Learning Theory

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks NeurIPS 2023 Provable Memorization Capacity of Transformers ICLR 2023 Provable Pathways: Learning Multiple Tasks over Multiple Paths AAAI 2023 Provable Sim-to-real Transfer in Continuous Domain with Partial Observations ICLR 2023 Provably and Practically Efficient Neural Contextual Bandits ICML 2023 Provably Efficient Algorithm for Nonstationary Low-Rank MDPs NeurIPS 2023 Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization AAAI 2023 Provably Efficient Model-Free Algorithms for Non-stationary CMDPs AISTATS 2023 Provably Efficient Offline Reinforcement Learning in Regular Decision Processes NeurIPS 2023 Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources ICML 2023 Provably Efficient Reinforcement Learning via Surprise Bound AISTATS 2023 Provably Safe Reinforcement Learning with Step-wise Violation Constraints NeurIPS 2023 Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal COLT 2023 Quantifying Context Mixing in Transformers EACL 2023 Quantifying Train-Evaluation Overlap with Nearest Neighbors ACL 2023 Quantitative Universal Approximation Bounds for Deep Belief Networks ICML 2023 Quantum Channel Certification with Incoherent Measurements COLT 2023 Quasi-Equivalence between Width and Depth of Neural Networks JMLR 2023 Random Feature Amplification: Feature Learning and Generalization in Neural Networks JMLR 2023 Random Feature Neural Networks Learn Black-Scholes Type PDEs Without Curse of Dimensionality JMLR 2023 Randomness Is the Root of All Evil: More Reliable Evaluation of Deep Active Learning WACV 2023 Random Teachers are Good Teachers ICML 2023 Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? ICCV 2023 R-divergence for Estimating Model-oriented Distribution Discrepancy NeurIPS 2023 ReadPrompt: A Readable Prompting Method for Reliable Knowledge Probing EMNLP 2023