Learning Theory

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses AISTATS 2025 Sample-Optimal Agnostic Boosting with Unlabeled Data ICML 2025 Sampling Boundary for Causal Effect Estimation ACML 2025 SAND: One-Shot Feature Selection with Additive Noise Distortion ICML 2025 Satisficing Regret Minimization in Bandits ICLR 2025 Scalable Acceleration for Classification-Based Derivative-Free Optimization AAAI 2025 Scalable Influence and Fact Tracing for Large Language Model Pretraining ICLR 2025 Scalable Model Merging with Progressive Layer-wise Distillation ICML 2025 Scalable Sobolev IPM for Probability Measures on a Graph ICML 2025 Scaling Data-Constrained Language Models JMLR 2025 Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check EMNLP 2025 Scaling Laws for Downstream Task Performance in Machine Translation ICLR 2025 Scaling Laws for Multilingual Language Models ACL 2025 Scaling Test-Time Compute Without Verification or RL is Suboptimal ICML 2025 Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning ICML 2025 ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model CVPR 2025 Scenario-Based Robust Optimization of Tree Structures AAAI 2025 Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows ICML 2025 Second Order Bounds for Contextual Bandits with Function Approximation ICLR 2025 Selective Induction Heads: How Transformers Select Causal Structures in Context ICLR 2025 Self-Consuming Generative Models with Adversarially Curated Data ICML 2025 Self-Improvement in Language Models: The Sharpening Mechanism ICLR 2025 SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses AAAI 2025 Self-Play Q-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma ICML 2025 Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning ICML 2025