learning theory

Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden’s J statistic EACL 2026 Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning AAAI 2026 Capacity Constraints Make Admissions Processes Less Predictable AAAI 2026 Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds AAAI 2026 Learning from Synthetic Data: Limitations of ERM ALT 2026 Limitations of SGD for Multi-Index Models Beyond Statistical Queries COLT 2026 Memorization and Expressivity in Transformers: A Learning-Theoretic Perspective AAAI 2026 On Coresets for End-to-end Learning from Crowds AAAI 2026 On the Probabilistic Learnability of Compact Neural Network Preimage Bounds AAAI 2026 Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms AAAI 2026 Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport (Abstract Reprint) AAAI 2026 Unified Structural Factors for Transfer Learning Generalization with PAC-Bayesian Guarantees AAAI 2026 An Effective Theory of Bias Amplification ICLR 2025 Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure ICLR 2025 A Theory of Initialisation's Impact on Specialisation ICLR 2025 A Unified Interpretation of Training-Time Out-of-Distribution Detection ICCV 2025 A Unified Theory of Quantum Neural Network Loss Landscapes ICLR 2025 Can In-context Learning Really Generalize to Out-of-distribution Tasks? ICLR 2025 Competition Dynamics Shape Algorithmic Phases of In-Context Learning ICLR 2025 Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025 Deconstructing Attention: Investigating Design Principles for Effective Language Modeling IJCNLP 2025 Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing ICLR 2025 Formation of Representations in Neural Networks ICLR 2025 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks ICLR 2025 Fundamental computational limits of weak learnability in high-dimensional multi-index models AISTATS 2025