Learning Theory

Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible? AISTATS 2025 Is Transductive Learning Equivalent to PAC Learning? ALT 2025 Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition ICLR 2025 L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning ICML 2025 Language Models can Categorize System Inputs for Performance Analysis NAACL 2025 Language models can learn implicit multi-hop reasoning, but only if they have lots of training data EMNLP 2025 Language Models Encode Numbers Using Digit Representations in Base 10 NAACL 2025 Language Models Grow Less Humanlike beyond Phase Transition ACL 2025 Language Models Learn to Mislead Humans via RLHF ICLR 2025 Language Models Need Inductive Biases to Count Inductively ICLR 2025 Language Models Resist Alignment: Evidence From Data Compression ACL 2025 Language models scale reliably with over-training and on downstream tasks ICLR 2025 Large Language and Reasoning Models are Shallow Disjunctive Reasoners ACL 2025 Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements EMNLP 2025 Lasso Bandit with Compatibility Condition on Optimal Arm ICLR 2025 LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation ICML 2025 LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits AISTATS 2025 Learnability of Parameter-Bounded Bayes Nets AAAI 2025 Learning Accurate and Interpretable Decision Trees (Extended Abstract) IJCAI 2025 Learning Algorithms for Multiple Instance Regression UAI 2025 Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent AISTATS 2025 Learning Classifiers That Induce Markets ICML 2025 Learning Complexity of Gradient Descent and Conjugate Gradient Algorithms AAAI 2025 Learning Compositional Functions with Transformers from Easy-to-Hard Data COLT 2025 Learning Constant-Depth Circuits in Malicious Noise Models COLT 2025