Learning Theory

Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs ICLR 2024 How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model ICML 2024 How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization? NeurIPS 2024 How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach NeurIPS 2024 How Does Unlabeled Data Provably Help Out-of-Distribution Detection? ICLR 2024 How Does Variance Shape the Regret in Contextual Bandits? NeurIPS 2024 How Do Large Language Models Acquire Factual Knowledge During Pretraining? NeurIPS 2024 How Do Nonlinear Transformers Learn and Generalize in In-Context Learning? ICML 2024 How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad NeurIPS 2024 How Flawed Is ECE? An Analysis via Logit Smoothing ICML 2024 How Hard Is It to Impact the Impact of Your Paper? IJCAI 2024 How many classifiers do we need? NeurIPS 2024 How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? ICLR 2024 How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization ICLR 2024 How Spurious Features are Memorized: Precise Analysis for Random and NTK Features ICML 2024 How to Boost Any Loss Function NeurIPS 2024 How to Escape Sharp Minima with Random Perturbations ICML 2024 How to Explore with Belief: State Entropy Maximization in POMDPs ICML 2024 How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization ICML 2024 How to Solve Contextual Goal-Oriented Problems with Offline Datasets? NeurIPS 2024 How Transformers Learn Causal Structure with Gradient Descent ICML 2024 How Two-Layer Neural Networks Learn, One (Giant) Step at a Time JMLR 2024 How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers ICML 2024 Hybrid Inverse Reinforcement Learning ICML 2024 Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank ICML 2024