吴 锦 辉 Jin-Hui Wu (J.-H. Wu) Master. candidate, LAMDA Group School of Artificial Intelligence Nanjing University, Nanjing 210023, China Supervisor: Prof. Yuan Jiang and Prof. Zhi-Hua Zhou Email: wujh@lamda.nju.edu.cn Laboratory: Computer Science Building, Xianlin Campus of Nanjing University

Biography

Currently I am a sixth-year graduate student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou. I got my B.Sc. degree in Kuang Yaming Honors School in June 2019 from Nanjing University. In the same year, I was admitted to pursue for a Ph.D. degree in Nanjing University without entrance examination.

Research Interests

My research interests include Machine Learning and Data Mining. Currently I am focusing on the subfields:

• Theories of neural networks, especially on theories of flexible transmitter networks and complex-valued neural networks.

Publications

* Equal Contribution.

• Universal Approximation and Approximation Advantages of Quaternion-valued Neural Networks [in Chinese]. [paper] [bib]
  Jin-Hui Wu, Yuan Jiang.
  Journal of Computer Research and Development, 2025, 62(5): 1205-1215.
  (Best Student Paper Award of the 10th China Conference on Data Mining (CCDM), 2024)


• The Role of Depth, Width, and Tree Size in Expressiveness of Deep Forest. [paper] [code] [bib]
  Shen-Huan Lyu*, Jin-Hui Wu*, Qin-Cheng Zheng, Baoliu Ye.
  In: Proceedings of the 27th European Conference on Artificial Intelligence (ECAI), 2024, 2042-2049.


• On the Intrinsic Structures of Spiking Neural Networks. [paper] [bib]
  Shao-Qun Zhang, Jia-Yi Chen, Jin-Hui Wu, Gao Zhang, Huan Xiong, Bin Gu, Zhi-Hua Zhou.
  Journal of Machine Learning Research (JMLR), 2024, 25(194): 1-74.


• Theoretical Exploration of Flexible Transmitter Model. [paper] [bib]
  Jin-Hui Wu, Shao-Qun Zhang, Yuan Jiang, Zhi-Hua Zhou.
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024, 35(3): 3674-3688.


• Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent. [paper] [poster] [code] [bib] [corrigenda]
  Jin-Hui Wu, Shao-Qun Zhang, Yuan Jiang, Zhi-Hua Zhou.
  In: Advances in Neural Information Processing Systems 36 (NeurIPS), 2023, 23714-23747.

Academic Service

Conference Reviewers:

• ACML: 2025
• AISTATS: 2025
• ECAI: 2023 (Early Bird Award)
• ICLR: 2024, 2025
• ICML: 2025
• NeurIPS: 2023, 2024, 2025
• PAKDD: 2023, 2024, 2025

Journal Reviewers:

• TNNLS

Teaching Assistant

• Introduction to Machine Learning. (with Prof. Zhi-Hua Zhou, Prof. De-Chuan Zhan, Dr. Han-Jia Ye; for undergraduate students; spring, 2020)
• Game Theory. (with Assoc. Prof. Wei Gao; for graduate and undergraduate students; spring, 2021)
• Introduction to Machine Learning Theory. (with Assoc. Prof. Wei Wang; for graduate students; spring, 2021)
• Introduction to Machine Learning Theory. (with Prof. Wei Wang; for graduate students; spring, 2023)
• Introduction to Machine Learning Theory. (with Prof. Wei Wang; for graduate students; spring, 2024)

Links

• PhD Seminar (LAMDA members only; organizer in autumn 2021)
• Theory Seminar (LAMDA members only; organizer in autumn 2023 and spring 2024)
• Template of Mid Term Tech Report (used in 2022 for PhD Students at NJUAI)

Correspondence

Email: wujh@lamda.nju.edu.cn
Office: Room 912, Computer Science Building, Xianlin Campus of Nanjing University
Address: State Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China