving Sparse Vector Technique With Renyi Differential Privacy Highlight: In this paper, we revisit SVT from the lens of Renyi differential privacy, which results in new privacy bounds, new theoretical insight and new variants of SVT algorithms. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuqing Zhu; Yu-Xiang Wang; | |
| 1701 | Latent Template Induction With Gumbel-CRFs Highlight: Specifically, we propose a Gumbel-CRF, a continuous relaxation of the CRF sampling algorithm using a relaxed Forward-Filtering Backward-Sampling (FFBS) approach. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yao Fu; Chuanqi Tan; Bin Bi; Mosha Chen; Yansong Feng; Alexander Rush; | |
| 1702 | Instance Based Approximations To Profile Maximum Likelihood Highlight: In this paper we provide a new efficient algorithm for approximately computing the profile maximum likelihood (PML) distribution, a prominent quantity in symmetric property estimation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nima Anari; Moses Charikar; Kirankumar Shiragur; Aaron Sidford; | |
| 1703 | Factorizable Graph Convolutional Networks Highlight: In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network (FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yiding Yang; Zunlei Feng; Mingli Song; Xinchao Wang; | code |
| 1704 | Guided Adversarial Attack For Evaluating And Enhancing Adversarial Defenses Highlight: In this work, we introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adversarial training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gaurang Sriramanan; Sravanti Addepalli; Arya Baburaj; Venkatesh Babu R; | |
| 1705 | A Study On Encodings For Neural Architecture Search Highlight: In this work, we present the first formal study on the effect of architecture encodings for NAS, including a theoretical grounding and an empirical study. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Colin White; Willie Neiswanger; Sam Nolen; Yash Savani; | code |
| 1706 | Noise2Same: Optimizing A Self-Supervised Bound For Image Denoising Highlight: In this work, we introduce Noise2Same, a novel self-supervised denoising framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yaochen Xie; Zhengyang Wang; Shuiwang Ji; | |
| 1707 | Early-Learning Regularization Prevents Memorization Of Noisy Labels Highlight: We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sheng Liu; Jonathan Niles-Weed; Narges Razavian; Carlos Fernandez-Granda; | |
| 1708 | LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network For Single Image Super-resolution And Beyond Highlight: This paper addresses this pain point by proposing a linearly-assembled pixel-adaptive regression network (LAPAR), which casts the direct LR to HR mapping learning into a linear coefficient regression task over a dictionary of multiple predefined filter bases. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenbo Li; Kun Zhou; Lu Qi; Nianjuan Jiang; Jiangbo Lu; Jiaya Jia; | |
| 1709 | Learning Parities With Neural Networks Highlight: In this paper we make a step towards showing leanability of models that are inherently non-linear. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amit Daniely; Eran Malach; | |
| 1710 | Consistent Plug-in Classifiers For Complex Objectives And Constraints Highlight: We present a statistically consistent algorithm for constrained classification problems where the objective (e.g. F-measure, G-mean) and the constraints (e.g. demographic parity, coverage) are defined by general functions of the confusion matrix. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shiv Kumar Tavker; Harish Guruprasad Ramaswamy; Harikrishna Narasimhan; | |
| 1711 | Movement Pruning: Adaptive Sparsity By Fine-Tuning Highlight: We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Victor Sanh; Thomas Wolf; Alexander Rush; | |
| 1712 | Sanity-Checking Pruning Methods: Random Tickets Can Win The Jackpot Highlight: In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call initial tickets”), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jingtong Su; Yihang Chen; Tianle Cai; Tianhao Wu; Ruiqi Gao; Liwei Wang; Jason D. Lee; | |
| 1713 | Online Matrix Completion With Side Information Highlight: We give an online algorithm and prove novel mistake and regret bounds for online binary matrix completion with side information. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mark Herbster; Stephen Pasteris; Lisa Tse; | |
| 1714 | Position-based Scaled Gradient For Model Quantization And Pruning Highlight: We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jangho Kim; KiYoon Yoo; Nojun Kwak; | |
| 1715 | Online Learning With Primary And Secondary Losses Highlight: We study the problem of online learning with primary and secondary losses. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Avrim Blum; Han Shao; | |
| 1716 | Graph Information Bottleneck Highlight: Here we introduce Graph Information Bottleneck (GIB), an information-theoretic principle that optimally balances expressiveness and robustness of the learned representation of graph-structured data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tailin Wu; Hongyu Ren; Pan Li; Jure Leskovec; | |
| 1717 | The Complexity Of Adversarially Robust Proper Learning Of Halfspaces With Agnostic Noise Highlight: We study the computational complexity of adversarially robust proper learning of halfspaces in the distribution-independent agnostic PAC model, with a focus on Lp perturbations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilias Diakonikolas; Daniel M. Kane; Pasin Manurangsi; | |
| 1718 | Adaptive Online Estimation Of Piecewise Polynomial Trends Highlight: We consider the framework of non-stationary stochastic optimization [Besbes et.al. 2015] with squared error losses and noisy gradient feedback where the dynamic regret of an online learner against a time varying comparator sequence is studied. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Dheeraj Baby; Yu-Xiang Wang; | |
| 1719 | RNNPool: Efficient Non-linear Pooling For RAM Constrained Inference Highlight: In this paper, we introduce RNNPool, a novel pooling operator based on Recurrent Neural Networks (RNNs), that efficiently aggregates features over large patches of an image and rapidly downsamples activation maps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Oindrila Saha; Aditya Kusupati; Harsha Vardhan Simhadri; Manik Varma; Prateek Jain; | code |
| 1720 | Agnostic Learning With Multiple Objectives Highlight: Instead, we propose a new framework of \emph{Agnostic Learning with Multiple Objectives} ($\almo$), where a model is optimized for \emph{any} weights in the mixture of base objectives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Corinna Cortes; Mehryar Mohri; Javier Gonzalvo; Dmitry Storcheus; | |
| 1721 | 3D Multi-bodies: Fitting Sets Of Plausible 3D Human Models To Ambiguous Image Data Highlight: We suggest that ambiguities can be modeled more effectively by parametrizing the possible body shapes and poses via a suitable 3D model, such as SMPL for humans. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benjamin Biggs; David Novotny; Sebastien Ehrhardt; Hanbyul Joo; Ben Graham; Andrea Vedaldi; | |
| 1722 | Auto-Panoptic: Cooperative Multi-Component Architecture Search For Panoptic Segmentation Highlight: In this work, we propose an efficient, cooperative and highly automated framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module in a unified panoptic segmentation pipeline based on the prevailing one-shot Network Architecture Search (NAS) paradigm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yangxin Wu; Gengwei Zhang; Hang Xu; Xiaodan Liang; Liang Lin; | |
| 1723 | Differentiable Top-k With Optimal Transport Highlight: To address the issue, we propose a smoothed approximation, namely SOFT (Scalable Optimal transport-based diFferenTiable) top-k operator. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yujia Xie; Hanjun Dai; Minshuo Chen; Bo Dai; Tuo Zhao; Hongyuan Zha; Wei Wei; Tomas Pfister; | |
| 1724 | Information-theoretic Task Selection For Meta-Reinforcement Learning Highlight: We propose a task selection algorithm based on information theory, which optimizes the set of tasks used for training in meta-RL, irrespectively of how they are generated. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ricardo Luna Gutierrez; Matteo Leonetti; | |
| 1725 | A Limitation Of The PAC-Bayes Framework Highlight: In this manuscript we present a limitation for the PAC-Bayes framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Roi Livni; Shay Moran; | |
| 1726 | On Completeness-aware Concept-Based Explanations In Deep Neural Networks Highlight: In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chih-Kuan Yeh; Been Kim; Sercan Arik; Chun-Liang Li; Tomas Pfister; Pradeep Ravikumar; | |
| 1727 | Stochastic Recursive Gradient Descent Ascent For Stochastic Nonconvex-Strongly-Concave Minimax Problems Highlight: In this paper, we propose a novel method called Stochastic Recursive gradiEnt Descent Ascent (SREDA), which estimates gradients more efficiently using variance reduction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Luo Luo; Haishan Ye; Zhichao Huang; Tong Zhang; | |
