Learning Theory

OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres ACL 2021 Optimal Algorithms for Stochastic Contextual Preference Bandits NeurIPS 2021 Optimal Dynamic Regret in Exp-Concave Online Learning COLT 2021 Optimal prediction of Markov chains with and without spectral gap NeurIPS 2021 Optimal Rates of Distributed Regression with Imperfect Kernels JMLR 2021 Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings NeurIPS 2021 Optimism in Reinforcement Learning with Generalized Linear Function Approximation ICLR 2021 Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD NeurIPS 2021 Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure NeurIPS 2021 Outlier-Robust Learning of Ising Models Under Dobrushin’s Condition COLT 2021 Overparameterization Improves Robustness to Covariate Shift in High Dimensions NeurIPS 2021 PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes COLT 2021 PAC-Learning for Strategic Classification ICML 2021 PAC Learning of Causal Trees with Latent Variables AAAI 2021 **Paper retracted by author request (see pdf for retraction notice from the authors)** Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping COLT 2021 Parameter-free HE-friendly Logistic Regression NeurIPS 2021 Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies AAAI 2021 Parametric Complexity Bounds for Approximating PDEs with Neural Networks NeurIPS 2021 Passive learning of Timed Automata from logs (Student Abstract) AAAI 2021 PeerReview4All: Fair and Accurate Reviewer Assignment in Peer Review JMLR 2021 Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning ICML 2021 Power of Hints for Online Learning with Movement Costs AISTATS 2021 Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers NeurIPS 2021 Predicting Deep Neural Network Generalization with Perturbation Response Curves NeurIPS 2021 Predicting What You Already Know Helps: Provable Self-Supervised Learning NeurIPS 2021