SCS & CSE Recruiting Seminar: Chi Jin

Event Details
  • Date/Time:
    • Thursday February 14, 2019 - Friday February 15, 2019
      11:00 am - 11:59 am
  • Location: KACB 1116W
  • Phone:
  • URL:
  • Email:
  • Fee(s):
  • Extras:

Tess Malone, Communications Officer


Summary Sentence: Machine Learning: Why Do Simple Algorithms Work So Well?

Full Summary: No summary paragraph submitted.

  • Chi Jin Chi Jin

TITLE: Machine Learning: Why Do Simple Algorithms Work So Well?


While state-of-the-art machine learning models are deep, large-scale, sequential, and highly nonconvex, the backbone of modern learning algorithms are simple algorithms such as stochastic gradient descent, or Q-learning (in the case of reinforcement learning tasks). A basic question endures —why do simple algorithms work so well even in these challenging settings?
This talk focuses on two fundamental problems: (1) in nonconvex optimization, can gradient descent escape saddle points efficiently? (2) In reinforcement learning, is Q-learning sample efficient? We will provide the first line of provably positive answers to both questions. In particular, we will show that simple modifications to these classical algorithms guarantee significantly better properties, which explains the underlying mechanisms behind their favorable performance in practice.



Chi Jin is a Ph.D. candidate in computer science at UC Berkeley, advised by Michael I. Jordan. He received a B.S. in Physics from Peking University. His research interests lie in machine learning, statistics, and optimization, with his PhD work primarily focused on nonconvex optimization and reinforcement learning.

Additional Information

In Campus Calendar

College of Computing, School of Computer Science, School of Computational Science and Engineering

Invited Audience
Faculty/Staff, Postdoc, Public, Graduate students, Undergraduate students
No keywords were submitted.
  • Created By: Tess Malone
  • Workflow Status: Published
  • Created On: Feb 6, 2019 - 3:45pm
  • Last Updated: Feb 8, 2019 - 10:23am