Chi Jin (金驰)

I am currently a 6th-year Ph.D. student in EECS at UC Berkeley advised by Michael I. Jordan. I am also a member of RISELab and Berkeley Artificial Intelligence Research (BAIR). Prior to that, I received a B.S. in Physics from Peking University, and did my undergraduate thesis with Liwei Wang.

My research interests lie in machine learning, statistics and optimization. The primary goal of my Ph.D. research is to design better learning algorithms that are theoretically sound, and efficient in sample complexity, runtime and space. To achieve this goal, my research has focused on providing a deeper understanding of fundamental questions in nonconvex optimization and recently in reinforcement learning.

I will join the department of Electrical Engineering at Princeton University as an assistant professor in Sep 2019. I will also participate in "Special Year on Optimization, Statistics, and Theoretical Machine Learning" at IAS in fall 2019.

News

Oct 2018 I gave an invited talk at 56th Annual Allerton Conference.

July 2018 Paper "Is Q-learning Provably Efficient?" won best paper award in ICML 2018 workshop "Exploration in RL".

July 2018 Co-organized ICML 2018 workshop "Modern Trends in Nonconvex Optimization for Machine Learning".

July 2017 Blog post on How to Escape Saddle Point Efficiently.

Selected Paper

What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? [arXiv]

Chi Jin, Praneeth Netrapalli, Michael I. Jordan

ArXiv Preprint

Is Q-learning Provably Efficient? [arXiv]

Chi Jin*, Zeyuan Allen-Zhu*, Sebastien Bubeck, Michael I. Jordan

Neural Information Processing Systems (NIPS) 2018. Best Paper in ICML 2018 workshop "Exploration in RL"

Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent [arXiv]

Chi Jin, Praneeth Netrapalli, Michael I. Jordan

Conference of Learning Theory (COLT) 2018

How to Escape Saddle Points Efficiently [arXiv] [blog]

Chi Jin, Rong Ge, Praneeth Netrapalli, Sham M. Kakade, Michael I. Jordan

International Conference on Machine Learning (ICML) 2017.

Education

2013 - Present University of California, Berkeley

Ph.D. student in Computer Science

2012 - 2013 University of Toronto

Visiting student in Statistics

2008 - 2012 Peking University

Bachelor of Science in Physics

Experience

Summer 2016 Microsoft Research, Redmond

Research Intern with Dong Yu

Summer 2015 Microsoft Research, New England

Research Intern with Sham Kakade