Learning Theory

Separation Power of Equivariant Neural Networks ICLR 2025 Set-Valued Sensitivity Analysis of Deep Neural Networks AAAI 2025 Shallow diffusion networks provably learn hidden low-dimensional structure ICLR 2025 Shapley Value Computation in Ontology-Mediated Query Answering (Extended Abstract) IJCAI 2025 Sharp bounds on aggregate expert error ALT 2025 Sharper Bounds for Chebyshev Moment Matching, with Applications COLT 2025 Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods ICLR 2025 Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate ICML 2025 Sharpness-Aware Minimization: General Analysis and Improved Rates ICLR 2025 Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks ICML 2025 Simplifying Adversarially Robust PAC Learning With Tolerance COLT 2025 Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks ICLR 2025 Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale ICLR 2025 SOI Matters: Analyzing Multi-Setting Training Dynamics in Pretrained Language Models via Subsets of Interest EMNLP 2025 Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery COLT 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Speeding Up the NSGA-II with a Simple Tie-Breaking Rule AAAI 2025 Spherical Dimension COLT 2025 Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion ICML 2025 Stability and Generalization for Stochastic (Compositional) Optimizations IJCAI 2025 Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology AAAI 2025 Stability and List-Replicability for Agnostic Learners COLT 2025 Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning AAAI 2025 Stabilizing Sample Similarity in Representation via Mitigating Random Consistency ICML 2025 Stable Fair Graph Representation Learning with Lipschitz Constraint ICML 2025