Rujun Jiang (江如俊)

Associate Professor
School of Data Science
Fudan University
No. 220 Handan Road, Shanghai 200433

Office: N202, Zibin Building
Email: rjjiang@fudan.edu.cn

Background

Rujun Jiang is currently an associate professor at School of Data Science, Fudan University. He received his Bachelor degree in Mathematics in 2012 from University of Science and Technology of China. He then obtained his PhD degree in 2016 in The Chinese University of Hong Kong under the supervision of Professor Duan Li. Before joining Fudan in 2017, He spent one year in CUHK as a postdoctoral fellow. He has received an ICML Outstanding Paper Award (2022). .

Postdoc and graduate student positions available

Research Interest

Optimization methods and theory and their applications in operations research, machine learning and signal processing
Current focus

Preprints

  1. Zehao Zhang, Rujun Jiang. Accelerated Gradient Descent by Concatenation of Stepsize Schedules arXiv preprint arXiv:2410.12395
  2. Yuze Ge, Rujun Jiang. SOREL: A Stochastic Algorithm for Spectral Risks Minimization. arXiv preprint arXiv:2407.14618, 2024
  3. Chenyu Zhang, Rujun Jiang. Riemannian Adaptive Regularized Newton Methods with Hölder Continuous Hessians. arXiv preprint arXiv:2309.04052, 2023
  4. Peng Wang, Rujun Jiang, Qingyuan Kong, Laura Balzano. Difference-of-Convex Reformulation for Chance Constrained Programs. arXiv preprint arXiv:2301.00423, 2023

Selected Journal Articles

  1. Chenyu Zhang, Rufeng Xiao, Wen Huang, Rujun Jiang. Riemannian Trust Region Methods for SC1 Minimization. Journal of Scientific Computing, 101.2, 2024: 32. arXiv preprint arXiv:2307.00490, 2023
  2. Xiangyu Cui, Rujun Jiang, Yun Shi, Rufeng Xiao, Yifan Yan. Decision Making under Cumulative Prospect Theory: An Alternating Direction Method of Multipliers. INFORMS Journal on Computing, 2024. doi.org/10.1287/ijoc.2023.0243
  3. Alex L. Wang, Rujun Jiang. New notions of simultaneous diagonalizability of quadratic forms with applications to QCQPs. Mathematical Programming, 2024. code doi.org/10.1007/s10107-024-02120-0
  4. Wutao Si, P.-A. Absil, Wen Huang, Rujun Jiang, Simon Vary. A Riemannian Proximal Newton Method. SIAM Journal on Optimization 34.1 (2024), 654-681.
  5. Rujun Jiang and Duan Li. Exactness Conditions for Semidefinite Programming Relaxations of Generalization of the Extended Trust Region Subproblem. Mathematics of Operations Research. 48.3 (2023): 1235-1253. doi/abs/10.1287/moor.2022.1305
  6. Rujun Jiang, Zhizhuo Zhou, Zirui Zhou. Cubic Regularization Methods with Second-Order Complexity Guarantee Based on a New Subproblem Reformulation. Journal of the Operations Research Society of China. 10 (2022): 471–506. https://doi.org/10.1007/s40305-022-00398-5
  7. Rujun Jiang, Xudong Li. H\"olderian error bounds and Kurdyka-{\L}ojasiewicz inequality for the trust region subproblem. Mathematics of Operations Research. 47.4 (2022): 3025-3050. https://doi.org/10.1287/moor.2021.1243 (There is a typo in the first column in Table 1 in the published version, where \perp should be \not\perp.)
  8. Rujun Jiang, Man-Chung Yue, Zhishuo Zhou. An accelerated first-order method with complexity analysis for solving cubic regularization subproblems. Computational Optimization and Applications. 79.2 (2021): 471-506. https://doi.org/10.1007/s10589-021-00274-7
  9. Hezhi Luo, Xiaodong Ding, Jiming Peng, Rujun Jiang, Duan Li. Complexity Results and Effective Algorithms for Worst-case Linear Optimization under Uncertainties. INFORMS Journal on Computing. 33.1 (2020):180-197. https://doi.org/10.1287/ijoc.2019.0941 appendix data and code
  10. Rujun Jiang, Duan Li. A Linear-Time Algorithm for Generalized Trust Region Subproblems. SIAM Journal on Optimization. 30.1 (2020): 915-932.
  11. Rujun Jiang, Duan Li. Second order cone constrained convex relaxations for nonconvex quadratically constrained quadratic programming. Journal of Global Optimization. 75.2 (2019): 461-494. https://doi.org/10.1007/s10898-019-00793-y
  12. Rujun Jiang, Duan Li. Novel reformulations and efficient algorithms for the generalized trust region subproblem. SIAM Journal on Optimization. 29.2 (2019): 1603-1633.
  13. Baiyi Wu, Duan Li and Rujun Jiang. Quadratic Convex Reformulation for Quadratic Programming with Linear On-Off Constraints. European Journal of Operational Research. 274.3 (2019): 824-836.
  14. Xueting Cui, Xiaoling Sun, Shushang Zhu, Rujun Jiang, Duan Li. Portfolio Optimization with Nonparametric Value at Risk: A Block Coordinate Descent Method. INFORMS Journal on Computing. 30.3 (2018): 454-471. appendix
  15. Rujun Jiang, Duan Li, Baiyi Wu. SOCP reformulation for the generalized trust region subproblem via a canonical form of two symmetric matrices. Mathematical Programming. 169.2 (2018): 531-563.
  16. Rujun Jiang, Duan Li. Simultaneous diagonalization of matrices and its applications in quadratically constrained quadratic programming. SIAM Journal on Optimization. 26.3 (2016): 1649-1668.

