Supervisor

Professor Zhi-Hua Zhou.

Biography

• Currently I am a second-year PhD student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group (LAMDA Publications), led by professor Zhi-Hua Zhou.
• I got my B.Sc. degree in Department of Computer Science and Technology in Nanjing University in June 2020.

Research Interest

My research interests include Machine Learning and Data Mining. Most recently, I am interested in Online Learning and Games.

Invited Talks

• Universal Online Learning with Gradient Variation
  2025.04.18, TrustML Young Scientist Seminar at RIKEN AIP, Online.

Publication

1. Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality. [PDF, bibtex]
   Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
   In: Advances in Neural Information Processing Systems 38 (NeurIPS 2025), San Diego, USA, 2025. Page: to appear.
   
   
2. Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness. (Spotlight) [PDF, bibtex]
   Yuheng Zhao, Yu-Hu Yan, Kfir Yehuda Levy, and Peng Zhao.
   In: Advances in Neural Information Processing Systems 38 (NeurIPS 2025), San Diego, USA, 2025. Page: to appear.
   
   
3. A Simple and Optimal Approach for Universal Online Learning with Gradient Variations. [PDF, bibtex]
   Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
   In: Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, Canada, 2024. Page: 11132-11163.
   
   
4. Handling Heterogeneous Curvatures in Bandit LQR Control. (Spotlight) [PDF, bibtex]
   Yu-Hu Yan, Jing Wang, and Peng Zhao.
   In: Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024. Page: 55839-55858.
   
   
5. Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach. (Spotlight) [PDF, arXiv, bibtex]
   Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
   In: Advances in Neural Information Processing Systems 36 (NeurIPS 2023), Louisiana, USA, 2023. Page: 37682--37715.
   
   
6. Online Non-stochastic Control with Partial Feedback. [PDF, bibtex]
   Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
   Journal of Machine Learning Research (JMLR), 24(273):1−50, 2023
   
   
7. Non-stationary Online Learning with Memory and Non-stochastic Control. [PDF, arXiv, bibtex]
   Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang, and Zhi-Hua Zhou.
   Journal of Machine Learning Research (JMLR), 24(206):1−70, 2023
   
   
8. Fast Rates in Time-Varying Strongly Monotone Games. [PDF, bibtex]
   Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
   In: Proceedings of the 40th International Conference on Machine Learning (ICML 2023), Hawaii, USA, 2023. Page: 39138-39164.
   
   
9. Towards Enabling Learnware to Handle Unseen Jobs. [PDF, code, bibtex]
   Yu-Jie Zhang, Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
   s In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), online, 2021. Page: 10964-10972.
   
   
10. Storage Fit Learning with Feature Evolvable Streams. [PDF, code, bibtex]
    Bo-Jian Hou, Yu-Hu Yan, Peng Zhao, and Zhi-Hua Zhou.
    In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), online, 2021. Page: 7729-7736.
    
    

Academic Service

• Reviewer of conferences: ICML (2022, 2023, 2024), NeurIPS (2022, 2023, 2024), ICLR (2024), AAAI (2024), UAI (2022, 2023, 2024), AISTATS (2023, 2024)
• Reviewer of journals: TPAMI, MLJ, TMLR

Awards & Honors

• 南京大学优秀研究生标兵. 2024
• 国家奖学金. 2024
• 华为奖学金. 2023
• 南京大学优秀研究生. 2023
• 江苏银行奖学金. 2021
• 南京大学学业奖学金一等奖. 2021
• 南京大学优秀研究生. 2021
• 南京大学优秀毕业生. 2020
• 江苏金融租赁奖学金. 2019
• 国家奖学金. 2018
• 人民奖学金二等奖. 2017
• 南京大学优秀学生. 2017

Correspondence

Mail:
National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(In Chinese:) 南京市栖霞区仙林大道163号，南京大学仙林校区603信箱，软件新技术国家重点实验室，210023。

Last modified: 2023-04-25