| 1728 | Why Normalizing Flows Fail To Detect Out-of-Distribution Data Highlight: We investigate why normalizing flows perform poorly for OOD detection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Polina Kirichenko; Pavel Izmailov; Andrew Gordon Wilson; | |
| 1729 | Explaining Naive Bayes And Other Linear Classifiers With Polynomial Time And Delay Highlight: In contrast, we show that the computation of one PI-explanation for an NBC can be achieved in log-linear time, and that the same result also applies to the more general class of linear classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Joao Marques-Silva; Thomas Gerspacher; Martin Cooper; Alexey Ignatiev; Nina Narodytska; | |
| 1730 | Unsupervised Translation Of Programming Languages Highlight: In this paper, we propose to leverage recent approaches in unsupervised machine translation to train a fully unsupervised neural transcompiler. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Baptiste Roziere; Marie-Anne Lachaux; Lowik Chanussot; Guillaume Lample; | |
| 1731 | Adversarial Style Mining For One-Shot Unsupervised Domain Adaptation Highlight: To this end, we propose a novel Adversarial Style Mining approach, which combines the style transfer module and task-specific module into an adversarial manner. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yawei Luo; Ping Liu; Tao Guan; Junqing Yu; Yi Yang; | |
| 1732 | Optimally Deceiving A Learning Leader In Stackelberg Games Highlight: In this paper, we fill this gap by showing that it is always possible for the follower to efficiently compute (near-)optimal payoffs for various scenarios of learning interaction between the leader and the follower. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Georgios Birmpas; Jiarui Gan; Alexandros Hollender; Francisco Marmolejo; Ninad Rajgopal; Alexandros Voudouris; | |
| 1733 | Online Optimization With Memory And Competitive Control Highlight: This paper presents competitive algorithms for a novel class of online optimization problems with memory. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guanya Shi; Yiheng Lin; Soon-Jo Chung; Yisong Yue; Adam Wierman; | |
| 1734 | IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method Highlight: We introduce a framework for designing primal methods under the decentralized optimization setting where local functions are smooth and strongly convex. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yossi Arjevani; Joan Bruna; Bugra Can; Mert Gurbuzbalaban; Stefanie Jegelka; Hongzhou Lin; | |
| 1735 | Evolving Graphical Planner: Contextual Global Planning For Vision-and-Language Navigation Highlight: In this paper, we introduce Evolving Graphical Planner (EGP), a module that allows global planning for navigation based on raw sensory input. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhiwei Deng; Karthik Narasimhan; Olga Russakovsky; | |
| 1736 | Learning From Failure: De-biasing Classifier From Biased Classifier Highlight: Based on the obser- vations, we propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junhyun Nam; Hyuntak Cha; Sung-Soo Ahn; Jaeho Lee; Jinwoo Shin; | |
| 1737 | Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder Highlight: In this paper, we make the observation that some of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhisheng Xiao; Qing Yan; Yali Amit; | |
| 1738 | Deep Diffusion-Invariant Wasserstein Distributional Classification Highlight: In this paper, we present a novel classification method called deep diffusion-invariant Wasserstein distributional classification (DeepWDC). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sung Woo Park+; Dong Wook Shu; Junseok Kwon; | |
| 1739 | Finding All $\epsilon$-Good Arms In Stochastic Bandits Highlight: We introduce two algorithms to overcome these and demonstrate their great empirical performance on a large-scale crowd-sourced dataset of $2.2$M ratings collected by the New Yorker Caption Contest as well as a dataset testing hundreds of possible cancer drugs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Blake Mason; Lalit Jain; Ardhendu Tripathy; Robert Nowak; | |
| 1740 | Meta-Learning Through Hebbian Plasticity In Random Networks Highlight: Inspired by this biological mechanism, we propose a search method that, instead of optimizing the weight parameters of neural networks directly, only searches for synapse-specific Hebbian learning rules that allow the network to continuously self-organize its weights during the lifetime of the agent. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Elias Najarro; Sebastian Risi; | |
| 1741 | A Computational Separation Between Private Learning And Online Learning Highlight: We show that, assuming the existence of one-way functions, such an efficient conversion is impossible even for general pure-private learners with polynomial sample complexity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mark Bun; | |
| 1742 | Top-KAST: Top-K Always Sparse Training Highlight: In this work we propose Top-KAST, a method that preserves constant sparsity throughout training (in both the forward and backward-passes). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siddhant Jayakumar; Razvan Pascanu; Jack Rae; Simon Osindero; Erich Elsen; | |
| 1743 | Meta-Learning With Adaptive Hyperparameters Highlight: Instead of searching for better task-aware initialization, we focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sungyong Baik; Myungsub Choi; Janghoon Choi; Heewon Kim; Kyoung Mu Lee; | |
| 1744 | Tight Last-iterate Convergence Rates For No-regret Learning In Multi-player Games Highlight: We study the question of obtaining last-iterate convergence rates for no-regret learning algorithms in multi-player games. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Noah Golowich; Sarath Pattathil; Constantinos Daskalakis; | |
| 1745 | Curvature Regularization To Prevent Distortion In Graph Embedding Highlight: To address the problem, we propose curvature regularization, to enforce flatness for embedding manifolds, thereby preventing the distortion. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hongbin Pei; Bingzhe Wei; Kevin Chang; Chunxu Zhang; Bo Yang; | |
| 1746 | Perturbing Across The Feature Hierarchy To Improve Standard And Strict Blackbox Attack Transferability Highlight: We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nathan Inkawhich; Kevin Liang; Binghui Wang; Matthew Inkawhich; Lawrence Carin; Yiran Chen; | |
| 1747 | Statistical And Topological Properties Of Sliced Probability Divergences Highlight: In this paper, we aim at bridging this gap and derive various theoretical properties of sliced probability divergences. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kimia Nadjahi; Alain Durmus; L�na�c Chizat; Soheil Kolouri; Shahin Shahrampour; Umut Simsekli; | |
| 1748 | Probabilistic Active Meta-Learning Highlight: In this work, we introduce task selection based on prior experience into a meta-learning algorithm by conceptualizing the learner and the active meta-learning setting using a probabilistic latent variable model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jean Kaddour; Steindor Saemundsson; Marc Deisenroth; | |
| 1749 | Knowledge Distillation In Wide Neural Networks: Risk Bound, Data Efficiency And Imperfect Teacher Highlight: In this paper, we theoretically analyze the knowledge distillation of a wide neural network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Guangda Ji; Zhanxing Zhu; | |
| 1750 | Adversarial Attacks On Deep Graph Matching Highlight: This paper proposes an adversarial attack model with two novel attack techniques to perturb the graph structure and degrade the quality of deep graph matching: (1) a kernel density estimation approach is utilized to estimate and maximize node densities to derive imperceptible perturbations, by pushing attacked nodes to dense regions in two graphs, such that they are indistinguishable from many neighbors; and (2) a meta learning-based projected gradient descent method is developed to well choose attack starting points and to improve the search performance for producing effective perturbations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zijie Zhang; Zeru Zhang; Yang Zhou; Yelong Shen; Ruoming Jin; Dejing Dou; | |
| 1751 | The Generalization-Stability Tradeoff In Neural Network Pruning Highlight: We demonstrate that this generalization-stability tradeoff” is present across a wide variety of pruning settings and propose a mechanism for its cause: pruning regularizes similarly to noise injection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Brian Bartoldson; Ari Morcos; Adrian Barbu; Gordon Erlebacher; | |
| 1752 | Gradient-EM Bayesian Meta-Learning Highlight: The key idea behind Bayesian meta-learning is empirical Bayes inference of hierarchical model. In this work, we extend this framework to include a variety of existing methods, before proposing our variant based on gradient-EM algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yayi Zou; Xiaoqi Lu; | |
