Learning Theory

Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts ICLR 2025 Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing ICLR 2025 Density Ratio Estimation with Conditional Probability Paths ICML 2025 Determinant Estimation under Memory Constraints and Neural Scaling Laws ICML 2025 Deterministic Apple Tasting COLT 2025 Differential learning kinetics govern the transition from memorization to generalization during in-context learning ICLR 2025 Differentially Private Kernelized Contextual Bandits AISTATS 2025 Differential Privacy Mechanisms in Neural Tangent Kernel Regression WACV 2025 Differential Privacy Under Class Imbalance: Methods and Empirical Insights ICML 2025 Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates AAAI 2025 Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient ICLR 2025 Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models ICLR 2025 Dimension-Independent Rates for Structured Neural Density Estimation ICML 2025 Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension ICML 2025 Discrete Neural Algorithmic Reasoning ICML 2025 Disentangled Graph Spectral Domain Adaptation ICML 2025 Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study EMNLP 2025 Dissecting the Impact of Model Misspecification in Data-Driven Optimization AISTATS 2025 Distilling the Knowledge in Data Pruning ICML 2025 Distinguishing fair from unfair compositional generalization tasks EMNLP 2025 Distributed Conformal Prediction via Message Passing ICML 2025 Distributionally Robust Policy Learning under Concept Drifts ICML 2025 Distribution-Specific Agnostic Conditional Classification With Halfspaces ICLR 2025 DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models EMNLP 2025 Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? EMNLP 2025