Huang, Audrey

17 publications

COLT 2025 Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning Under Misspecification (extended Abstract) Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster

ICLR 2025 Correcting the Mythos of KL-Regularization: Direct Alignment Without Overoptimization via Chi-Squared Preference Optimization Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan J Foster

ICML 2025 Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan J Foster

NeurIPS 2025 Model Selection for Off-Policy Evaluation: New Algorithms and Experimental Protocol Pai Liu, LingfengZhao, Shivangi Agarwal, Jinghan Liu, Audrey Huang, Philip Amortila, Nan Jiang

ICLR 2025 Self-Improvement in Language Models: The Sharpening Mechanism Audrey Huang, Adam Block, Dylan J Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

NeurIPS 2024 Occupancy-Based Policy Gradient: Estimation, Convergence, and Optimality Audrey Huang, Nan Jiang

NeurIPSW 2024 Self-Improvement in Language Models: The Sharpening Mechanism Audrey Huang, Adam Block, Dylan J Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

AISTATS 2024 Timing as an Action: Learning When to Observe and Act Helen Zhou, Audrey Huang, Kamyar Azizzadenesheli, David Childers, Zachary Lipton

NeurIPSW 2023 Non-Adaptive Online Finetuning for Offline Reinforcement Learning Audrey Huang, Mohammad Ghavamzadeh, Nan Jiang, Marek Petrik

ICML 2023 Reinforcement Learning in Low-Rank MDPs with Density Features Audrey Huang, Jinglin Chen, Nan Jiang

AISTATS 2022 Off-Policy Risk Assessment for Markov Decision Processes Audrey Huang, Liu Leqi, Zachary Lipton, Kamyar Azizzadenesheli

NeurIPS 2022 Beyond the Return: Off-Policy Function Estimation Under User-Specified Error-Measuring Distributions Audrey Huang, Nan Jiang

ICMLW 2022 Beyond the Return: Off-Policy Function Estimation Under User-Specified Error-Measuring Distributions Audrey Huang, Nan Jiang

COLT 2022 Offline Reinforcement Learning with Realizability and Single-Policy Concentrability Wenhao Zhan, Baihe Huang, Audrey Huang, Nan Jiang, Jason Lee

ICML 2022 Supervised Learning with General Risk Functionals Liu Leqi, Audrey Huang, Zachary Lipton, Kamyar Azizzadenesheli

NeurIPS 2021 Off-Policy Risk Assessment in Contextual Bandits Audrey Huang, Liu Leqi, Zachary Lipton, Kamyar Azizzadenesheli

CoRL 2019 Graph-Structured Visual Imitation Maximilian Sieb, Zhou Xian, Audrey Huang, Oliver Kroemer, Katerina Fragkiadaki