| 1753 | Logarithmic Regret Bound In Partially Observable Linear Dynamical Systems Highlight: Deploying this estimation method, we propose adaptive control online learning (AdapOn), an efficient reinforcement learning algorithm that adaptively learns the system dynamics and continuously updates its controller through online learning steps. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ali Sahin Lale; Kamyar Azizzadenesheli; Babak Hassibi; Anima Anandkumar; | |
| 1754 | Linearly Converging Error Compensated SGD Highlight: In this paper, we propose a unified analysis of variants of distributed SGD with arbitrary compressions and delayed updates. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Eduard Gorbunov; Dmitry Kovalev; Dmitry Makarenko; Peter Richtarik; | |
| 1755 | Canonical 3D Deformer Maps: Unifying Parametric And Non-parametric Methods For Dense Weakly-supervised Category Reconstruction Highlight: We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Novotny; Roman Shapovalov; Andrea Vedaldi; | |
| 1756 | A Self-Tuning Actor-Critic Algorithm Highlight: In this paper, we take a step towards addressing this issue by using metagradients to automatically adapt hyperparameters online by meta-gradient descent (Xu et al., 2018). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tom Zahavy; Zhongwen Xu; Vivek Veeriah; Matteo Hessel; Junhyuk Oh; Hado P. van Hasselt; David Silver; Satinder Singh; | |
| 1757 | The Cone Of Silence: Speech Separation By Localization Highlight: At the core of our method is a deep network, in the waveform domain, which isolates sources within an angular region ?±w/2, given an angle of interest ? and angular window size w. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Teerapat Jenrungrot; Vivek Jayaram; Steve Seitz; Ira Kemelmacher-Shlizerman; | |
| 1758 | High-Dimensional Bayesian Optimization Via Nested Riemannian Manifolds Highlight: In this paper, we propose to exploit the geometry of non-Euclidean search spaces, which often arise in a variety of domains, to learn structure-preserving mappings and optimize the acquisition function of BO in low-dimensional latent spaces. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
No�mie Jaquier; Leonel Rozo; | |
| 1759 | Train-by-Reconnect: Decoupling Locations Of Weights From Their Values Highlight: To assess our hypothesis, we propose a novel method called lookahead permutation (LaPerm) to train DNNs by reconnecting the weights. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yushi Qiu; Reiji Suda; | |
| 1760 | Learning Discrete Distributions: User Vs Item-level Privacy Highlight: We study the fundamental problem of learning discrete distributions over $k$ symbols with user-level differential privacy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuhan Liu; Ananda Theertha Suresh; Felix Xinnan X. Yu; Sanjiv Kumar; Michael Riley; | |
| 1761 | Matrix Completion With Quantified Uncertainty Through Low Rank Gaussian Copula Highlight: This paper pro- poses a probabilistic and scalable framework for missing value imputation with quantified uncertainty. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuxuan Zhao; Madeleine Udell; | |
| 1762 | Sparse And Continuous Attention Mechanisms Highlight: This paper expands that work in two directions: first, we extend alpha-entmax to continuous domains, revealing a link with Tsallis statistics and deformed exponential families. Second, we introduce continuous-domain attention mechanisms, deriving efficient gradient backpropagation algorithms for alpha in {1,2}. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Andr� Martins; Ant�nio Farinhas; Marcos Treviso; Vlad Niculae; Pedro Aguiar; Mario Figueiredo ; | |
| 1763 | Generalized Focal Loss: Learning Qualified And Distributed Bounding Boxes For Dense Object Detection Highlight: This paper delves into the \emph{representations} of the above three fundamental elements: quality estimation, classification and localization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiang Li; Wenhai Wang; Lijun Wu; Shuo Chen; Xiaolin Hu; Jun Li; Jinhui Tang; Jian Yang; | |
| 1764 | Learning By Minimizing The Sum Of Ranked Range Highlight: In this work, we introduce the sum of ranked range (SoRR) as a general approach to form learning objectives. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shu Hu; Yiming Ying; xin wang; Siwei Lyu; | |
| 1765 | Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations Highlight: We propose the state-adversarial Markov decision process (SA-MDP) to study the fundamental properties of this problem, and develop a theoretically principled policy regularization which can be applied to a large family of DRL algorithms, including deep deterministic policy gradient (DDPG), proximal policy optimization (PPO) and deep Q networks (DQN), for both discrete and continuous action control problems. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Huan Zhang; Hongge Chen; Chaowei Xiao; Bo Li; mingyan liu; Duane Boning; Cho-Jui Hsieh; | |
| 1766 | Understanding Anomaly Detection With Deep Invertible Networks Through Hierarchies Of Distributions And Features Highlight: We refine previous investigations of this failure at anomaly detection for invertible generative networks and provide a clear explanation of it as a combination of model bias and domain prior: Convolutional networks learn similar low-level feature distributions when trained on any natural image dataset and these low-level features dominate the likelihood. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Robin Schirrmeister; Yuxuan Zhou; Tonio Ball; Dan Zhang; | code |
| 1767 | Fair Hierarchical Clustering Highlight: In this paper we extend this notion to hierarchical clustering, where the goal is to recursively partition the data to optimize a specific objective. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sara Ahmadian; Alessandro Epasto; Marina Knittel; Ravi Kumar; Mohammad Mahdian; Benjamin Moseley; Philip Pham; Sergei Vassilvitskii; Yuyan Wang; | |
| 1768 | Self-training Avoids Using Spurious Features Under Domain Shift Highlight: We identify and analyze one particular setting where the domain shift can be large, but these algorithms provably work: certain spurious features correlate with the label in the source domain but are independent of the label in the target. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yining Chen; Colin Wei; Ananya Kumar; Tengyu Ma; | |
| 1769 | Improving Online Rent-or-Buy Algorithms With Sequential Decision Making And ML Predictions Highlight: In this work we study online rent-or-buy problems as a sequential decision making problem. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Soumya Banerjee; | |
| 1770 | CircleGAN: Generative Adversarial Learning Across Spherical Circles Highlight: We present a novel discriminator for GANs that improves realness and diversity of generated samples by learning a structured hypersphere embedding space using spherical circles. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Woohyeon Shim; Minsu Cho; | |
| 1771 | WOR And $p$'s: Sketches For $\ell_p$-Sampling Without Replacement Highlight: We design novel composable sketches for WOR {\em $\ell_p$ sampling}, weighted sampling of keys according to a power $p\in[0,2]$ of their frequency (or for signed data, sum of updates). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edith Cohen; Rasmus Pagh; David Woodruff; | |
| 1772 | Hypersolvers: Toward Fast Continuous-Depth Models Highlight: We introduce hypersolvers, neural networks designed to solve ODEs with low overhead and theoretical guarantees on accuracy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Michael Poli; Stefano Massaroli; Atsushi Yamashita; edit Hajime Asama; Jinkyoo Park; | |
| 1773 | Log-Likelihood Ratio Minimizing Flows: Towards Robust And Quantifiable Neural Distribution Alignment Highlight: In this paper, we propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ben Usman; Avneesh Sud; Nick Dufour; Kate Saenko; | |
| 1774 | Escaping The Gravitational Pull Of Softmax Highlight: To circumvent these shortcomings we investigate an alternative transformation, the \emph{escort} mapping, that demonstrates better optimization properties. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jincheng Mei; Chenjun Xiao; Bo Dai; Lihong Li; Csaba Szepesvari; Dale Schuurmans; | |
| 1775 | Regret In Online Recommendation Systems Highlight: This paper proposes a theoretical analysis of recommendation systems in an online setting, where items are sequentially recommended to users over time. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaito Ariu; Narae Ryu; Se-Young Yun; Alexandre Proutiere; | |
| 1776 | On Convergence And Generalization Of Dropout Training Highlight: We study dropout in two-layer neural networks with rectified linear unit (ReLU) activations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Poorya Mianjy; Raman Arora; | |
| 1777 | Second Order Optimality In Decentralized Non-Convex Optimization Via Perturbed Gradient Tracking Highlight: In this paper we study the problem of escaping from saddle points and achieving second-order optimality in a decentralized setting where a group of agents collaborate to minimize their aggregate objective function. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Isidoros Tziotis; Constantine Caramanis; Aryan Mokhtari; | |
