Honghao Wei

About Me

I am a final year Ph.D. student in the Department of Electrical Engineering and Computer Science at The University of Michigan, Ann Arbor. I am very fortunate to be advised by Prof. Lei Ying. My research interests lie in designing theoretical and practical machine learning algorithms with strong theoretical guarantees.

Research

My major research interests include:

  • Online Learning and Decision-making
  • Reinforcement Learning and Constrained Reinforcement Learning
  • Stochastic Modeling, Analysis and Optimization
  • Reinforcement Learning with Applications in Communication, Ride-hailing Networks, and Social Networks

Preprints

Xin Liu, Honghao Wei, Lei Ying, ‘‘Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems.’’

Selected Publications

Hengquan Guo, Xin Liu, Honghao Wei, Lei Ying, “Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond” in Proc. NeurIPS-22 (acceptance rate: 25.6%).

Honghao Wei, Xin Liu, Lei Ying, “Triple-Q: A Model-Free Algorithm for Constrained Reinforcement Learning with Sublinear Regret and Zero Constraint Violation” in Proc. AISTATS-22 (acceptance rate: 29%) .

Honghao Wei, Xin Liu, Lei Ying, “A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes” in Proc. AAAI-22 (acceptance rate: 15.0%).

Qining Zhang, Honghao Wei, Weina Wang, Lei Ying, “On Low-Complexity Quickest Intervention of Mutated Diffusion Processes Through Local Approximation” in Proc. MobiHoc-22 (acceptance rate: 20%).

Honghao Wei, Lei Ying “Fork: A forward-looking actor for model-free reinforcement learning” in Proc. CDC-21.

Honghao Wei, Xiaohan Kang, Weina Wang, Lei Ying, “QuickStop: A Markov Optimal Stopping Approach for Quickest Misinformation Detection” in Proc. Sigmetrics-19 (acceptance rate: 16%).

Teaching Experience

Graduate Student Instructor, EECS 598 Reinforcement Learning, Winter 2022.

Graduate Student Instructor, EECS 501 Probability and Random Processes, Fall 2021.

Graduate Student Instructor, EECS 598 Reinforcement Learning, Winter 2020.

Graduate Student Instructor, EECS 598 Reinforcement Learning, Fall 2020.

Lab Teaching Assistant, EEE 334 Circuits II, Spring 2018.

Lab Teaching Assistant, EEE 455 Communication Systems, Fall 2017.

Professional Service

Conference Reviewer: NeurIPS 22 / ICML 22 / ICML 22 / AAAI 22, 23 / AISTATS 22,23 / OnlineMarketplaces 2022 / ISIT 21/ CDC 21/ RL4ITS 21 /

Journal Reviewer: IEEE Trans. Inf. Theory / Netw / Control. Netw. Syst.