Learning Theory

The Trade-offs of Domain Adaptation for Neural Language Models ACL 2022 The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization CVPR 2022 The Uncanny Similarity of Recurrence and Depth ICLR 2022 Tight bounds for minimum ℓ_1-norm interpolation of noisy data AISTATS 2022 Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes NeurIPS 2022 Tight query complexity bounds for learning graph partitions COLT 2022 Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints NeurIPS 2022 Top K Ranking for Multi-Armed Bandit with Noisy Evaluations AISTATS 2022 Toward learning human-aligned cross-domain robust models by countering misaligned features UAI 2022 Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise AISTATS 2022 Towards Bridging Sample Complexity and Model Capacity AAAI 2022 Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality ICLR 2022 Towards General Function Approximation in Zero-Sum Markov Games ICLR 2022 Towards IID representation learning and its application on biomedical data MIDL 2022 Towards painless policy optimization for constrained MDPs UAI 2022 Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent AISTATS 2022 Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs ICML 2022 Towards Understanding Generalization via Decomposing Excess Risk Dynamics ICLR 2022 Towards Understanding Grokking: An Effective Theory of Representation Learning NeurIPS 2022 Towards understanding how momentum improves generalization in deep learning ICML 2022 Towards Understanding Sharpness-Aware Minimization ICML 2022 Towards Understanding the Condensation of Neural Networks at Initial Training NeurIPS 2022 Towards Understanding the Mixture-of-Experts Layer in Deep Learning NeurIPS 2022 Trading Off Resource Budgets For Improved Regret Bounds NeurIPS 2022 Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent JMLR 2022