learning theory

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency ICLR 2025 Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power ICLR 2025 Generation through the lens of learning theory COLT 2025 How many samples are needed to train a deep neural network? ICLR 2025 How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs ACL 2025 Instability, Computational Efficiency and Statistical Accuracy JMLR 2025 Learnability of Parameter-Bounded Bayes Nets AAAI 2025 Learning High-Degree Parities: The Crucial Role of the Initialization ICLR 2025 Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound JMLR 2025 MGDA Converges under Generalized Smoothness, Provably ICLR 2025 No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models ICLR 2025 Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings COLING 2025 Quantifying Generalization Complexity for Large Language Models ICLR 2025 SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning EMNLP 2025 Shallow diffusion networks provably learn hidden low-dimensional structure ICLR 2025 Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology AAAI 2025 Statistical Deficiency for Task Inclusion Estimation ACL 2025 The Complexity of Sequential Prediction in Dynamical Systems L4DC 2025 The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFT EMNLP 2025 Towards a learning theory of representation alignment ICLR 2025 Towards Improved Risk Bounds for Transductive Learning IJCAI 2025 Unlocking Global Optimality in Bilevel Optimization: A Pilot Study ICLR 2025 Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability NeurIPS 2024 A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) AAAI 2024 Bagging Provides Assumption-free Stability JMLR 2024