Learning Theory

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks JMLR 2024 Least Squares Regression Can Exhibit Under-Parameterized Double Descent NeurIPS 2024 Length independent PAC-Bayes bounds for Simple RNNs AISTATS 2024 Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often! ICML 2024 Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking EMNLP 2024 Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures AISTATS 2024 Linear bandits with polylogarithmic minimax regret COLT 2024 Linear Regression using Heterogeneous Data Batches NeurIPS 2024 List Sample Compression and Uniform Convergence COLT 2024 LLM Circuit Analyses Are Consistent Across Training and Scale NeurIPS 2024 Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit NeurIPS 2024 Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs NeurIPS 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning NeurIPS 2024 Logical characterizations of recurrent graph neural networks with reals and floats NeurIPS 2024 Logical Languages Accepted by Transformer Encoders with Hard Attention ICLR 2024 Lookback Prophet Inequalities NeurIPS 2024 Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains AAAI 2024 Low Degree Hardness for Broadcasting on Trees NeurIPS 2024 Low-degree phase transitions for detecting a planted clique in sublinear time COLT 2024 Lower Bounds on the Expressivity of Recurrent Neural Language Models NAACL 2024 Lower Complexity Bounds of Finite-Sum Optimization Problems: The Results and Construction JMLR 2024 Lower-level Duality Based Reformulation and Majorization Minimization Algorithm for Hyperparameter Optimization AISTATS 2024 Low-rank Matrix Bandits with Heavy-tailed Rewards UAI 2024 Low-rank MDPs with Continuous Action Spaces AISTATS 2024