Wei Jiang (姜伟)   Professor School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China Google Scholar Email: jiangw@lamda.nju.edu.cn;   12025220@njust.edu.cn [Chinese version]

Research Interests

      Machine Learning, Stochastic Optimization, LLM Optimization.

Working Experiences

• 2025.10 - now, Nanjing University of Science and Technology.

  • Professor, School of Computer Science and Engineering.

Education Experiences

• 2020.09 - 2025.06, Ph.D., Computer Science and Technology, Nanjing University.

  • Supervisor: Professor Lijun Zhang (LAMDA Group).
  • 2023.10 - 2024.05, Visiting Student, National University of Singapore.

• 2016.09 - 2020.06, B.E., Computer Science and Technology (Honors Science Program), Xi'an Jiaotong University.

  • 2019.01 - 2019.06, Exchange Student, University of California, Berkeley. [certificate][transcript]
  • 2018.07 - 2018.08, Exchange Student, University of Manchester. [certificate]

Selected First-author Papers (Publications by Year)

1. Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
   W. Jiang, M. Xu, W. Yang, Y. Wang, Z. Li, and L. Zhang
   In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), to appear, 2026.
   
   
2. Optimizing Unnormalized Statistical Models through Compositional Optimization [PDF]
   W. Jiang, J. Qin, L. Wu, C. Chen, T. Yang, and L. Zhang
   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 48(2): 1949 - 1960, 2026.
   
   
3. Revisiting Stochastic Multi-Level Compositional Optimization [PDF]
   W. Jiang, S. Yang, Y. Wang, T. Yang, and L. Zhang
   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 47(7): 5613 - 5624, 2025.
   
   
4. Normalized Adaptive Variance Reduction Method [PDF]
   W. Jiang, S. Yang, Y. Wang, and L. Zhang
   Journal of Software, 36(11): 4893 - 4905, 2025.
   
   
5. Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions [PDF]
   W. Jiang, S. Yang, Y. Wang, and L. Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 22047 - 22080, 2024.
   
   
6. Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction [PDF]
   W. Jiang, S. Yang, W. Yang, and L. Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 33891 - 33932, 2024.
   
   
7. Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization [PDF]
   W. Jiang, S. Yang, W. Yang, Y. Wang, Y. Wan, and L. Zhang
   In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 21962 - 21987, 2024.
   
   
8. Learning Unnormalized Statistical Models via Compositional Optimization [PDF]
   W. Jiang, J. Qin, L. Wu, C. Chen, T. Yang, L. Zhang
   In Proceedings of the 40th International Conference on Machine Learning (ICML 2023), pages 15105 - 15124, 2023.
   
   
9. Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [PDF, Supplementary]
   W. Jiang, G. Li, Y. Wang, L. Zhang, and T. Yang
   In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pages 32499 - 32511, 2022.
   
   
10. Optimal Algorithms for Stochastic Multi-Level Compositional Optimization [PDF]
    W. Jiang, B. Wang, Y. Wang, L. Zhang, and T. Yang
    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022), pages 10195 - 10216, 2022.
    
    

Honors and Awards

• Excellent Graduate of Nanjing University, 2025
• National Scholarship, 2024
• Excellent Student of Nanjing University, 2024
• NeurIPS Top Reviewer, 2024
• National Scholarship, 2023
• Excellent Student of Nanjing University, 2023
• LAMDA Elite Award, 2023
• Tencent Scholarship, 2022
• Excellent Student of Nanjing University, 2022
• Industrial Bank Scholarship, 2021
• Excellent Student of Nanjing University, 2021
• Grand Champion of DeeCamp Artificial Intelligence Camp, 2020 (￥100,000)
• Excellent Graduate of Xi'an jiaotong University, 2020

Foundation

Distributed Optimization of Compositional Loss Functions. Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX24_0231) 2024.05-2025.05

Academic Service

• Area Chair for Conference: NeurIPS.
• Reviewer for Conference: ICML, NeurIPS, ICLR, AAAI, AISTATS, etc.
• Reviewer for Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE Transactions on Information Forensics and Security; IEEE Transactions on Evolutionary Computation; Scientific Reports; Machine Learning; Applied Numerical Mathematics; Information Sciences; Neurocomputing; Transactions on Machine Learning Research.