Learning Theory

Generation through the lens of learning theory COLT 2025 Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates ICML 2025 Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems ICML 2025 Geometry and Stability of Supervised Learning Problems JMLR 2025 Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits ICLR 2025 Geometry of Lightning Self-Attention: Identifiability and Dimension ICLR 2025 Global Convergence and Rich Feature Learning in L-Layer Infinite-Width Neural Networks under μ Parametrization ICML 2025 Global Convergence of Adjoint-Optimized Neural PDEs JMLR 2025 Global Convergence of Policy Gradient in Average Reward MDPs ICLR 2025 GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in Graphs ICLR 2025 GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration ACL 2025 Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs ICML 2025 Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations ICCV 2025 Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models ICML 2025 Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation ICML 2025 GraphRouter: A Graph-based Router for LLM Selections ICLR 2025 Grokking at the Edge of Linear Separability ICML 2025 Grokking Beyond the Euclidean Norm of Model Parameters ICML 2025 Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift AISTATS 2025 Heterogeneous Label Shift: Theory and Algorithm ICML 2025 Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It ICML 2025 Hierarchical Reinforcement Learning with Targeted Causal Interventions ICML 2025 High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws ICLR 2025 High-Dimensional L2-Boosting: Rate of Convergence JMLR 2025 High-Dimensional Tensor Regression With Oracle Properties ICML 2025