杨斯凡 Sifan Yang Master student, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Google Scholar

Supervisor

      Professor Lijun Zhang

Education Experiences

• 2023.09 - Now, Master, Computer Science and Technology, Nanjing University.

• 2019.09 - 2023.06, B.E., Artificial Intelligence , Nanjing University.

Research Interests

      My research interests include Machine Learning, Stochastic Optimization and Online Learning.

Journal

1. Revisiting Stochastic Multi-Level Compositional Optimization.
   W. Jiang, S. Yang, Y. Wang, T. Yang and L. Zhang
   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear, 2025.
   
   
2. Normalized Adaptive Variance Reduction Method.
   W. Jiang, S. Yang, Y. Wang, and L. Zhang
   Journal of Software, to appear, 2025.
   
   

Conference

1. Dimension-Free Adaptive Subgradient Methods with Frequent Directions
   S. Yang, Y. Wan, P. Li, Y. Wang, X. Zhang, Z. Wei and L. Zhang
   In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025), to appear, 2025.
   
   
2. Smoothed Online Convex Optimization with Delayed Feedback
   S. Yang, W. Yang, W. Jiang, Y. Wan, and L. Zhang
   In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025), to appear, 2025. .
   
   
3. Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting
   S. Yang, Y. Wan, and L. Zhang
   In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), pages 21992-22000, 2025.
   
   
4. Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions [arXiv]
   W. Jiang, S. Yang, Y. Wang, and L. Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), to appear, 2024.
   
   
5. Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction [arXiv]
   W. Jiang, S. Yang, W. Yang, and L. Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), to appear, 2024.
   
   
6. 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.
   
   

Honors and Awards

• Excellent Student of Nanjing University, 2024
• National Scholarship, 2023

Academic Service

• Reviewer for Conferences: NeurIPS 2025.

Teaching Assistant

• Computational Methods (With Prof. Lijun Zhang; For Undergraduate Student, Spring, 2025)

Correspondence

• Email: yangsf@lamda.nju.edu.cn

• Office: Room 516, Yifu Building, Xianlin Campus of Nanjing University