| 1778 | Implicit Regularization In Deep Learning May Not Be Explainable By Norms Highlight: The current paper resolves this open question in the negative, by proving that there exist natural matrix factorization problems on which the implicit regularization drives all norms (and quasi-norms) towards infinity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Noam Razin; Nadav Cohen; | |
| 1779 | POMO: Policy Optimization With Multiple Optima For Reinforcement Learning Highlight: We introduce Policy Optimization with Multiple Optima (POMO), an end-to-end approach for building such a heuristic solver. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yeong-Dae Kwon; Jinho Choo; Byoungjip Kim; Iljoo Yoon; Youngjune Gwon; Seungjai Min; | |
| 1780 | Uncertainty-aware Self-training For Few-shot Text Classification Highlight: We propose an approach to improve self-training by incorporating uncertainty estimates of the underlying neural network leveraging recent advances in Bayesian deep learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Subhabrata Mukherjee; Ahmed Awadallah; | |
| 1781 | Learning To Learn With Feedback And Local Plasticity Highlight: In this study, we employ meta-learning to discover networks that learn using feedback connections and local, biologically inspired learning rules. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jack Lindsey; Ashok Litwin-Kumar; | |
| 1782 | Every View Counts: Cross-View Consistency In 3D Object Detection With Hybrid-Cylindrical-Spherical Voxelization Highlight: In this paper, we present a novel framework to unify and leverage the benefits from both BEV and RV. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qi Chen; Lin Sun; Ernest Cheung; Alan L. Yuille; | |
| 1783 | Sharper Generalization Bounds For Pairwise Learning Highlight: In this paper, we provide a refined stability analysis by developing generalization bounds which can be $\sqrt{n}$-times faster than the existing results, where $n$ is the sample size. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yunwen Lei; Antoine Ledent; Marius Kloft; | |
| 1784 | A Measure-Theoretic Approach To Kernel Conditional Mean Embeddings Highlight: We present a new operator-free, measure-theoretic approach to the conditional mean embedding as a random variable taking values in a reproducing kernel Hilbert space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Junhyung Park; Krikamol Muandet; | |
| 1785 | Quantifying The Empirical Wasserstein Distance To A Set Of Measures: Beating The Curse Of Dimensionality Highlight: We consider the problem of estimating the Wasserstein distance between the empirical measure and a set of probability measures whose expectations over a class of functions (hypothesis class) are constrained. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nian Si; Jose Blanchet; Soumyadip Ghosh; Mark Squillante; | |
| 1786 | Bootstrap Your Own Latent – A New Approach To Self-Supervised Learning Highlight: We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jean-Bastien Grill; Florian Strub; Florent Altch�; Corentin Tallec; Pierre Richemond; Elena Buchatskaya; Carl Doersch; Bernardo Avila Pires; Zhaohan Guo; Mohammad Gheshlaghi Azar; Bilal Piot; koray kavukcuoglu; Remi Munos; Michal Valko; | |
| 1787 | Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam In Deep Learning Highlight: This work aims to provide understandings on this generalization gap by analyzing their local convergence behaviors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pan Zhou; Jiashi Feng; Chao Ma; Caiming Xiong; Steven Chu Hong Hoi; Weinan E; | |
| 1788 | RSKDD-Net: Random Sample-based Keypoint Detector And Descriptor Highlight: This paper proposes Random Sample-based Keypoint Detector and Descriptor Network (RSKDD-Net) for large scale point cloud registration. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fan Lu; Guang Chen; Yinlong Liu; Zhongnan Qu; Alois Knoll; | code |
| 1789 | Efficient Clustering For Stretched Mixtures: Landscape And Optimality Highlight: To overcome this issue, we propose a non-convex program seeking for an affine transform to turn the data into a one-dimensional point cloud concentrating around -1 and 1, after which clustering becomes easy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaizheng Wang; Yuling Yan; Mateo Diaz; | |
| 1790 | A Group-Theoretic Framework For Data Augmentation Highlight: In this paper, we develop such a framework to explain data augmentation as averaging over the orbits of the group that keeps the data distribution approximately invariant, and show that it leads to variance reduction. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shuxiao Chen; Edgar Dobriban; Jane Lee; | |
| 1791 | The Statistical Cost Of Robust Kernel Hyperparameter Turning Highlight: We consider the problem of finding the best interpolant from a class of kernels with unknown hyperparameters, assuming only that the noise is square-integrable. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Raphael Meyer; Christopher Musco; | |
| 1792 | How Does Weight Correlation Affect Generalisation Ability Of Deep Neural Networks? Highlight: This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks’ generalisation ability. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gaojie Jin; Xinping Yi; Liang Zhang; Lijun Zhang; Sven Schewe; Xiaowei Huang; | |
| 1793 | ContraGAN: Contrastive Learning For Conditional Image Generation Highlight: In this paper, we propose ContraGAN that considers relations between multiple image embeddings in the same batch (data-to-data relations) as well as the data-to-class relations by using a conditional contrastive loss. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minguk Kang; Jaesik Park; | code |
| 1794 | On The Distance Between Two Neural Networks And The Stability Of Learning Highlight: This paper relates parameter distance to gradient breakdown for a broad class of nonlinear compositional functions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jeremy Bernstein; Arash Vahdat; Yisong Yue; Ming-Yu Liu; | code |
| 1795 | A Topological Filter For Learning With Label Noise Highlight: To tackle this problem, in this paper, we propose a new method for filtering label noise. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pengxiang Wu; Songzhu Zheng; Mayank Goswami; Dimitris Metaxas; Chao Chen; | |
| 1796 | Personalized Federated Learning With Moreau Envelopes Highlight: To address this, we propose an algorithm for personalized FL (pFedMe) using Moreau envelopes as clients’ regularized loss functions, which help decouple personalized model optimization from the global model learning in a bi-level problem stylized for personalized FL. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Canh T. Dinh; Nguyen Tran; Tuan Dung Nguyen; | |
| 1797 | Avoiding Side Effects In Complex Environments Highlight: In toy environments, Attainable Utility Preservation (AUP) avoided side effects by penalizing shifts in the ability to achieve randomly generated goals. We scale this approach to large, randomly generated environments based on Conway’s Game of Life. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Turner; Neale Ratzlaff; Prasad Tadepalli; | code |
| 1798 | No-regret Learning In Price Competitions Under Consumer Reference Effects Highlight: We study long-run market stability for repeated price competitions between two firms, where consumer demand depends on firms’ posted prices and consumers’ price expectations called reference prices. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Negin Golrezaei; Patrick Jaillet; Jason Cheuk Nam Liang; | |
| 1799 | Geometric Dataset Distances Via Optimal Transport Highlight: In this work we propose an alternative notion of distance between datasets that (i) is model-agnostic, (ii) does not involve training, (iii) can compare datasets even if their label sets are completely disjoint and (iv) has solid theoretical footing. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
David Alvarez Melis; Nicolo Fusi; | |
| 1800 | Task-Agnostic Amortized Inference Of Gaussian Process Hyperparameters Highlight: We introduce an approach to the identification of kernel hyperparameters in GP regression and related problems that sidesteps the need for costly marginal likelihoods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sulin Liu; Xingyuan Sun; Peter J. Ramadge; Ryan P. Adams; | code |
| 1801 | A Novel Variational Form Of The Schatten-$p$ Quasi-norm Highlight: Here, we propose and analyze a novel {\it variational form of Schatten-$p$ quasi-norm} which, for the first time in the literature, is defined for any continuous value of $p\in(0,1]$ and decouples along the columns of the factorized matrices. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Paris Giampouras; Rene Vidal; Athanasios Rontogiannis; Benjamin Haeffele; | |