Selected Conference Articles

  1. Pengyu Chen, Xu Shi, Rujun Jiang, Jiulin Wang. Penalty-based Methods for Simple Bilevel Optimization under H\"{o}lderian Error Bounds. To appear in Advances in Neural Information Processing Systems 37: Proceedings of the 2024 Conference (NeurIPS 2024). arXiv preprint arXiv:2402.02155, 2024
  2. Jiulin Wang, Xu Shi, Rujun Jiang. Near-Optimal Convex Simple Bilevel Optimization with a Bisection Method. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024), 2024.
  3. He Chen, Haochen Xu, Rujun Jiang, Anthony Man-Cho So. Lower-Level Duality Based Reformulation and Majorization Minimization Algorithm for Hyperparameter Optimization. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024), 2024.
  4. Rufeng Xiao, Yuze Ge, Rujun Jiang, Yifan Yan. Unified Framework for Rank-based Loss Minimization. Advances in Neural Information Processing Systems 36: Proceedings of the 2023 Conference (NeurIPS 2023).
  5. Jiali Wang, Wen Huang, Rujun Jiang, Xudong Li, Alex L. Wang. Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation. International Conference on Machine Learning (ICML), 2022. Outstanding Paper Award code
  6. Jiali Wang, He Chen, Rujun Jiang, Xudong Li, Zihao Li. Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss. International Conference on Machine Learning (ICML), 2021. code
  7. Rujun Jiang, Huikang Liu, Anthony Man-Cho So. LPA-SD: An Efficient First-Order Method for Single-Group Multicast Beamforming. Proceedings of the 19th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2018), 2018.
  8. Rujun Jiang, Duan Li. On Conic Relaxations of Generalization of the Extended Trust Region Subproblem. In World Congress on Global Optimization, pp. 145-154. Springer, Cham, 2019.
  9. Rujun Jiang, Duan Li. Semidefinite Programming Based Convex Relaxation for Nonconvex Quadratically Constrained Quadratic Programming. In World Congress on Global Optimization, pp. 213-220. Springer, Cham, 2019.

Teaching

DATA620008: Optimization Theory and Methods

DATA130026: Numerical Optimization

Professional Service

  • Area Chair for NeurIPS 2024