Learning Theory

When Is Generalizable Reinforcement Learning Tractable? NeurIPS 2021 When Is Unsupervised Disentanglement Possible? NeurIPS 2021 Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? ICLR 2021 Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks NeurIPS 2021 WILDS: A Benchmark of in-the-Wild Distribution Shifts ICML 2021 Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging ICML 2021 A Bayesian Perspective on Training Speed and Model Selection NeurIPS 2020 Abstraction Mechanisms Predict Generalization in Deep Neural Networks ICML 2020 A Closer Look at Small-loss Bounds for Bandits with Graph Feedback COLT 2020 A Closer Look at the Training Strategy for Modern Meta-Learning NeurIPS 2020 A Computational Separation between Private Learning and Online Learning NeurIPS 2020 A Constructive Prediction of the Generalization Error Across Scales ICLR 2020 Active Learning in the Geometric Block Model AAAI 2020 Active Local Learning COLT 2020 Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality JMLR 2020 A determinantal point process for column subset selection JMLR 2020 A Distance-Weighted Class-Homogeneous Neighbourhood Ratio for Algorithm Selection ACML 2020 A Duality Approach for Regret Minimization in Average-Award Ergodic Markov Decision Processes L4DC 2020 Adversarial Bandits with Corruptions: Regret Lower Bound and No-regret Algorithm NeurIPS 2020 Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks ICML 2020 A Dynamical Central Limit Theorem for Shallow Neural Networks NeurIPS 2020 A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates COLT 2020 A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation ICML 2020 A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling NeurIPS 2020