| 1802 | Energy-based Out-of-distribution Detection Highlight: We propose a unified framework for OOD detection that uses an energy score. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weitang Liu; Xiaoyun Wang; John Owens; Sharon Yixuan Li; | |
| 1803 | On The Loss Landscape Of Adversarial Training: Identifying Challenges And How To Overcome Them Highlight: We analyze the influence of adversarial training on the loss landscape of machine learning models. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chen Liu; Mathieu Salzmann; Tao Lin; Ryota Tomioka; Sabine S�sstrunk; | |
| 1804 | User-Dependent Neural Sequence Models For Continuous-Time Event Data Highlight: In this paper, we extend the broad class of neural marked point process models to mixtures of latent embeddings,where each mixture component models the characteristic traits of a given user. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Alex Boyd; Robert Bamler; Stephan Mandt; Padhraic Smyth; | |
| 1805 | Active Structure Learning Of Causal DAGs Via Directed Clique Trees Highlight: In this work, we develop a \textit{universal} lower bound for single-node interventions that establishes that the largest clique is \textit{always} a fundamental impediment to structure learning. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Chandler Squires; Sara Magliacane; Kristjan Greenewald; Dmitriy Katz; Murat Kocaoglu; Karthikeyan Shanmugam; | code |
| 1806 | Convergence And Stability Of Graph Convolutional Networks On Large Random Graphs Highlight: We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior on standard models of random graphs, where nodes are represented by random latent variables and edges are drawn according to a similarity kernel. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicolas Keriven; Alberto Bietti; Samuel Vaiter; | |
| 1807 | BoTorch: A Framework For Efficient Monte-Carlo Bayesian Optimization Highlight: We introduce BoTorch, a modern programming framework for Bayesian optimization that combines Monte-Carlo (MC) acquisition functions, a novel sample average approximation optimization approach, auto-differentiation, and variance reduction techniques. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maximilian Balandat; Brian Karrer; Daniel Jiang; Samuel Daulton; Ben Letham; Andrew Gordon Wilson; Eytan Bakshy; | |
| 1808 | Reconsidering Generative Objectives For Counterfactual Reasoning Highlight: As a step towards more flexible, scalable and accurate ITE estimation, we present a novel generative Bayesian estimation framework that integrates representation learning, adversarial matching and causal estimation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Danni Lu; Chenyang Tao; Junya Chen; Fan Li; Feng Guo; Lawrence Carin; | |
| 1809 | Robust Federated Learning: The Case Of Affine Distribution Shifts Highlight: The primary goal of this paper is to develop a robust federated learning algorithm that achieves satisfactory performance against distribution shifts in users’ samples. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Amirhossein Reisizadeh; Farzan Farnia; Ramtin Pedarsani; Ali Jadbabaie; | |
| 1810 | Quantile Propagation For Wasserstein-Approximate Gaussian Processes Highlight: We develop a new approximate inference method for Gaussian process models which overcomes the technical challenges arising from abandoning these convenient divergences. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rui Zhang; Christian Walder; Edwin V. Bonilla; Marian-Andrei Rizoiu; Lexing Xie; | |
| 1811 | Generating Adjacency-Constrained Subgoals In Hierarchical Reinforcement Learning Highlight: In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a k-step adjacent region of the current state using an adjacency constraint. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Tianren Zhang; Shangqi Guo; Tian Tan; Xiaolin Hu; Feng Chen; | |
| 1812 | High-contrast �gaudy� Images Improve The Training Of Deep Neural Network Models Of Visual Cortex Highlight: We propose high-contrast, binarized versions of natural images—termed gaudy images—to efficiently train DNNs to predict higher-order visual cortical responses. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Benjamin Cowley; Jonathan W. Pillow; | |
| 1813 | Duality-Induced Regularizer For Tensor Factorization Based Knowledge Graph Completion Highlight: To address this challenge, we propose a novel regularizer—namely, \textbf{DU}ality-induced \textbf{R}egul\textbf{A}rizer (DURA)—which is not only effective in improving the performance of existing models but widely applicable to various methods. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhanqiu Zhang; Jianyu Cai; Jie Wang; | |
| 1814 | Distributed Training With Heterogeneous Data: Bridging Median- And Mean-Based Algorithms Highlight: To overcome this gap, we provide a novel gradient correction mechanism that perturbs the local gradients with noise, which we show can provably close the gap between mean and median of the gradients. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiangyi Chen; Tiancong Chen; Haoran Sun; Steven Z. Wu; Mingyi Hong; | |
| 1815 | H-Mem: Harnessing Synaptic Plasticity With Hebbian Memory Networks Highlight: Here, we propose Hebbian Memory Networks (H-Mems), a simple neural network model that is built around a core hetero-associative network subject to Hebbian plasticity. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Thomas Limbacher; Robert Legenstein; | |
| 1816 | Neural Unsigned Distance Fields For Implicit Function Learning Highlight: In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Julian Chibane; Mohamad Aymen mir; Gerard Pons-Moll; | code |
| 1817 | Curriculum By Smoothing Highlight: In this paper, we propose an elegant curriculum-based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Samarth Sinha; Animesh Garg; Hugo Larochelle; | |
| 1818 | Fast Transformers With Clustered Attention Highlight: To address this, we propose clustered attention, which instead of computing the attention for every query, groups queries into clusters and computes attention just for the centroids. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Apoorv Vyas; Angelos Katharopoulos; Fran�ois Fleuret; | |
| 1819 | The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations For Neural Network Verification Highlight: We improve the effectiveness of propagation- and linear-optimization-based neural network verification algorithms with a new tightened convex relaxation for ReLU neurons. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christian Tjandraatmadja; Ross Anderson; Joey Huchette; Will Ma; KRUNAL KISHOR PATEL; Juan Pablo Vielma; | |
| 1820 | Strongly Incremental Constituency Parsing With Graph Neural Networks Highlight: In this paper, we propose a novel transition system called attach-juxtapose. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaiyu Yang; Jia Deng; | code |
| 1821 | AOT: Appearance Optimal Transport Based Identity Swapping For Forgery Detection Highlight: In this work, we provide a new identity swapping algorithm with large differences in appearance for face forgery detection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hao Zhu; Chaoyou Fu; Qianyi Wu; Wayne Wu; Chen Qian; Ran He; | |
| 1822 | Uncertainty-Aware Learning For Zero-Shot Semantic Segmentation Highlight: In this paper, we identify this challenge and address it with a novel framework that learns to discriminate noisy samples based on Bayesian uncertainty estimation. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ping Hu; Stan Sclaroff; Kate Saenko; | |
| 1823 | Delta-STN: Efficient Bilevel Optimization For Neural Networks Using Structured Response Jacobians Highlight: In this paper, we diagnose several subtle pathologies in the training of STNs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Juhan Bae; Roger B. Grosse; | |
| 1824 | First-Order Methods For Large-Scale Market Equilibrium Computation Highlight: We develop simple first-order methods suitable for solving these programs for large-scale markets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuan Gao; Christian Kroer; | |
| 1825 | Minimax Optimal Nonparametric Estimation Of Heterogeneous Treatment Effects Highlight: In this paper, we model the HTE as a smooth nonparametric difference between two less smooth baseline functions, and determine the tight statistical limits of the nonparametric HTE estimation as a function of the covariate geometry. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zijun Gao; Yanjun Han; | |
| 1826 | Residual Force Control For Agile Human Behavior Imitation And Extended Motion Synthesis Highlight: To overcome the dynamics mismatch, we propose a novel approach, residual force control (RFC), that augments a humanoid control policy by adding external residual forces into the action space. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ye Yuan; Kris Kitani; | code |
| 1827 | A General Method For Robust Learning From Batches Highlight: We develop a general framework of robust learning from batches, and determine the limits of both distribution estimation, and notably, classification, over arbitrary, including continuous, domains. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ayush Jain; Alon Orlitsky; | |
