About me
I am a postdoctoral researcher at University of Illinois at Urbana-Champaign, where I am fortunate to be advised by Prof. R. Srikant (IEEE Fellow). I am broadly interested in the area of machine learning, including online learning (in particular, multi-armed bandit), reinforcement learning and representation learning.
Prior to that, I received my Ph.D. from Institute for Interdisciplinary Information Sciences (headed by Prof. Andrew Chi-Chih Yao), Tsinghua University in June, 2023. During my Ph.D. study, I was fortunate to be advised by Prof. Longbo Huang and also worked closely with Dr. Wei Chen (IEEE Fellow, Director of MSR Asia Theory Center).
I visited Cornell University in person during September-December, 2022, where I was lucky to be supervised by Prof. Wen Sun. I was also a research intern at MSR Asia during January-May, 2020, supervised by Dr. Wei Chen.
My committee members are Wei Chen (MSRA, IEEE Fellow), Wei Chen (CAS), Jian Li (Tsinghua) and Jun Zhu (Tsinghua, IEEE Fellow).
Email: duyh18@mails.tsinghua.edu.cn yihandu@illinois.edu
Download my CV here.
- Online Learning (in particular, Multi-armed Bandit)
- Reinforcement Learning
- Representation Learning
-
Postdoctoral Researcher, August 2023 - Present
University of Illinois at Urbana-Champaign
-
Ph.D. in Computer Science, September 2018 - June 2023
Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University
-
Visiting Ph.D. Student (in-person), September - December 2022
Cornell University
-
B.E. in Computer Science, September 2014 - June 2018
Xiamen University
Publications
Yihan Du, Longbo Huang, Wen Sun, “Multi-task Representation Learning for Pure Exploration in Linear Bandits,” International Conference on Machine Learning (ICML), 2023. [pdf] [arXiv]
Yihan Du, Siwei Wang, Longbo Huang, “Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path,” International Conference on Learning Representations (ICLR), 2023. [pdf] [arXiv]
Yihan Du, Wei Chen, Yuko Kuroki, Longbo Huang, “Collaborative Pure Exploration in Kernel Bandit,” International Conference on Learning Representations (ICLR), 2023. [pdf] [arXiv]
Yihan Du, Wei Chen, “Branching Reinforcement Learning,” International Conference on Machine Learning (ICML), 2022. [pdf] [arXiv]
Yihan Du, Siwei Wang, Zhixuan Fang, Longbo Huang, “Continuous Mean-Covariance Bandits,” Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2021. [pdf] [arXiv]
Yihan Du, Yuko Kuroki, Wei Chen, “Combinatorial Pure Exploration with Bottleneck Reward Function,” Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2021. [pdf] [arXiv]
Yihan Du, Siwei Wang, Longbo Huang, “A One-Size-Fits-All Solution to Conservative Bandit Problems,” Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021. [pdf] [arXiv]
Yihan Du*, Yuko Kuroki*, Wei Chen, “Combinatorial Pure Exploration with Full-Bandit or Partial Linear Feedback,” Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021 (* denotes equal contribution). [pdf] [arXiv]
[*alphabetical order] Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao, “Combinatorial Pure Exploration for Dueling Bandit,” International Conference on Machine Learning (ICML), 2020. [pdf] [arXiv]
Yihan Du, Siwei Wang, Longbo Huang, “Dueling Bandits: From Two-dueling to Multi-dueling,” Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020. [pdf] [arXiv]
Yihan Du, Yan Yan, Si Chen, Yang Hua, “Object-adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation,” Neurocomputing, 2019.
Yihan Du, Yan Yan, Si Chen, Yang Hua, Hanzi Wang, “Object-adaptive LSTM Network for Visual Tracking,” International Conference on Pattern Recognition (ICPR), 2018.
Selected Awards
Beijing Outstanding Graduate, by Beijing Municipal Education Commission (the only recipient among CS graduates at IIIS, Tsinghua University in 2023), June 2023
Tsinghua Outstanding Doctoral Thesis, by Tsinghua University (the only recipient among CS graduates at IIIS, Tsinghua University in 2023), June 2023
China National Scholarship, by Ministry of Education of China (the only recipient among CS students at IIIS, Tsinghua University in 2022), October 2022
Toyota Scholarship, by Toyota and Tsinghua University, October 2021
Huawei Academic Excellence Scholarship, by Huawei and Tsinghua University, October 2020
Wuqing Talent Scholarship, by Tianjin Wuqing District Government and Tsinghua University, October 2020
Outstanding Graduate, by Xiamen University, June 2018
Invited Talks
“Risk-aware Online Decision Making,” TrustML Young Scientist Seminar, RIKEN AIP, May 2023
“Risk-aware Online Decision Making,” MLOPT Idea Seminar, University of Wisconsin-Madison, April 2023
“Optimal Experimental Design in Linear Bandit,” Bandit Algorithm Seminar, Yau Mathematical Sciences Center (YMSC), Tsinghua University, November 2022
“Combinatorial Pure Exploration for Dueling Bandit,” China Computer Federation (CCF) Doctoral Forum in Theoretical Computer Science, June 2021
(Only 18 Ph.D. students in theoretical computer science are invited nationwide)
Academic Service & Activities
Program Committee Member/Reviewer
Conference: ICML 2021-2023, NeurIPS 2021-2023, ICLR 2022-2023
Journal: Transactions on Machine Learning Research (TMLR), Transactions on Networking (ToN)
Teaching Assistant
Stochastic Network Optimization, graduate course (IIIS, Tsinghua University), Spring 2021
Introduction to Computer Science, undergraduate course (Yao Class, Tsinghua University), Fall 2019
Social Activity
President of Graduate Union at IIIS, Tsinghua University, June 2020 - June 2021
Contact
- yihandu@illinois.edu
- Coordinated Science Laboratory, 1308 W. Main Street, Urbana, Illinois 61801