Theory

Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers NeurIPS 2021 Prediction against a limited adversary JMLR 2021 Present-Biased Optimization AAAI 2021 Probabilistic Sufficient Explanations IJCAI 2021 Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits AISTATS 2021 Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021 Provable Hierarchical Imitation Learning via EM AISTATS 2021 Provable Lipschitz Certification for Generative Models ICML 2021 Provably Safe PAC-MDP Exploration Using Analogies AISTATS 2021 Provably Strict Generalisation Benefit for Equivariant Models ICML 2021 Pure Exploration in Kernel and Neural Bandits NeurIPS 2021 Quantum algorithms for reinforcement learning with a generative model ICML 2021 Reaching Individually Stable Coalition Structures in Hedonic Games AAAI 2021 Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition NeurIPS 2021 Recursive prosody is not finite-state ACL 2021 Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021 Reinforcement Learning in Newcomblike Environments NeurIPS 2021 Relative Flatness and Generalization NeurIPS 2021 Relative stability toward diffeomorphisms indicates performance in deep nets NeurIPS 2021 Relevance-CAM: Your Model Already Knows Where To Look CVPR 2021 Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection NeurIPS 2021 Removing Foreground Occlusions in Light Field using Micro-lens Dynamic Filter IJCAI 2021 Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance ACL 2021 Representational aspects of depth and conditioning in normalizing flows ICML 2021 Representation Costs of Linear Neural Networks: Analysis and Design NeurIPS 2021