Learning Theory

Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity ICML 2021 Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting NeurIPS 2021 Sample Efficient Reinforcement Learning with REINFORCE AAAI 2021 Sample-Optimal PAC Learning of Halfspaces with Malicious Noise ICML 2021 Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot ICML 2021 Scalable Intervention Target Estimation in Linear Models NeurIPS 2021 Scalable Thompson Sampling using Sparse Gaussian Process Models NeurIPS 2021 Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs ICLR 2021 Self-Attention Networks Can Process Bounded Hierarchical Languages ACL 2021 Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics NeurIPS 2021 Sequential prediction under log-loss and misspecification COLT 2021 Sequential prediction under log-loss with side information ALT 2021 SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation AISTATS 2021 SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021 SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs NeurIPS 2021 Sharp Analysis of a Simple Model for Random Forests AISTATS 2021 Sharper Generalization Bounds for Clustering ICML 2021 Sharper Generalization Bounds for Learning with Gradient-dominated Objective Functions ICLR 2021 Shift Invariance Can Reduce Adversarial Robustness NeurIPS 2021 Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples JMLR 2021 Simple combinatorial algorithms for combinatorial bandits: corruptions and approximations UAI 2021 Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent ACL 2021 Simpson's Bias in NLP Training AAAI 2021 Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection NeurIPS 2021 Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy ICLR 2021