| 1828 | Not All Unlabeled Data Are Equal: Learning To Weight Data In Semi-supervised Learning Highlight: In this paper we study how to use a different weight for “every” unlabeled example. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhongzheng Ren; Raymond Yeh; Alexander Schwing; | |
| 1829 | Hard Negative Mixing For Contrastive Learning Highlight: In this paper, we argue that an important aspect of contrastive learning, i.e. the effect of hard negatives, has so far been neglected. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yannis Kalantidis; Mert Bulent Sariyildiz; Noe Pion; Philippe Weinzaepfel; Diane Larlus; | |
| 1830 | MOReL: Model-Based Offline Reinforcement Learning Highlight: In this work, we present MOReL, an algorithmic framework for model-based offline RL. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rahul Kidambi; Aravind Rajeswaran; Praneeth Netrapalli; Thorsten Joachims; | |
| 1831 | Weisfeiler And Leman Go Sparse: Towards Scalable Higher-order Graph Embeddings Highlight: Here, we propose local variants and corresponding neural architectures, which consider a subset of the original neighborhood, making them more scalable, and less prone to overfitting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Christopher Morris; Gaurav Rattan; Petra Mutzel; | |
| 1832 | Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion Highlight: We propose a new algorithm combining alternating minimization with extreme-value filtering and provide sufficient and necessary conditions to recover the original rank-one matrix. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qianqian Ma; Alex Olshevsky; | |
| 1833 | Learning Semantic-aware Normalization For Generative Adversarial Networks Highlight: In this paper, we propose a novel image synthesis approach by learning Semantic-aware relative importance for feature channels in Generative Adversarial Networks (SariGAN). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Heliang Zheng; Jianlong Fu; Yanhong Zeng; Jiebo Luo; Zheng-Jun Zha; | |
| 1834 | Differentiable Causal Discovery From Interventional Data Highlight: This work constitutes a new step in this direction by proposing a theoretically-grounded method based on neural networks that can leverage interventional data. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Philippe Brouillard; S�bastien Lachapelle; Alexandre Lacoste; Simon Lacoste-Julien; Alexandre Drouin; | |
| 1835 | One-sample Guided Object Representation Disassembling Highlight: In this paper, we introduce the One-sample Guided Object Representation Disassembling (One-GORD) method, which only requires one annotated sample for each object category to learn disassembled object representation from unannotated images. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zunlei Feng; Yongming He; Xinchao Wang; Xin Gao; Jie Lei; Cheng Jin; Mingli Song; | |
| 1836 | Extrapolation Towards Imaginary 0-Nearest Neighbour And Its Improved Convergence Rate Highlight: In this paper, we propose a novel multiscale $k$-NN (MS-$k$-NN), that extrapolates unweighted $k$-NN estimators from several $k \ge 1$ values to $k=0$, thus giving an imaginary 0-NN estimator. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Akifumi Okuno; Hidetoshi Shimodaira; | |
| 1837 | Robust Persistence Diagrams Using Reproducing Kernels Highlight: In this work, we develop a framework for constructing robust persistence diagrams from superlevel filtrations of robust density estimators constructed using reproducing kernels. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Siddharth Vishwanath; Kenji Fukumizu; Satoshi Kuriki; Bharath K. Sriperumbudur; | |
| 1838 | Contextual Games: Multi-Agent Learning With Side Information Highlight: By means of kernel-based regularity assumptions, we model the correlation between different contexts and game outcomes and propose a novel online (meta) algorithm that exploits such correlations to minimize the contextual regret of individual players. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Pier Giuseppe Sessa; Ilija Bogunovic; Andreas Krause; Maryam Kamgarpour; | |
| 1839 | Goal-directed Generation Of Discrete Structures With Conditional Generative Models Highlight: In this paper, we investigate the use of conditional generative models which directly attack this inverse problem, by modeling the distribution of discrete structures given properties of interest. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Maolaaisha Aminanmu; Brooks Paige; Alexandros Kalousis; | |
| 1840 | Beyond Lazy Training For Over-parameterized Tensor Decomposition Highlight: In this paper we study a closely related tensor decomposition problem: given an $l$-th order tensor in $(R^d)^{\otimes l}$ of rank $r$ (where $r\ll d$), can variants of gradient descent find a rank $m$ decomposition where $m > r$? Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xiang Wang; Chenwei Wu; Jason D. Lee; Tengyu Ma; Rong Ge; | |
| 1841 | Denoised Smoothing: A Provable Defense For Pretrained Classifiers Highlight: We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hadi Salman; Mingjie Sun; Greg Yang; Ashish Kapoor; J. Zico Kolter; | code |
| 1842 | Minibatch Stochastic Approximate Proximal Point Methods Highlight: To do this, we propose two minibatched algorithms for which we prove a non-asymptotic upper bound on the rate of convergence, revealing a linear speedup in minibatch size. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hilal Asi; Karan Chadha; Gary Cheng; John C. Duchi; | |
| 1843 | Attribute Prototype Network For Zero-Shot Learning Highlight: To this end, we propose a novel zero-shot representation learning framework that jointly learns discriminative global and local features using only class-level attributes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenjia Xu; Yongqin Xian; Jiuniu Wang; Bernt Schiele; Zeynep Akata; | |
| 1844 | CrossTransformers: Spatially-aware Few-shot Transfer Highlight: In this work, we illustrate how the neural network representations which underpin modern vision systems are subject to supervision collapse, whereby they lose any information that is not necessary for performing the training task, including information that may be necessary for transfer to new tasks or domains. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Carl Doersch; Ankush Gupta; Andrew Zisserman; | |
| 1845 | Learning Latent Space Energy-Based Prior Model Highlight: We propose an energy-based model (EBM) in the latent space of a generator model, so that the EBM serves as a prior model that stands on the top-down network of the generator model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bo Pang; Tian Han; Erik Nijkamp; Song-Chun Zhu; Ying Nian Wu; | |
| 1846 | Learning Long-Term Dependencies In Irregularly-Sampled Time Series Highlight: We provide a solution by designing a new algorithm based on the long short-term memory (LSTM) that separates its memory from its time-continuous state. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mathias Lechner; Ramin Hasani; | |
| 1847 | SEVIR : A Storm Event Imagery Dataset For Deep Learning Applications In Radar And Satellite Meteorology Highlight: To help address this problem, we introduce the Storm EVent ImagRy (SEVIR) dataset – a single, rich dataset that combines spatially and temporally aligned data from multiple sensors, along with baseline implementations of deep learning models and evaluation metrics, to accelerate new algorithmic innovations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mark Veillette; Siddharth Samsi; Chris Mattioli; | |
| 1848 | Lightweight Generative Adversarial Networks For Text-Guided Image Manipulation Highlight: We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Bowen Li; Xiaojuan Qi; Philip Torr; Thomas Lukasiewicz; | |
| 1849 | High-Dimensional Contextual Policy Search With Unknown Context Rewards Using Bayesian Optimization Highlight: We develop effective models that leverage the structure of the search space to enable contextual policy optimization directly from the aggregate rewards using Bayesian optimization. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Qing Feng ; Ben Letham; Hongzi Mao; Eytan Bakshy; | |
| 1850 | Model Fusion Via Optimal Transport Highlight: We present a layer-wise model fusion algorithm for neural networks that utilizes optimal transport to (soft-) align neurons across the models before averaging their associated parameters. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sidak Pal Singh; Martin Jaggi; | code |
| 1851 | On The Stability And Convergence Of Robust Adversarial Reinforcement Learning: A Case Study On Linear Quadratic Systems Highlight: In this work, we reexamine the effectiveness of RARL under a fundamental robust control setting: the linear quadratic (LQ) case. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kaiqing Zhang; Bin Hu; Tamer Basar; | |
| 1852 | Learning Individually Inferred Communication For Multi-Agent Cooperation Highlight: To tackle these difficulties, we propose Individually Inferred Communication (I2C), a simple yet effective model to enable agents to learn a prior for agent-agent communication. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ziluo Ding; Tiejun Huang; Zongqing Lu; | |
