Research Interests

Reinforcement learning, online machine learning (e.g., multi-armed bandit problem)

Ph.D Thesis

1. Performance Guarantees for Online Learning: Cascading Bandits and Adversarial Corruptions
   (Louis Chen Hsiao Yun Best Dissertation Prize)
   Zixin Zhong
   Department of Mathematics, National University of Singapore, October 2021

Tutorials

1. Pure Exploration in Multi-Armed Bandits
   Vincent Y. F. Tan, Zixin Zhong
   International Joint Conference on Artificial Intelligence (IJCAI), Messe Wien, Vienna, Austria, July 23 - 29, 2022

*: Corresponding author， ∗: equal contribution.

Journal Papers

1. Optimal Clustering with Bandit Feedback
   Junwen Yang, Zixin Zhong, and Vincent Y. F. Tan
   Journal of Machine Learning Research (JMLR) , Vol. 25, No. 186, Pages 1 - 54, July 2024
2. Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Stochastic Bandits (featured certification) [code]
   Zixin Zhong, Wang Chi Cheung, and Vincent Y. F. Tan
   Transactions on Machine Learning Research (TMLR), Accepted in September 2023
3. Almost Optimal Variance-Constrained Best Arm Identification
   Yunlong Hou, Vincent Y. F. Tan, and Zixin Zhong*
   IEEE Transactions on Information Theory (IEEE TIT), 2023, doi: 10.1109/TIT.2022.3222231
4. Fast Beam Alignment via Pure Exploration in Multi-armed Bandits (Journal Version)
   Yi Wei, Zixin Zhong*, and Vincent Y. F. Tan
   IEEE Transactions on Wireless Communications (IEEE TWC), 2023, doi: 10.1109/TWC.2022.3217131
5. Thompson Sampling Algorithms for Cascading Bandits [code]
   Zixin Zhong, Wang Chi Cheung, and Vincent Y. F. Tan
   Journal of Machine Learning Research (JMLR) , Vol. 22, No. 218, Pages 1 - 66, September 2021

Conference Papers

1. Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
   Yunlong Hou, Vincent Y. F. Tan, and Zixin Zhong*
   Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 9-15 December 2024
2. Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
   Yunlong Hou, Vincent Y. F. Tan, and Zixin Zhong*
   International Conference on Machine Learning (ICML), Hawaii, US, 23-29 July 2023
3. Stochastic Gradient Succeeds for Bandits
   Jincheng Mei*∗, Zixin Zhong*∗, Bo Dai, Alekh Agarwal, Csaba Szepesvári, and Dale Schuurmans
   International Conference on Machine Learning (ICML), Hawaii, US, 23-29 July 2023
4. Fast Beam Alignment via Pure Exploration in Multi-armed Bandits
   Yi Wei, Zixin Zhong, and Vincent Y. F. Tan
   IEEE International Symposium on Information Theory (ISIT), Aalto, Finland, 26 June-1 July 2022
5. Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions [video, code]
   Zixin Zhong, Wang Chi Cheung, and Vincent Y. F. Tan
   International Conference on Machine Learning (ICML), Virtual, 18-24 July 2021
6. Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
   Zixin Zhong, Wang Chi Cheung, and Vincent Y. F. Tan
   International Conference on Machine Learning (ICML), Virtual, 13-18 July 2020
7. A Thompson Sampling Algorithm for Cascading Bandits (oral presentation)
   Wang Chi Cheung, Vincent Y. F. Tan, and Zixin Zhong
   International Conference on Artificial Intelligence and Statistics (AISTATS), Naha, Okinawa, Japan, 16-18 April 2019

Professional Activities

Conference Reviewer
2023-   European Workshop on Reinforcement Learning (EWRL)
2022-   International Conference on Machine Learning (ICML)
2022-   International Conference on Learning Representations (ICLR)
2021-   Neural Information Processing Systems (NeurIPS)
2021-   International Conference on Artificial Intelligence and Statistics (AISTATS)

Journal Reviewer
            IEEE Transactions on Information Theory (TIT)
            IEEE Transactions on Signal Processing (TSP)
            Transactions on Machine Learning Research (TMLR)

Academic Activities

1. Rising Stars Workshop in EECS, The University of Texas at Austin, 27-28 October 2022
2. INFORMS 2021 Annual Meeting, Virtual, 24-27 October 2021
   Oral presentation of the work appeared at ICML 2021
3. The 22nd Conference of the International Federation of Operational Research Societies (IFORS), Virtual, 23-27 August 2021
   Oral presentation of the work appeared at ICML 2021
4. The 3rd TBSI Workshop on Learning Theory (WOLT), TBSI, 5-7 July 2021
   Oral and poster presentation of the work appeared at ICML 2021
5. Analytics for X, iORA, NUS, 19-21 May 2021
   Oral presentation of the work appeared at ICML 2021