Learning Theory

Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems L4DC 2020 Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks ICLR 2020 Precise Tradeoffs in Adversarial Training for Linear Regression COLT 2020 Predicting Performance for Natural Language Processing Tasks ACL 2020 Prediction with Corrupted Expert Advice NeurIPS 2020 Privately Answering Classification Queries in the Agnostic PAC Model ALT 2020 Privately Learning Thresholds: Closing the Exponential Gap COLT 2020 Probably Approximately Correct Constrained Learning NeurIPS 2020 Probing for Multilingual Numerical Understanding in Transformer-Based Language Models EMNLP 2020 Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction ACL 2020 Production-based Cognitive Models as a Test Suite for Reinforcement Learning Algorithms EMNLP 2020 Proper Learning, Helly Number, and an Optimal SVM Bound COLT 2020 Provable guarantees for decision tree induction: the agnostic setting ICML 2020 Provably adaptive reinforcement learning in metric spaces NeurIPS 2020 Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning NeurIPS 2020 Provably Efficient Exploration in Policy Optimization ICML 2020 Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations NeurIPS 2020 Provably efficient reinforcement learning with linear function approximation COLT 2020 Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison UAI 2020 Quantitative Propagation of Chaos for SGD in Wide Neural Networks NeurIPS 2020 Reasoning About Generalization via Conditional Mutual Information COLT 2020 Recovery of Sparse Signals from a Mixture of Linear Samples ICML 2020 Reducibility and Statistical-Computational Gaps from Secret Leakage COLT 2020 Reducing Adversarially Robust Learning to Non-Robust PAC Learning NeurIPS 2020 Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems UAI 2020