Qi Deng is currently an Associate Professor at the Antai College of Economics and Management, Shanghai Jiao Tong University (Room 815, Haoran Building). Prior to this, he worked at the School of Information Management and Engineering, Shanghai University of Finance and Economics, serving as Assistant Professor and then Associate Professor. He received his Ph.D. in Computer Science from the University of Florida and his B.S. from Shanghai Jiao Tong University. His research interests span mathematical programming and machine learning, with a focus on large-scale optimization algorithms and complexity analysis of algorithms. He has recently developed a strong interest in the intersection of AI and optimization. His recent work has been published in leading journals and conferences in operations research and machine learning, including Mathematical Programming, INFORMS Journal on Computing, Mathematics of Operations Research, Production and Operations Management, NeurIPS, and ICML. He currently serves as PI on grants from the National Natural Science Foundation of China and the Shanghai Municipal Natural Science Foundation, and is a co-PI on a Major Project of the National Natural Science Foundation of China.

Contact: qdeng24(at)sjtu.edu.cn (replace (at) with @)

Openings for Graduate Students

Research background includes Operations Research/Optimization and machine learning. Prospective students should commit to academic research, be self-disciplined, and possess a solid foundation in English writing, programming, and mathematics. Interested candidates are encouraged to get in touch.

International applicants with an exceptional research fit—such as publications in optimization or machine learning journals/conferences—are encouraged to contact me.

Research interests:  Algorithm design and complexity analysis for stochastic optimization, nonsmooth optimization, and constrained optimization; integrated learning and optimization, energy and power system

Recent related work

Boob, D., Deng, Q. and Khalafi, M., 2025. First-order methods for stochastic variational inequality problems with function constraints. Mathematics of Operations Research, accepted

Ren, Y., Xu, H. and Deng, Q., (2025) Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.

Han, Q., Li, C., Lin, Z., Chen, C., Deng, Q., Ge, D., Liu, H. and Ye, Y., 2025. A low-rank admm splitting approach for semidefinite programming. INFORMS Journal on Computing.

Boob, D., Deng, Q., & Lan, G. (2025). Level constrained first order methods for function constrained optimization. Mathematical Programming, 209(1), pp.1-61.

Lin, Z. & Deng, Q. (2024) Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints. NeurIPS 2024

Deng, Q., Feng, Q., Gao, W., Ge, D., Jiang, B., Jiang, Y., Liu, J., Liu, T., Xue, C., & Ye, Y. (2024). An Enhanced ADMM-based Interior Point Method for Linear and Conic Optimization. Informs Journal on Computing.

Lin, Z., Xue, C., Deng, Q., & Ye, Y. (2024). A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes. ICML 2024. 

Processes

Gao, W., & Deng, Q. (2024). Stochastic Weakly Convex Optimization Beyond Lipschitz Continuity. ICML 2024.

Tan, J., Xue, C., Zhang, C., Deng, Q., Ge, D., & Ye, Y. (2024). A Homogenization Approach for Gradient-Dominated Stochastic Optimization.UAI 2024. 

Xie, C., Li, C., Zhang, C., Deng, Q., Ge, D., & Ye, Y. (2024). Trust region methods for nonconvex stochastic optimization beyond Lipschitz smoothness. Proceedings of the AAAI Conference on Artificial Intelligence, 

Liu, J., Xie, C., Deng, Q., Ge, D., & Ye, Y. (2024). Sketched Newton Value Iteration for Large-Scale Markov Decision Processes. Proceedings of the AAAI Conference on Artificial Intelligence, 

Lin, Z., Xia, J., Deng, Q., & Luo, L. (2024). Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, 

Han, Q., Li, C., Lin, Z., Chen, C., Deng, Q., Ge, D., Liu, H., & Ye, Y. (2024). A Low-Rank ADMM Splitting Approach for Semidefinite Programming. arXiv preprint arXiv:2403.09133. 

Gao, W., & Deng, Q. (2024). Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization. Advances in Neural Information Processing Systems, 36. 

王新迎, 闫冬, 施展, 张东霞, 邓琪, 林振炜. 机器学习赋能的优化算法及其在新型电力系统中的应用与展望[J]. 中国电机工程学报, 2024, 44 (16): 6367-6385.

Shi, Z., Wang, X., Yan, D., Chen, S., Lin, Z., Xia, J., & Deng, Q. (2023). An accelerated primal‐dual method for semi‐definite programming relaxation of optimal power flow. IET Energy Systems Integration, 5(4), 477-490. 

Liu, J., Xie, C., Deng, Q., Ge, D., & Ye, Y. (2023). Stochastic Dimension-reduced Second-order Methods for Policy Optimization. arXiv preprint arXiv:2301.12174. 

Lin, Z., & Deng, Q. (2023). Gbm-based bregman proximal algorithms for constrained learning. arXiv preprint arXiv:2308.10767. 

Boob, D., Deng, Q., & Lan, G. (2023). Stochastic first-order methods for convex and nonconvex functional constrained optimization. Mathematical programming, 197(1), 215-279. 

Boob, D., & Deng, Q. (2023). First-order methods for Stochastic Variational Inequality problems with Function Constraints. arXiv preprint arXiv:2304.04778. 

Deng, Q., & Gao, W. (2021). Minibatch and momentum model-based methods for stochastic weakly convex optimization. Advances in Neural Information Processing Systems, 34, 23115-23127. 

邓琪, 高建军, 葛冬冬, 何斯迈, 江波, 李晓澄, 王子卓, 杨超林, & 叶荫宇. (2020). 现代优化理论与应用. 中国科学: 数学, 50(7), 899-968. 

Deng, Q., & Lan, C. (2020). Efficiency of coordinate descent methods for structured nonconvex optimization. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 

Boob, D., Deng, Q., Lan, G., & Wang, Y. (2020). A feasible level proximal point method for nonconvex sparse constrained optimization. Advances in Neural Information Processing Systems, 33, 16773-16784. 

Tan, Y., Paul, A. A., Deng, Q., & Wei, L. (2017). Mitigating inventory overstocking: Optimal order‐up‐to level to achieve a target fill rate over a finite horizon. Production and Operations Management, 26(11), 1971-1988. 

Data structures