| 1853 | Set2Graph: Learning Graphs From Sets Highlight: This paper advocates a family of neural network models for learning Set2Graph functions that is both practical and of maximal expressive power (universal), that is, can approximate arbitrary continuous Set2Graph functions over compact sets. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hadar Serviansky; Nimrod Segol; Jonathan Shlomi; Kyle Cranmer; Eilam Gross; Haggai Maron; Yaron Lipman; | |
| 1854 | Graph Random Neural Networks For Semi-Supervised Learning On Graphs Highlight: In this paper, we propose a simple yet effective framework—GRAPH RANDOM NEURAL NETWORKS (GRAND)—to address these issues. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Wenzheng Feng; Jie Zhang; Yuxiao Dong; Yu Han; Huanbo Luan; Qian Xu; Qiang Yang; Evgeny Kharlamov; Jie Tang; | code |
| 1855 | Gradient Boosted Normalizing Flows Highlight: We propose an alternative: Gradient Boosted Normalizing Flows (GBNF) model a density by successively adding new NF components with gradient boosting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Robert Giaquinto; Arindam Banerjee; | |
| 1856 | Open Graph Benchmark: Datasets For Machine Learning On Graphs Highlight: We present the Open Graph Benchmark (OGB), a diverse set of challenging and realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine learning (ML) research. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Weihua Hu; Matthias Fey; Marinka Zitnik; Yuxiao Dong; Hongyu Ren; Bowen Liu; Michele Catasta; Jure Leskovec; | code |
| 1857 | Towards Understanding Hierarchical Learning: Benefits Of Neural Representations Highlight: In this work, we demonstrate that intermediate \emph{neural representations} add more flexibility to neural networks and can be advantageous over raw inputs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Minshuo Chen; Yu Bai; Jason D. Lee; Tuo Zhao; Huan Wang; Caiming Xiong; Richard Socher; | |
| 1858 | Texture Interpolation For Probing Visual Perception Highlight: Here, we show that distributions of deep convolutional neural network (CNN) activations of a texture are well described by elliptical distributions and therefore, following optimal transport theory, constraining their mean and covariance is sufficient to generate new texture samples. Then, we propose the natural geodesics (ie the shortest path between two points) arising with the optimal transport metric to interpolate between arbitrary textures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jonathan Vacher; Aida Davila; Adam Kohn; Ruben Coen-Cagli; | |
| 1859 | Hierarchical Neural Architecture Search For Deep Stereo Matching Highlight: In this paper, we propose the first \emph{end-to-end} hierarchical NAS framework for deep stereo matching by incorporating task-specific human knowledge into the neural architecture search framework. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Xuelian Cheng; Yiran Zhong; Mehrtash Harandi; Yuchao Dai; Xiaojun Chang; Hongdong Li; Tom Drummond; Zongyuan Ge; | code |
| 1860 | MuSCLE: Multi Sweep Compression Of LiDAR Using Deep Entropy Models Highlight: We present a novel compression algorithm for reducing the storage of LiDAR sensory data streams. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Sourav Biswas; Jerry Liu; Kelvin Wong; Shenlong Wang; Raquel Urtasun; | |
| 1861 | Implicit Bias In Deep Linear Classification: Initialization Scale Vs Training Accuracy Highlight: We provide a detailed asymptotic study of gradient flow trajectories and their implicit optimization bias when minimizing the exponential loss over "diagonal linear networks". Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edward Moroshko; Blake E. Woodworth; Suriya Gunasekar; Jason D. Lee; Nati Srebro; Daniel Soudry; | |
| 1862 | Focus Of Attention Improves Information Transfer In Visual Features Highlight: In this paper we focus on unsupervised learning for transferring visual information in a truly online setting by using a computational model that is inspired to the principle of least action in physics. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matteo Tiezzi; Stefano Melacci; Alessandro Betti; Marco Maggini; Marco Gori; | |
| 1863 | Auditing Differentially Private Machine Learning: How Private Is Private SGD? Highlight: More generally, our work takes a quantitative, empirical approach to understanding the privacy afforded by specific implementations of differentially private algorithms that we believe has the potential to complement and influence analytical work on differential privacy. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Matthew Jagielski; Jonathan Ullman; Alina Oprea; | |
| 1864 | A Dynamical Central Limit Theorem For Shallow Neural Networks Highlight: Here, we analyze the mean-field dynamics as a Wasserstein gradient flow and prove that the deviations from the mean-field evolution scaled by the width, in the width-asymptotic limit, remain bounded throughout training. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhengdao Chen; Grant Rotskoff; Joan Bruna; Eric Vanden-Eijnden; | |
| 1865 | Measuring Systematic Generalization In Neural Proof Generation With Transformers Highlight: We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nicolas Gontier; Koustuv Sinha; Siva Reddy; Chris Pal; | |
| 1866 | Big Self-Supervised Models Are Strong Semi-Supervised Learners Highlight: A key ingredient of our approach is the use of big (deep and wide) networks during pretraining and fine-tuning. We find that, the fewer the labels, the more this approach (task-agnostic use of unlabeled data) benefits from a bigger network. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ting Chen; Simon Kornblith; Kevin Swersky; Mohammad Norouzi; Geoffrey E. Hinton; | |
| 1867 | Learning From Label Proportions: A Mutual Contamination Framework Highlight: In this work we address these two issues by posing LLP in terms of mutual contamination models (MCMs), which have recently been applied successfully to study various other weak supervision settings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Clayton Scott; Jianxin Zhang; | |
| 1868 | Fast Matrix Square Roots With Applications To Gaussian Processes And Bayesian Optimization Highlight: While existing methods typically require O(N^3) computation, we introduce a highly-efficient quadratic-time algorithm for computing K^{1/2}b, K^{-1/2}b, and their derivatives through matrix-vector multiplication (MVMs). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Geoff Pleiss; Martin Jankowiak; David Eriksson; Anil Damle; Jacob Gardner; | |
| 1869 | Self-Adaptively Learning To Demoir� From Focused And Defocused Image Pairs Highlight: In this paper, we propose a self-adaptive learning method for demoiréing a high-frequency image, with the help of an additional defocused moiré-free blur image. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lin Liu; Shanxin Yuan; Jianzhuang Liu; Liping Bao; Gregory Slabaugh; Qi Tian; | |
| 1870 | Confounding-Robust Policy Evaluation In Infinite-Horizon Reinforcement Learning Highlight: We develop a robust approach that estimates sharp bounds on the (unidentifiable) value of a given policy in an infinite-horizon problem given data from another policy with unobserved confounding, subject to a sensitivity model. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nathan Kallus; Angela Zhou; | |
| 1871 | Model Class Reliance For Random Forests Highlight: In this paper we introduce a new technique that extends computation of Model Class Reliance (MCR) to Random Forest classifiers and regressors. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Gavin Smith; Roberto Mansilla; James Goulding; | |
| 1872 | Follow The Perturbed Leader: Optimism And Fast Parallel Algorithms For Smooth Minimax Games Highlight: In this work, we show that when the sequence of loss functions is \emph{predictable}, a simple modification of FTPL which incorporates optimism can achieve better regret guarantees, while retaining the optimal worst-case regret guarantee for unpredictable sequences. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Arun Suggala; Praneeth Netrapalli; | |
| 1873 | Agnostic $Q$-learning With Function Approximation In Deterministic Systems: Near-Optimal Bounds On Approximation Error And Sample Complexity Highlight: We propose a novel recursion-based algorithm and show that if $\delta = O\left(\rho/\sqrt{\dim_E}\right)$, then one can find the optimal policy using $O(\dim_E)$ trajectories, where $\rho$ is the gap between the optimal $Q$-value of the best actions and that of the second-best actions and $\dim_E$ is the Eluder dimension of $\mathcal{F}$. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simon S. Du; Jason D. Lee; Gaurav Mahajan; Ruosong Wang; | |
| 1874 | Learning To Adapt To Evolving Domains Highlight: To tackle these challenges, we propose a meta-adaptation framework which enables the learner to adapt to continually evolving target domain without catastrophic forgetting. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Hong Liu; Mingsheng Long; Jianmin Wang; Yu Wang; | |
