Learning Theory

Active Learning of General Halfspaces: Label Queries vs Membership Queries NeurIPS 2024 Active learning of neural population dynamics using two-photon holographic optogenetics NeurIPS 2024 Active Learning with Simple Questions COLT 2024 A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models ACL 2024 Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve? EMNLP 2024 Adaptive Accompaniment with ReaLchords ICML 2024 Adaptive Group Personalization for Federated Mutual Transfer Learning ICML 2024 Adaptive Regret for Bandits Made Possible: Two Queries Suffice ICLR 2024 Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization JMLR 2024 A distributional simplicity bias in the learning dynamics of transformers NeurIPS 2024 A Doubly Robust Approach to Sparse Reinforcement Learning AISTATS 2024 Adversarially Robust Hypothesis Transfer Learning ICML 2024 Adversarial Online Learning with Temporal Feedback Graphs COLT 2024 Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies ICML 2024 A Dynamical Model of Neural Scaling Laws ICML 2024 A faster and simpler algorithm for learning shallow networks COLT 2024 A General Framework for Sequential Decision-Making under Adaptivity Constraints ICML 2024 A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts ICML 2024 A Geometric Explanation of the Likelihood OOD Detection Paradox ICML 2024 Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms ICML 2024 Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms ICML 2024 Agnostic Membership Query Learning with Nontrivial Savings: New Results and Techniques ALT 2024 Agnostic Sample Compression Schemes for Regression ICML 2024 Algorithmic progress in language models NeurIPS 2024 Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses ICML 2024