Shi Pu’s Homepage
Welcome! I am an associate professor with tenure at the School of Data Science, The Chinese University of Hong Kong, Shenzhen.
Research Interests
Distributed optimization, federated learning, large-scale machine learning, multi-agent networks.
See here for our research topics, and here for our publications.
Openings
We are always looking for self-motivated students with solid mathematical background and research interests in distributed optimization, large-scale optimization algorithms, machine learning, federated learning, game theory, etc.
Recent News
- July. 2026: I become an associate professor with tenure at CUHK-Shenzhen!
- June. 2026: Our paper, Accelerating Decentralized Optimization via Overlapping Local Steps (with Yijie Zhou), has been accepted by IEEE Control Systems Letters!
- May. 2026: Congratulations to Yijie Zhou for passing the PhD defense!
- May. 2026: Our paper, BAS: Bridging Adam and SignSGD for Memory-Efficient LLM Training (with Yijie Zhou, Mingliang Zhang, Jiaqi Zhang and Xunliang Cai), has been accepted by ICML 2026!
- March. 2026: Our paper, Stochastic Push-Pull for Decentralized Nonconvex Optimization (with Runze You), has been accepted for publication in IEEE Transactions on Signal Processing!
- January. 2026: Our paper, Arbitrary-Order Block SignSGD for Memory-Efficient LLM Fine-Tuning (with Yijie Zhou), has been accepted by ICLR 2026!
- October. 2025: Our paper, Distributed Stochastic Momentum Tracking with Local Updates: Achieving Optimal Communication and Iteration Complexities (with Kun Huang), is online!
- October. 2025: We oganized the 2025 Symposium on Distributed Optimization and Learning (SDOL 2025) at SUSTech (with Prof. Xuyang Wu).
- June. 2025: Our paper, Stochastic Push-Pull for Decentralized Nonconvex Optimization (with Runze You), is online!
- May. 2025: Our paper, Decentralized Min-Max Optimization with Gradient Tracking (with Runze You and Kun Huang), is online!
- May. 2025: Our paper, Asynchronous Decentralized SGD under Non-Convexity: A Block-Coordinate Descent Framework (with Yijie Zhou), is online!
- March. 2025: Our paper, Distributed Learning over Arbitrary Topology: Linear Speed-Up with Polynomial Transient Time (with Runze You), is online!
- March. 2025: Our paper, Distributed Random Reshuffling Methods with Improved Convergence (with Kun Huang and Linli Zhou), has been accepted for publication in IEEE Transactions on Automatic Control!
- February. 2025: Our paper, An Accelerated Distributed Stochastic Gradient Method with Momentum (with Kun Huang and Angelia Nedić), has been accepted for publication in Mathematical Programming!
- February. 2025: I gave a talk titled “B-ary Tree Push-Pull Method for Distributed Optimization” at Anhui University. Thank Prof. Songsong Cheng for inviting!
- December. 2024: Congratulations to Kun Huang for passing the PhD defense!
- December. 2024: Our paper, Distributed Normal Map-based Stochastic Proximal Gradient Methods over Networks (with Kun Huang and Angelia Nedić), is online!
- December. 2024: Our paper, Linear Convergence Analysis of Single-loop Algorithm for Bilevel Optimization via Small-gain Theorem (with Jianhui Li, Jianqi Chen and Junfeng Wu), is online!
- November. 2024: I gave a talk titled “B-ary Tree Push-Pull Method for Distributed Optimization” at SUSTech. Thank Prof. Jin Zhang for inviting!
- September. 2024: Our paper, CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence (with Kun Huang), has been accepted for publication in IEEE Transactions on Automatic Control as Full Paper!
- September. 2024: Our paper, B-ary Tree Push-Pull Method is Provably Efficient for Decentralized Learning on Heterogeneous Data (with Runze You), has been accepted by NeurIPS 2024!
- August. 2024: Our paper, A Robust Compressed Push-Pull Method for Decentralized Nonconvex Optimization (with Yiwei Liao, Zhuorui Li and Tsung-Hui Chang), is online!
- April. 2024: Our paper, Distributed Stochastic Optimization under a General Variance Condition (with Kun Huang and Xiao Li), has been accepted for publication in IEEE Transactions on Automatic Control as Full Paper!
- April. 2024: Our paper, B-ary Tree Push-Pull Method is Provably Efficient for Decentralized Learning on Heterogeneous Data (with Runze You), is online!
- February. 2024: Our paper, An Accelerated Distributed Stochastic Gradient Method with Momentum (with Kun Huang and Angelia Nedić), is online!