Teaching

Fundamentals of Distributed Optimization, Peking University

This course introduces fundamentals of distributed optimization for beginning graduate students in engineering and applied mathematics, with an emphasis on the theoretical aspects. Topics covered in this course include a review of convex analysis and centralized first-order methods, consensus methods for distributed averaging, decentralized gradient descent, gradient tracking methods, decentralized ADMM, time-varying communication networks, and a brief introduction to distributed optimization in federated learning.

  • Lecture Notes (Working draft. Any feedback will be appreciated!)

ZJU-CSE Summer School 2022

Teaching Fellow, Harvard University

  • Learning, Estimation and Control of Dynamical Systems
    APMTH 232   Spring 2020   Instructor: Na Li

Teaching Assistant, Caltech