Shixiang Chen (陈士祥)
 |
Assistant Professor(特任研究员), |
About me
I am an Assistant Professor(特任研究员) at School of Mathematical Sciences, University of Science and Technology(USTC). Between September 2021 and April 2023, I worked as an Algorithm Scientist at JD Explore Academy, JD.com. I was a Postdoctoral Associate at Texas A&M University from Sept. 2019 to Aug. 2021, with Prof. Alfredo Garcia and Prof. Shahin Shahrampour. I completed my PhD at The Chinese University of Hong Kong(CUHK) in 2019, under the supervision of Prof. Shiqian Ma and Prof. Anthony Man-Cho So. I earned Bachelor’s degree in Mathematics at Nanjing University in 2015. My research interests are optimization and machine learning. My recent research focuses on decentralized optimization and Riemannian optimization.
Research
My research interests include:
Optimization
Machine Learning
News
Our paper [Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold ]received the SIAM Review SIGEST Award! Coauthored with Shiqian Ma, Anthony Man-Cho So and Tong Zhang. - Roughly every four years one paper from SIAM J. Optimization is selected for this award!
Preprints
Jinxin Wang, Jiang Hu, Shixiang Chen, Zengde Deng, Anthony Man-Cho So. Decentralized Weakly Convex Optimization Over the Stiefel Manifold. [pdf]
Journal papers
Shixiang Chen, Alfredo Garcia, Mingyi Hong and Shahin Shahrampour. On the Local Linear Rate of Consensus on the Stiefel Manifold. Accepted in IEEE Transactions on Automatic Control, 2024 [pdf].
Zhongruo Wang, Bingyuan Liu, Shixiang Chen, Shiqian Ma, Lingzhou Xue, Hongyu Zhao, "A Manifold Proximal Linear Method for Sparse Spectral Clustering with Application to Single-Cell RNA Sequencing Data Analysis", Informs Journal on Optimization, 2022 .[pdf].
Shixiang Chen, Zengde Deng, Shiqian Ma and Anthony Man-Cho So, "Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning", IEEE Transactions on Signal Processing, 2021. [pdf]
Xiao Li*, Shixiang Chen*, Zengde Deng, Qing Qu, Zhihui Zhu, Anthony Man-Cho So, "Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods", SIAM Journal on Optimization, 2021.[pdf].
Shixiang Chen, Alfredo Garcia and Shahin Shahrampour, "On Distributed Non-convex Optimization: Projected Subgradient Method For Weakly Convex Problems in Networks", IEEE Transactions on Automatic Control, 2021 .[pdf]
Shixiang Chen, Shiqian Ma, Lingzhou Xue and Hui Zou, "An Alternating Manifold Proximal Gradient Method for Sparse PCA and Sparse CCA", Informs Journal on Optimization, 2020.[pdf][code]
Shixiang Chen, Shiqian Ma, Anthony Man-Cho So, and Tong Zhang, "Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold," SIAM Journal on Optimization, 2020. [pdf][code]
Conference papers
Yan Sun, Li Shen, Shixiang Chen, Liang Ding, Dacheng Tao, "Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape", ICML 2023
Yibo Yang, Shixiang Chen, Liang Xie, Xiangtai Li, Zhouchen Lin, Dacheng Tao, "Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?", NeurIPS 2022 . [pdf]
Shixiang Chen, Alfredo Garcia, Mingyi Hong, Shahin Shahrampour, "Decentralized Riemannian Gradient Descent on the Stiefel Manifold", ICML 2021. [pdf][code]
Shixiang Chen, Zengde Deng, Shiqian Ma and Anthony Man-Cho So, "Manifold proximal point algorithms for dual principal component pursuit and orthogonal dictionary learning", Asilomar Conference on Signals, Systems, and Computers, 2019.
Shixiang Chen, Shiqian Ma and Wei Liu, "Geometric descent method for convex composite minimization", NeurIPS 2017 . [pdf]
Note: * indicates equal contribution.
Academic service
Reviewer
SIAM Journal on Optimization, Optimization Methods and Software, Computational Optimization and Applications, Journal of Global Optimization, Optimization,
IEEE Transactions on Automatic control, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Signal Processing
ICML, Neurips, ICLR, CDC