Learning Theory

Stable learning using spiking neural networks equipped with affine encoders and decoders JMLR 2025 State space models, emergence, and ergodicity: How many parameters are needed for stable predictions? L4DC 2025 Statistical Deficiency for Task Inclusion Estimation ACL 2025 Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise ICML 2025 Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs ICLR 2025 Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem AISTATS 2025 Stochastic Bandits Robust to Adversarial Attacks ICLR 2025 Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs ACL 2025 Stochastic Deep Restoration Priors for Imaging Inverse Problems ICML 2025 Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets ICML 2025 STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework ACL 2025 STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving ICML 2025 Strategic Classification With Externalities ICLR 2025 Strategy Coopetition Explains the Emergence and Transience of In-Context Learning ICML 2025 Strategyproof Learning with Advice ALT 2025 Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation ICML 2025 Strong Model Collapse ICLR 2025 Strong Preferences Affect the Robustness of Preference Models and Value Alignment ICLR 2025 Structure Trumps Size: Rethinking Data Quality for LLM Reasoning EMNLP 2025 Subspace Optimization for Large Language Models with Convergence Guarantees ICML 2025 Supervised and Unsupervised Probing of Shortcut Learning: Case Study on the Emergence and Evolution of Syntactic Heuristics in BERT ACL 2025 Swing-by Dynamics in Concept Learning and Compositional Generalization ICLR 2025 Synchronization in Learning in Periodic Zero-Sum Games Triggers Divergence from Nash Equilibrium AAAI 2025 Syntactic Blind Spots: How Misalignment Leads to LLMs’ Mathematical Errors EMNLP 2025 System-Aware Unlearning Algorithms: Use Lesser, Forget Faster ICML 2025