Publications

Authors with * contributed equally.

2025

• Learning an Optimal Assortment Policy under Observational Data
  Yuxuan Han, Han Zhong, Miao Lu, Jose Blanchet, Zhengyuan Zhou
  arXiv preprint, Feb, 2025 [PDF]
  

• Can Neural Networks Achieve Optimal Computational-Statistical Tradeoff? An Analysis on Single-Index Model
  Siyu Chen*, Beining Wu*, Miao Lu, Zhuoran Yang, Tianhao Wang
  NeurIPS Workshop on Mathematics of Modern Machine Learning (M3L) 2024 Oral
  International Conference on Learning Representations (ICLR) 2025 Oral [PDF] [Slides]
  

Before 2025

• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
  Zhihan Liu*, Miao Lu*, Shenao Zhang, Boyi Liu, Hongyi Guo, Yingxiang Yang, Jose Blanchet, Zhaoran Wang
  ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET) 2024
  Neural Information Processing Systems (NeurIPS) 2024 [PDF] [Code] [Poster]
  

• Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm
  Miao Lu*, Han Zhong*, Tong Zhang, Jose Blanchet
  ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET) 2024
  Neural Information Processing Systems (NeurIPS) 2024 [PDF] [Slides]
  

• Benign Oscillation of Stochastic Gradient Descent with Large Learning Rates
  Miao Lu*, Beining Wu*, Xiaodong Yang, Difan Zou
  NeurIPS Workshop on Mathematics of Modern Machine Learning (M3L) 2023
  International Conference on Learning Representations (ICLR) 2024 [PDF] [Poster]
  

• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration
  Zhihan Liu*, Miao Lu*, Wei Xiong*, Han Zhong, Hao Hu, Shenao Zhang, Sirui Zheng, Zhuoran Yang, Zhaoran Wang
  Neural Information Processing Systems (NeurIPS) 2023 Spotlight [PDF] [Code] [Slides]
  

• Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage
  Jose Blanchet, Miao Lu, Tong Zhang, Han Zhong (alphabetical)
  Neural Information Processing Systems (NeurIPS) 2023 (short version)
  arXiv preprint, Aug, 2023 (long version) [PDF] [Slides]
  

• Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
  Miao Lu, Yifei Min, Zhaoran Wang, Zhuoran Yang
  International Conference on Learning Representations (ICLR) 2023 [PDF] [Slides]
  

• Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy
  Zhihan Liu*, Miao Lu*, Zhaoran Wang, Michael I. Jordan, Zhuoran Yang
  International Conference on Machine Learning (ICML) 2022 [PDF] [Code] [Slides]
  

• Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, and No Retraining
  Miao Lu*, Xiaolong Luo*, Tianlong Chen, Wuyang Chen, Dong Liu, Zhangyang Wang
  International Conference on Learning Representations (ICLR) 2022 Spotlight [PDF] [Code] [Slides]
  

• Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization
  Yufei Kuang, Miao Lu, Jie Wang, Qi Zhou, Bin Li, Houqiang Li
  Association for the Advancement of Artificial Intelligence (AAAI) 2022 [PDF] [Code] [Slides]