Learning Theory

Prediction against a limited adversary JMLR 2021 Prediction with Finitely many Errors Almost Surely AISTATS 2021 Predictive Learning on Hidden Tree-Structured Ising Models JMLR 2021 Private learning implies quantum stability NeurIPS 2021 Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions ICML 2021 Probing for idiomaticity in vector space models EACL 2021 Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits AISTATS 2021 Problem Dependent View on Structured Thresholding Bandit Problems ICML 2021 Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise ICML 2021 Provable Memorization via Deep Neural Networks using Sub-linear Parameters COLT 2021 Provable Rich Observation Reinforcement Learning with Combinatorial Latent States ICLR 2021 Provable Robustness of Adversarial Training for Learning Halfspaces with Noise ICML 2021 Provably Correct Optimization and Exploration with Non-linear Policies ICML 2021 Provably Efficient Algorithms for Multi-Objective Competitive RL ICML 2021 Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions ICML 2021 Provably efficient multi-task reinforcement learning with model transfer NeurIPS 2021 Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping ICML 2021 Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints NeurIPS 2021 Provably efficient, succinct, and precise explanations NeurIPS 2021 Provably Sample Efficient Reinforcement Learning in Competitive Linear Quadratic Systems L4DC 2021 Provably Strict Generalisation Benefit for Equivariant Models ICML 2021 Provably Strict Generalisation Benefit for Invariance in Kernel Methods NeurIPS 2021 Pure Exploration in Kernel and Neural Bandits NeurIPS 2021 Q-learning with Logarithmic Regret AISTATS 2021 Quantifying and Improving Transferability in Domain Generalization NeurIPS 2021