Learning Theory

Learning Curves of Stochastic Gradient Descent in Kernel Regression ICML 2025 Learning curves theory for hierarchically compositional data with power-law distributed features ICML 2025 Learning DNF through Generalized Fourier Representations COLT 2025 Learning dynamics in linear recurrent neural networks ICML 2025 Learning Dynamics of LLM Finetuning ICLR 2025 Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures ICML 2025 Learning Gaussian DAG Models without Condition Number Bounds ICML 2025 Learning general Gaussian mixtures with efficient score matching COLT 2025 Learning Hierarchical Polynomials of Multiple Nonlinear Features ICLR 2025 Learning High-Degree Parities: The Crucial Role of the Initialization ICLR 2025 Learning In-context n-grams with Transformers: Sub-n-grams Are Near-Stationary Points ICML 2025 Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span AISTATS 2025 Learning Input Encodings for Kernel-Optimal Implicit Neural Representations ICML 2025 Learning Intersections of Two Margin Halfspaces under Factorizable Distributions COLT 2025 Learning Mask Invariant Mutual Information for Masked Image Modeling ICLR 2025 Learning Mixtures of Gaussians Using Diffusion Models COLT 2025 Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics ICLR 2025 Learning multivariate Gaussians with imperfect advice ICML 2025 Learning on Model Weights using Tree Experts CVPR 2025 Learning Partitions with Optimal Query and Round Complexities COLT 2025 Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks ICML 2025 Learning Probabilistic Temporal Logic Specifications for Stochastic Systems IJCAI 2025 Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems ICML 2025 Learning-to-Optimize with PAC-Bayesian Guarantees: Theoretical Considerations and Practical Implementation JMLR 2025 Learning Trajectories of Figurative Language for Pre-Trained Language Models EMNLP 2025