Welcome to
Shi Pu 濮实 WEBSITE
I am an assistant professor in the School of Data Science (SDS) at The Chinese University of Hong Kong, Shenzhen. I received a B.S. Degree in Engineering Mechanics from Peking University, in 2012, and a Ph.D. Degree in Systems Engineering from the University of Virginia, in 2016. From 2016 to 2019, I was a postdoc at the University of Florida, Arizona State University and Boston University, respectively.
My research interests mainly lie in distributed optimization, learning and control within networked multi-agent systems. In particular, I have been focusing on studying distributed stochastic gradient methods and optimization over general, directed network topologies. I have also been working on algorithms involving communication compression techniques recently.
I am always looking for self-motivated students with solid mathematical background and research interests in networks, optimization, machine learning, distributed algorithms, etc.
Sep. 2020: Our paper, A general framework for decentralized optimization with first-order methods (with Ran Xin, Angelia Nedich and Usman Khan) has been accepted by Proceedings of the IEEE.
Aug. 2020: On August 8, I was invited to give a talk at The Workshop on Control, Optimization and Security of Networked Systems, Southeast University. Thank Prof. Guanghui Wen for hosting!
July. 2020: On July 12, I was invited to give a talk at Tongji University. Thank Prof. Jinlong Lei for hosting!
July. 2020: Our paper, A Robust Gradient Tracking Method for Distributed Optimization over Directed Networks, has been accepted by 2020 IEEE 59th Conference on Decision and Control (CDC).
Mar. 2020: We are organizing an invited session for CDC 2020 this December in Jeju Island, Republic of Korea (with Jinming Xu and Hoi To Wai).
Mar. 2020: Our paper, Distributed Stochastic Gradient Tracking Methods (with Angelia Nedich) has been accepted by Mathematical Programming.
Feb. 2020: Our paper, Push-Pull Gradient Methods for Distributed Optimization in Networks (with Wei Shi, Jinming Xu, and Angelia Nedich) has been accepted by IEEE Transactions on Automatic Control.
Jan. 2020: Our paper, Asymptotic Network Independence In Distributed Stochastic Optimization for Machine Learning (with Alex Olshevsky and Ioannis Ch. Paschalidis) has been accepted by IEEE Signal Processing Magazine.
Dec. 2019: Our paper, An Online Mechanism for Resource Allocation in Networks (with J.J. Escudero-Garzas, Alfredo Garcia and Shahin Shahrampour) has been accepted by IEEE Transactions on Control of Network Systems.
*(co-)supervised students/postdocs
#co-first author
Preprints
Z. Song*, L. Shi, S. Pu, M. Yan, Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs.
Z. Song*, L. Shi, S. Pu, M. Yan, Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks.
Y. Liao*, Z. Li*, K. Huang*, S. Pu, Compressed gradient tracking for decentralized optimization with linear convergence.
K. Huang* and S. Pu, Improving the Transient Times for Distributed Stochastic Gradient Methods, submitted.
S. Pu, A. Olshevsky and I.C. Paschalidis, A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent, submitted.
Journal Publications
R. Xin, S. Pu, A. Nedich and U. Khan. A General Framework for Decentralized Optimization With First-Order Methods. Proceedings of the IEEE, 108(11):1869-1889, 2020.
S. Pu and A. Nedich. Distributed Stochastic Gradient Tracking Methods. Mathematical Programming, 2020.
S. Pu, A. Olshevsky and I.C. Paschalidis, Asymptotic Network Independence In Distributed Stochastic Optimization for Machine Learning, IEEE Signal Processing Magazine, 37(3):114-122.
S. Pu, W. Shi#, J. Xu and A. Nedich. Push-Pull Gradient Methods for Distributed Optimization in Networks. IEEE Transactions on Automatic Control, 2020.
S. Pu, J.J. Escudero-Garzas, A. Garcia and S. Shahrampour. An Online Mechanism for Resource Allocation in Networks. IEEE Transactions on Control of Network Systems, 2020.
S. Pu and A. Garcia. Swarming for Faster Convergence in Stochastic Optimization. SIAM Journal on Control and Optimization, 56(4):2997-3020, 2018.
S. Pu and A. Garcia. A Flocking-based Approach for Distributed Stochastic Optimization. Operations Research, 66(1):267-281, 2018.
S. Pu, A. Garcia and Z. Lin. Noise Reduction by Swarming in Social Foraging. IEEE Transactions on Automatic Control, 61(12):4007-4013, 2016.
Conference Proceedings
S. Pu, A Robust Gradient Tracking Method for Distributed Optimization over Directed Networks, 2020 IEEE 59th Conference on Decision and Control (CDC), accepted.
S. Pu and A. Nedich. A Distributed Stochastic Gradient Tracking Method. 2018 IEEE 57th Conference on Decision and Control (CDC). [arxiv]
S. Pu, W. Shi, J. Xu and A. Nedich. A Push-Pull Gradient Method for Distributed Optimization in Networks. 2018 IEEE 57th Conference on Decision and Control (CDC). [arxiv]