Jiawei Zhang

Jiawei Zhang

Postdoctoral scholar in LIDS @ MIT

Massachusetts Institute of Technology

Biography

Jiawei Zhang is currently the postdoctoral scholar in the Laboratory for Information & Decision Systems (LIDS) at MIT, working with Asuman Ozdaglar. He obtained the Ph.D. degree in Computer and Information Engineering from the Chinese University of Hong Kong (CUHK), studied in CUHK-Shenzhen with advisory of Zhi-Quan (Tom) Luo. Previously, he obtained the B.Sc. in Mathematics (Hua Loo-Keng talent program) University of Science and Technology of China.

His research interests include optimization theory, designing efficient optimization algorithms and their applications to machine learning and data science. Recently, I am very interested in understanding machine learning especially deep learning from an optimization perspective.

I organized two sessions in INFORMS Annual meeting 2022 on nonconvex nonsmooth optimization and nonconvex constrained optimization.

Download my resumé.

Interests
  • Optimization theory
  • Optimization algorithms and their applications to machine learning and data science
  • Understanding machine learning especially deep learning from an optimization perspective
Education
  • Ph.D. in Computer and Information Engineering

    The Chinese University of Hong Kong (CUHK)

  • B.Sc. in Mathematics

    University of Science and Technology of China (USTC)

Recent Publications

Quickly discover relevant content by filtering publications.
(2022). Decentralized Non-Convex Learning With Linearly Coupled Constraints: Algorithm Designs and Application to Vertical Learning Problem. IEEE Transactions on Signal Processing.

Cite DOI

(2022). What is a Good Metric to Study Generalization of Minimax Learners?. arXiv preprint arXiv:2206.04502.

Cite

(2021). Communication Efficient Primal-Dual Algorithm for Nonconvex Nonsmooth Distributed Optimization. International Conference on Artificial Intelligence and Statistics.

Cite

(2021). Distributed stochastic consensus optimization with momentum for nonconvex nonsmooth problems. IEEE Transactions on Signal Processing.

Cite

Contact