Ph.D. Systems Engineering, University of Virginia, 2016

B.Sc. Engineering Mechanics,Peking University, 2012

Dr. Shi Pu is an Assistant Professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen. He received a B.S. degree from Peking University in 2012, and a Ph.D. degree in Systems Engineering from the University of Virginia in 2016. From 2016 to 2019, he conducted postdoctoral research at the University of Florida, Arizona State University and Boston University, respectively. His main research interests lie in distributed optimization and learning over multi-agent networks. Dr. Pu received the Louis T. Rader Outstanding Graduate Student Award in 2017. He has published in several top journals including Operations Research, Mathematical Programming and IEEE Transactions on Automatic Control. His research has been funded by NSFC, SRIBD and AIRS. He is serving as an associate editor on the conference editorial board (CEB) of the IEEE Control Systems Society.

Preprints

1. Kun Huang*, Linli Zhou* and Shi Pu, Distributed Random Reshuffling Methods with Improved Convergence, submitted.
2. Kun Huang*, Xiao Li and Shi Pu, Distributed Stochastic Optimization under a General Variance Condition, submitted.
3. Kun Huang* and Shi Pu, CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence, submitted.
4. Yiwei Liao*, Zhuorui Li and Shi Pu, A Linearly Convergent Robust Compressed Push-Pull Method for Decentralized Optimization, submitted.
5. Zhuoqing Song*, Lei Shi, Shi Pu and Ming Yan, Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs, submitted.

Journal Papers

1. Zhuoqing Song*, Lei Shi, Shi Pu and Ming Yan, Optimal Gradient Tracking for Decentralized Optimization, Mathematical Programming, accepted.
2. Kun Huang*, Xiao Li, Andre Milzarek, Shi Pu and Junwen Qiu, Distributed Random Reshuffling over Networks, IEEE Transactions on Signal Processing, accepted.
3. Yijie Zhou* and Shi Pu, Private and Accurate Decentralized Optimization via Encrypted and Structured Functional Perturbation, IEEE Control Systems Letters, 7:1339 - 1344, 2023.
4. Kun Huang* and Shi Pu, Improving the Transient Times for Distributed Stochastic Gradient Methods, IEEE Transactions on Automatic Control, accepted.
5. Zhuoqing Song*, Lei Shi, Shi Pu and Ming Yan, Compressed Gradient Tracking for Decentralized Optimization over General Directed Networks, IEEE Transactions on Signal Processing, 70:1775 - 1787, 2022.
6. Yiwei Liao*, Zhuorui Li*, Kun Huang* and Shi Pu, A Compressed Gradient Tracking Method for Decentralized Optimization with Linear Convergence, IEEE Transactions on Automatic Control, 67(10):5622-5629, 2022.
7. Shi Pu, Alex Olshevsky and Ioannis Ch. Paschalidis, A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent, IEEE Transactions on Automatic Control, 67(11):5900-5915, 2022.
8. Shi Pu and Angelia Nedić. Distributed Stochastic Gradient Tracking Methods. Mathematical Programming, 187(1):409-457, 2021. [arXiv]
9. Shi Pu, Wei Shi (co-first), Jinming Xu and Angelia Nedić. Push-Pull Gradient Methods for Distributed Optimization in Networks. IEEE Transactions on Automatic Control, 66(1):1-16, 2021. [arXiv]
10. Ran Xin, Shi Pu, Angelia Nedić and Usman Khan. A General Framework for Decentralized Optimization with First-order Methods. Proceedings of the IEEE, 108(11):1869-1889, 2020.
11. Shi Pu, Alex Olshevsky and Ioannis Ch. Paschalidis, Asymptotic Network Independence in Distributed Stochastic Optimization for Machine Learning: Examining Distributed and Centralized Stochastic Gradient Descent. IEEE Signal Processing Magazine, 37(3):114-122, 2020. [arXiv].
12. Shi Pu, J. Joaquin Escudero-Garzás, Alfredo Garcia and Shahin Shahrampour. An Online Mechanism for Resource Allocation in Networks. IEEE Transactions on Control of Network Systems, 7(3):1140-1150, 2020.
13. Shi Pu and Alfredo Garcia. Swarming for Faster Convergence in Stochastic Optimization. SIAM Journal on Control and Optimization, 56(4):2997-3020, 2018. [arXiv]
14. Shi Pu and Alfredo Garcia. A Flocking-based Approach for Distributed Stochastic Optimization. Operations Research, 66(1):267-281, 2018. [arXiv]
15. Shi Pu, Alfredo Garcia and Zongli Lin. Noise Reduction by Swarming in Social Foraging. IEEE Transactions on Automatic Control, 61(12):4007-4013, 2016.

Book Chapter

1. Alfredo Garcia, Bingyu Wang* and Shi Pu. Distributed Optimization. In: Pardalos, P.M., Prokopyev, O.A. (eds) Encyclopedia of Optimization. Springer, Cham.

Conference Papers

1. Shi Pu, A Robust Gradient Tracking Method for Distributed Optimization over Directed Networks, 2020 IEEE 59th Conference on Decision and Control (CDC).
2. Shi Pu and Angelia Nedić. A Distributed Stochastic Gradient Tracking Method. 2018 IEEE 57th Conference on Decision and Control (CDC).
3. Shi Pu, Wei Shi, Jinming Xu and Angelia Nedić. A Push-Pull Gradient Method for Distributed Optimization in Networks. 2018 IEEE 57th Conference on Decision and Control (CDC).

*(co-)supervised student/postdoc