Learning Theory

Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization ICML 2025 FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation ICML 2025 Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective ICML 2025 False Coverage Proportion Control for Conformal Prediction ICML 2025 Faster Algorithms for Agnostically Learning Disjunctions and their Implications COLT 2025 Fast Exact Unlearning for In-Context Learning Data for LLMs ICML 2025 Feature-Based Online Bilateral Trade ICLR 2025 Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry ICML 2025 Finite Sample Identification of Partially Observed Bilinear Dynamical Systems L4DC 2025 Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning ICML 2025 For Better or For Worse? Learning Minimum Variance Features With Label Augmentation ICLR 2025 For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent ALT 2025 Frequency & Compositionality in Emergent Communication EMNLP 2025 From Data to Knowledge: Evaluating How Efficiently Language Models Learn Facts ACL 2025 From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors EMNLP 2025 From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning ICML 2025 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks ICLR 2025 From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes AAAI 2025 From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling EMNLP 2025 From Parameters to Performance: A Data-Driven Study on LLM Structure and Development EMNLP 2025 From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs? EMNLP 2025 From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency ICLR 2025 From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers ICML 2025 Fundamental computational limits of weak learnability in high-dimensional multi-index models AISTATS 2025 Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds ICML 2025