Bo Xue (薛波)

Ph.D. Student City University of Hong Kong Hong Kong, China Supervisor: Prof. Qingfu Zhang E-mail: boxue4-c@my.cityu.edu.hk

About Me

Hello! I am Bo Xue (薛波). I have been working as a Research Assistant with Prof. Shuang Qiu since May 2026.

I completed my Ph.D. defense in March 2026 in the Department of Computer Science at the City University of Hong Kong, where I was very fortunate to be advised by Prof. Qingfu Zhang.

I got my M.S. degree from Department of Computer Science and Technology in June 2021 from Nanjing University, where I was very fortunate to be advised by Prof. Lijun Zhang. I was also a member of LAMDA group, led by Prof. Zhi-Hua Zhou.

I got my B.S. degree from School of Mathematics in June 2018 from Nanjing University. In the same year, I was admitted to study for a M.S. degree in Nanjing University without entrance examination.

I am interested in bandits, stochastic optimization and multi-objective optimization.

Selected Papers (Full publications)

1. Safe Multi-Objective Linear Bandits with Hierarchical Preferences [PDF] [BIB]
   Bo Xue,Mengxia He, Yilu Liu, Ji Cheng, Zhe Zhao and Qingfu Zhang
   In Proceedings of the 35th International Joint Conference on Artificial Intelligence (IJCAI 2026), pages: to appear, 2026.

2. Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits [PDF] [BIB]
   Bo Xue, Yuanyu Wan, Zhichao Lu and Qingfu Zhang
   In Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI 2026, Oral), pages 27414 - 27422, 2026.

3. Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound [PDF] [BIB]
   Bo Xue, Ji Cheng, Fei Liu, Yimu Wang, Lijun Zhang and Qingfu Zhang
   Journal of Machine Learning Research (JMLR), 26(223): 1 - 56, 2025.

4. Multi-objective Linear Reinforcement Learning with Lexicographic Rewards [PDF] [BIB]
   Bo Xue, Dake Bu, Ji Cheng, Yuanyu Wan and Qingfu Zhang
   In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025), pages 70065 - 70085, 2025.

5. Problem-dependent Regret for Lexicographic Multi-Armed Bandits with Adversarial Corruptions [PDF] [BIB]
   Bo Xue, Xi Lin, Yuanyu Wan and Qingfu Zhang
   In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025), pages 6776 - 6784, 2025.

6. Multiple Trade-offs: An Improved Approach for Lexicographic Linear Bandits [PDF] [BIB]
   Bo Xue, Xi Lin, Xiaoyuan Zhang and Qingfu Zhang
   In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025, Oral), pages 21850 - 21858, 2025.

7. Multiobjective Lipschitz Bandits under Lexicographic Ordering [PDF] [BIB]
   Bo Xue, Ji Cheng, Fei Liu, Yimu Wang, and Qingfu Zhang
   In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), pages 16238 - 16246, 2024.

8. Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards [PDF] [BIB]
   Bo Xue, Yimu Wang, Yuanyu Wan, Jinfeng Yi, and Lijun Zhang
   In Advances in Neural Information Processing Systems 36 (NeurIPS 2023), pages 70880 - 70891, 2023.

9. Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs [PDF] [BIB]
   Bo Xue, Guanghui Wang, Yimu Wang, and Lijun Zhang
   In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020), pages 2936 - 2942, 2020.

Academic Service

Reviewer for Conferences: NeurIPS, ICML, ICLR, AAAI, IJCAI, AISTATS, WWW.

Reviewer for Journals: EAAI, AI.