Learning Theory

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features ICML 2024 Stochastic Q-learning for Large Discrete Action Spaces ICML 2024 Structural perspective on constraint-based learning of Markov networks AISTATS 2024 Studying the Interplay between Information Loss and Operation Loss in Representations for Classification JMLR 2024 Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning NeurIPS 2024 Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs ICLR 2024 Superconstant Inapproximability of Decision Tree Learning COLT 2024 SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories EMNLP 2024 Supervised Matrix Factorization: Local Landscape Analysis and Applications ICML 2024 SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS ICLR 2024 Symmetric Single Index Learning ICLR 2024 Symmetry Induces Structure and Constraint of Learning ICML 2024 SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists EMNLP 2024 Systematic Evaluation of Long-Context LLMs on Financial Concepts EMNLP 2024 TabLog: Test-Time Adaptation for Tabular Data Using Logic Rules ICML 2024 Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation ICML 2024 Targeted Sequential Indirect Experiment Design NeurIPS 2024 Targeted Syntactic Evaluation on the Chomsky Hierarchy COLING 2024 Target Speaker Extraction with Curriculum Learning Interspeech 2024 Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning ICML 2024 Task Contamination: Language Models May Not Be Few-Shot Anymore AAAI 2024 Testable Learning of General Halfspaces with Adversarial Label Noise COLT 2024 Testable Learning with Distribution Shift COLT 2024 Testing exchangeability by pairwise betting AISTATS 2024 Testing Semantic Importance via Betting NeurIPS 2024