| 1875 | Synthesizing Tasks For Block-based Programming Highlight: In this paper, we formalize the problem of synthesizing visual programming tasks. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Umair Ahmed; Maria Christakis; Aleksandr Efremov; Nigel Fernandez; Ahana Ghosh; Abhik Roychoudhury; Adish Singla; | |
| 1876 | Scalable Belief Propagation Via Relaxed Scheduling Highlight: In this paper, we focus on efficient parallel algorithms for the key machine learning task of inference on graphical models, in particular on the fundamental belief propagation algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Vitalii Aksenov; Dan Alistarh; Janne H. Korhonen; | |
| 1877 | Firefly Neural Architecture Descent: A General Approach For Growing Neural Networks Highlight: We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks’ parameters and architectures. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Lemeng Wu; Bo Liu; Peter Stone; Qiang Liu; | |
| 1878 | Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff In Regret Highlight: We propose two provably efficient model-free algorithms, Risk-Sensitive Value Iteration (RSVI) and Risk-Sensitive Q-learning (RSQ). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yingjie Fei; Zhuoran Yang; Yudong Chen; Zhaoran Wang; Qiaomin Xie; | |
| 1879 | Learning To Decode: Reinforcement Learning For Decoding Of Sparse Graph-Based Channel Codes Highlight: We show in this work that reinforcement learning can be successfully applied to decoding short to moderate length sparse graph-based channel codes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Salman Habib; Allison Beemer; Joerg Kliewer; | |
| 1880 | Faster DBSCAN Via Subsampled Similarity Queries Highlight: In this paper, we propose a simple variant called SNG-DBSCAN, which clusters based on a subsampled $\epsilon$-neighborhood graph, only requires access to similarity queries for pairs of points and in particular avoids any complex data structures which need the embeddings of the data points themselves. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Heinrich Jiang; Jennifer Jang; Jakub Lacki; | |
| 1881 | De-Anonymizing Text By Fingerprinting Language Generation Highlight: We initiate the study of code security of ML systems by investigating how nucleus sampling—a popular approach for generating text, used for applications such as auto-completion—unwittingly leaks texts typed by users. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Zhen Sun; Roei Schuster; Vitaly Shmatikov; | |
| 1882 | Multiparameter Persistence Image For Topological Machine Learning Highlight: We introduce a new descriptor for multiparameter persistence, which we call the Multiparameter Persistence Image, that is suitable for machine learning and statistical frameworks, is robust to perturbations in the data, has finer resolution than existing descriptors based on slicing, and can be efficiently computed on data sets of realistic size. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Mathieu Carrie`re; Andrew Blumberg; | |
| 1883 | PLANS: Neuro-Symbolic Program Learning From Videos Highlight: We introduce PLANS (Program LeArning from Neurally inferred Specifications), a hybrid model for program synthesis from visual observations that gets the best of both worlds, relying on (i) a neural architecture trained to extract abstract, high-level information from each raw individual input (ii) a rule-based system using the extracted information as I/O specifications to synthesize a program capturing the different observations. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Rapha�l Dang-Nhu; | |
| 1884 | Matrix Inference And Estimation In Multi-Layer Models Highlight: We consider the problem of estimating the input and hidden variables of a stochastic multi-layer neural network from an observation of the output. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Parthe Pandit; Mojtaba Sahraee Ardakan; Sundeep Rangan; Philip Schniter; Alyson K. Fletcher; | |
| 1885 | MeshSDF: Differentiable Iso-Surface Extraction Highlight: Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Edoardo Remelli; Artem Lukoyanov; Stephan Richter; Benoit Guillard; Timur Bagautdinov; Pierre Baque; Pascal Fua; | |
| 1886 | Variational Interaction Information Maximization For Cross-domain Disentanglement Highlight: We derive a tractable bound of the objective and propose a generative model named Interaction Information Auto-Encoder (IIAE). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
HyeongJoo Hwang; Geon-Hyeong Kim; Seunghoon Hong; Kee-Eung Kim; | |
| 1887 | Provably Efficient Exploration For Reinforcement Learning Using Unsupervised Learning Highlight: We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a no-regret tabular RL algorithm. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Fei Feng; Ruosong Wang; Wotao Yin; Simon S. Du; Lin Yang; | |
| 1888 | Faithful Embeddings For Knowledge Base Queries Highlight: We address this problem with a novel QE method that is more faithful to deductive reasoning, and show that this leads to better performance on complex queries to incomplete KBs. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Haitian Sun; Andrew Arnold; Tania Bedrax Weiss; Fernando Pereira; William W. Cohen; | |
| 1889 | Wasserstein Distances For Stereo Disparity Estimation Highlight: We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Divyansh Garg; Yan Wang; Bharath Hariharan; Mark Campbell; Kilian Q. Weinberger; Wei-Lun Chao; | |
| 1890 | Multi-agent Trajectory Prediction With Fuzzy Query Attention Highlight: Specifically, we propose a relational model to flexibly model interactions between agents in diverse environments. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Nitin Kamra; Hao Zhu; Dweep Kumarbhai Trivedi; Ming Zhang; Yan Liu; | |
| 1891 | Multilabel Classification By Hierarchical Partitioning And Data-dependent Grouping Highlight: In this paper we exploit the sparsity of label vectors and the hierarchical structure to embed them in low-dimensional space using label groupings. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Shashanka Ubaru; Sanjeeb Dash; Arya Mazumdar; Oktay Gunluk; | |
| 1892 | An Analysis Of SVD For Deep Rotation Estimation Highlight: We present a theoretical analysis of SVD as used for projection onto the rotation group. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jake Levinson; Carlos Esteves; Kefan Chen; Noah Snavely; Angjoo Kanazawa; Afshin Rostamizadeh; Ameesh Makadia; | |
| 1893 | Can The Brain Do Backpropagation? — Exact Implementation Of Backpropagation In Predictive Coding Networks Highlight: We propose a BL model that (1) produces \emph{exactly the same} updates of the neural weights as~BP, while (2)~employing local plasticity, i.e., all neurons perform only local computations, done simultaneously. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yuhang Song; Thomas Lukasiewicz; Zhenghua Xu; Rafal Bogacz; | |
| 1894 | Manifold GPLVMs For Discovering Non-Euclidean Latent Structure In Neural Data Highlight: Here, we propose a new probabilistic latent variable model to simultaneously identify the latent state and the way each neuron contributes to its representation in an unsupervised way. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Kristopher Jensen; Ta-Chu Kao; Marco Tripodi; Guillaume Hennequin; | |
| 1895 | Distributed Distillation For On-Device Learning Highlight: To overcome these limitations, we introduce a distributed distillation algorithm where devices communicate and learn from soft-decision (softmax) outputs, which are inherently architecture-agnostic and scale only with the number of classes. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Ilai Bistritz; Ariana Mann; Nicholas Bambos; | |
| 1896 | COOT: Cooperative Hierarchical Transformer For Video-Text Representation Learning Highlight: In this paper, we propose a Cooperative hierarchical Transformer (COOT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Simon Ging; Mohammadreza Zolfaghari; Hamed Pirsiavash; Thomas Brox; | |
| 1897 | Passport-aware Normalization For Deep Model Protection Highlight: To this end, we propose a new passport-aware normalization formulation, which is generally applicable to most existing normalization layers and only needs to add another passport-aware branch for IP protection. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Jie Zhang; Dongdong Chen; Jing Liao; Weiming Zhang; Gang Hua; Nenghai Yu; | |
| 1898 | Sampling-Decomposable Generative Adversarial Recommender Highlight: Based on these findings, we propose a Sampling-Decomposable Generative Adversarial Recommender (SD-GAR). Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Binbin Jin; Defu Lian; Zheng Liu; Qi Liu; Jianhui Ma; Xing Xie; Enhong Chen; | |
| 1899 | Limits To Depth Efficiencies Of Self-Attention Highlight: In this paper, we theoretically study the interplay between depth and width in self-attention. Related Papers Related Patents Related Grants Related Orgs Related Experts Details |
Yoav Levine; Noam Wies; Or Sharir; Hofit Bata; Amnon Shashua; |