Learning Theory

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems NeurIPS 2021 Near-Optimal Offline Reinforcement Learning via Double Variance Reduction NeurIPS 2021 Near Optimal Reward-Free Reinforcement Learning ICML 2021 Near-tight Closure Bounds for the Littlestone and Threshold Dimensions ALT 2021 Network Inference and Influence Maximization from Samples ICML 2021 NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation JMLR 2021 Neural Active Learning with Performance Guarantees NeurIPS 2021 Neural Pseudo-Label Optimism for the Bank Loan Problem NeurIPS 2021 Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex NeurIPS 2021 Neural Tangent Kernel Maximum Mean Discrepancy NeurIPS 2021 Never Go Full Batch (in Stochastic Convex Optimization) NeurIPS 2021 Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis NeurIPS 2021 Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance L4DC 2021 Non-stationary Reinforcement Learning without Prior Knowledge: an Optimal Black-box Approach COLT 2021 Non-uniform Consistency of Online Learning with Random Sampling ALT 2021 No-regret Algorithms for Multi-task Bayesian Optimization AISTATS 2021 Norm-Based Generalisation Bounds for Deep Multi-Class Convolutional Neural Networks AAAI 2021 No-substitution k-means Clustering with Adversarial Order ALT 2021 Not all parameters are born equal: Attention is mostly what you need EMNLP 2021 Offline Contextual Bandits with Overparameterized Models ICML 2021 On Belief Change for Multi-Label Classifier Encodings IJCAI 2021 On Empirical Risk Minimization with Dependent and Heavy-Tailed Data NeurIPS 2021 On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting ICML 2021 On Learning Continuous Pairwise Markov Random Fields AISTATS 2021 On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources NeurIPS 2021