Learning Theory

Do Generative Video Models Understand Physical Principles? WACV 2026 Efficient and Provable Algorithms for Covariate Shift ALT 2026 Efficient Learning and Symmetry Discovery under Exact Invariances COLT 2026 Efficient Solution and Learning of Robust Factored MDPs AAAI 2026 ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction AAAI 2026 Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift COLT 2026 Error Slice Discovery via Manifold Compactness AAAI 2026 Expert Advice with Costly Observations UAI 2026 Explore, Refine, then Commit: Nearly Optimal Multi-Group Mean Estimation with Active Learning UAI 2026 Exploring Depth Generalization in Large Language Models for Solving Recursive Logic Tasks AAAI 2026 Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity COLT 2026 Finite Sample Bounds for Learning with Score Matching COLT 2026 Finite-Sample Regret Analysis of Nash Q-Learning with Random-Feature Approximation UAI 2026 Formalizing Task-Space Complexity for Zero-Shot Generalization L4DC 2026 From Continual Learning to SGD and Back: Better Rates for Continual Linear Models ALT 2026 From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation AAAI 2026 Gaussian Approximation for Two-Timescale Linear Stochastic Approximation AAAI 2026 GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning AAAI 2026 Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint) AAAI 2026 Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference UAI 2026 Group-realizable multi-group learning by minimizing empirical risk ALT 2026 High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks JMLR 2026 High-Pass Matters: Theoretical Insights and Sheaflet-Based Design for Hypergraph Neural Networks AAAI 2026 How fast can you find a good hypothesis? COLT 2026 How Many Features Can a Language Model Store Under the Linear Representation Hypothesis? COLT 2026