л İ
sample

Liwei Wang

Professor,

Department of Machine Intelligence,

School of Electronics Engineering and Computer Sciences,

Peking University

Email: wanglw at pku.edu.cn; wanglw at cis.pku.edu.cn


My research interest is machine learning. I study the foundations of machine learning, providing insights for the strength and weakness of learning algorithms and thus help to guide the development of new algorithms. Recently I am devoted to solving fundamental scientific and mathematical problems via the approach of machine learning. On the application side, I develop algorithms and systems for medical diagnosis based on machine learning methods.



NEWS



  • sample Our paper: "Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness "Bohang Zhang, Jingchu Gai, Yiheng Du, Qiwei Ye, Di He, Liwei Wang , has received ICLR 2024 outstanding paper award honorable mention! !
  • Our paper: "A Computational Framework for Neural Network-based Variational Monte Carlo with Forward Laplacian "Ruichen Li, Haotian Ye, Du Jiang, Xuelan Wen, Chuwei Wang, Zhe Li, Xiang Li, Di He, Ji Chen, Weiluo Ren, Liwei Wang , has been accepted by Nature Machine Intelligence !
  • Our paper: "Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective "Guhao Feng, Bohang Zhang, Yuntian Gu, Haotian Ye, Di He, Liwei Wang has been accepted by NeurIPS 2023 (Oral) !
  • Our paper: "A Reduction-based Framework for Sequential Decision Making with Delayed Feedback "Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, Liwei Wang , Simon S. Du has been accepted by NeurIPS 2023 !
  • Our paper: "Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds "Jiayi Huang, Han Zhong,Liwei Wang , Lin F. Yang has been accepted by NeurIPS 2023 !
  • Our paper: "PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds "Hao Yang, Haiyang Wang, Di Dai, Liwei Wang , has been accepted by NeurIPS 2023 !
  • Our paper: "Offline Meta Reinforcement Learning with In-Distribution Online Adaptation "Jianhao Wang, Jin Zhang, Haozhe Jiang, Junyu Zhang, Liwei Wang , Chongjie Zhang has been accepted by ICML 2023 !
  • Our paper: "A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests " Bohang Zhang, Guhao Feng, Yiheng Du, Di He, Liwei Wang , has been accepted by ICML 2023 !
  • Our paper: "On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness " Haotian Ye, Xiaoyu Chen, Liwei Wang , Simon Du, has been accepted by ICML 2023 !
  • sample Our paper: Rethinking the Expressive Power of GNNs via Graph Biconnectivity , Bohang Zhang, Shengjie Luo, Liwei Wang , Di He, received the ICLR 2023 Outstanding Paper Award!
  • Our paper: "Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game " Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, Liwei Wang , Tong Zhang, has been accepted by ICLR 2023 !

RECENT PUBLICATIONS (Full Paper List)


Full publication list here


Students



Current Students

PhD Students Master Students Undergraduate Students
  • Xiaoyu Chen
  • Jiachen Hu
  • Ruichen Li
  • Haiyang Wang
  • Yunchang Yang
  • Bohang Zhang
  • Han Zhong
  • Haojun Yu
  • Shengjie Luo
  • Hao Tang
  • Ruiheng Chang
  • Dengbo Chen
  • Shishuang Zhao
  • Ziwei Zhao
  • Chen Shi
  • Hao Yang
  • Jie Wu
  • Mingyu Yang
  • Meng Lei
  • Jiayi Huang
  • Haotian Ye
  • Du Jiang
  • Jikai Jin
  • Binghui Li
  • Chuwei Wang
  • Quanlin Wu


Postdoctoral

  • Dong Wang
Alumni


Courses



Current Courses

  • Machine Learning
  • Information Theory

Previous Courses

  • Statistical Learning