Learning Theory

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning ICML 2021 Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures NeurIPS 2021 Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs JMLR 2021 Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning NeurIPS 2021 Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach ICML 2021 Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ICML 2021 RL for Latent MDPs: Regret Guarantees and a Lower Bound NeurIPS 2021 RNNRepair: Automatic RNN Repair via Model-based Analysis ICML 2021 Robust Contextual Bandits via Bootstrapping AAAI 2021 Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free ICML 2021 Robust Generalization despite Distribution Shift via Minimum Discriminating Information NeurIPS 2021 Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time ICLR 2021 Robust Learning of Optimal Auctions NeurIPS 2021 Robust Learning under Strong Noise via SQs AISTATS 2021 Robust Pure Exploration in Linear Bandits with Limited Budget ICML 2021 Robust reinforcement learning under minimax regret for green security UAI 2021 Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions CoRL 2021 Safe Reinforcement Learning with Linear Function Approximation ICML 2021 Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons NeurIPS 2021 Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model ALT 2021 Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms AISTATS 2021 Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems L4DC 2021 Sample Complexity of Policy Gradient Finding Second-Order Stationary Points AAAI 2021 Sample Complexity of Robust Linear Classification on Separated Data ICML 2021 Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond NeurIPS 2021