Learning Theory

The True Sample Complexity of Identifying Good Arms AISTATS 2020 Thresholding Bandit Problem with Both Duels and Pulls AISTATS 2020 Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance ICML 2020 Tightening Exploration in Upper Confidence Reinforcement Learning ICML 2020 Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits NeurIPS 2020 Tight Lower Bounds for Combinatorial Multi-Armed Bandits COLT 2020 Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model NeurIPS 2020 Top-k Combinatorial Bandits with Full-Bandit Feedback ALT 2020 Towards a Combinatorial Characterization of Bounded-Memory Learning NeurIPS 2020 Towards Convergence Rate Analysis of Random Forests for Classification NeurIPS 2020 Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes NeurIPS 2020 Towards Problem-dependent Optimal Learning Rates NeurIPS 2020 Towards Robustifying NLI Models Against Lexical Dataset Biases ACL 2020 Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning NeurIPS 2020 Towards Understanding Hierarchical Learning: Benefits of Neural Representations NeurIPS 2020 Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations CVPR 2020 Toward the Fundamental Limits of Imitation Learning NeurIPS 2020 Training Linear Neural Networks: Non-Local Convergence and Complexity Results ICML 2020 Triple descent and the two kinds of overfitting: where & why do they appear? NeurIPS 2020 Truth or backpropaganda? An empirical investigation of deep learning theory ICLR 2020 Uncorrected Least-Squares Temporal Difference with Lambda-Return AAAI 2020 Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks NeurIPS 2020 Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition NeurIPS 2020 Understanding Generalization in Deep Learning via Tensor Methods AISTATS 2020 Understanding Generalization in Neural Networks for Robustness against Adversarial Vulnerabilities AAAI 2020