SCS Recruiting Seminar: Yuanzhi Li

Event Details
  • Date/Time:
    • Tuesday January 15, 2019 - Wednesday January 16, 2019
      11:00 am - 11:59 am
  • Location: KACB 1116W
  • Phone:
  • URL:
  • Email:
  • Fee(s):
  • Extras:

Tess Malone, Communications Officer


Summary Sentence: Towards Deeper Understandings of Deep Learning

Full Summary: No summary paragraph submitted.

  • Yuanzhi Li Yuanzhi Li

TITLE: Towards Deeper Understandings of Deep Learning


Recent breakthroughs in machine learning often involve learning highly non-convex models, especially deep neural networks. Though many empirical works have demonstrated the success of these methods, the formal study of the principles behind them is less established.

This talk will show a few of the recent results towards developing such principles. In particular, we focus on the over-parameterized neural networks for multi-class classifications. We will show that stochastic gradient descent (SGD) on over-parameterized deep neural networks provably finds the global minimum for the training objective. Moreover, we also prove that such perfect fitting can also be extended to test data set when the labels are generated by certain teaching networks.

This talk will also cover how to use the above results as a step to establish the theory behind the “magic’’ of learning rate decay in training neural networks, as well as how the identity mapping in ResNet helps in the learning process.


Yuanzhi Li is a postdoctoral researcher at the computer science department of Stanford University. Previously, he obtained his Ph.D. at Princeton under the advice of Sanjeev Arora. His research interests include topics in deep learning, non-convex optimization, and online learning.


Additional Information

In Campus Calendar

College of Computing, School of Computer Science

Invited Audience
Faculty/Staff, Postdoc, Public, Graduate students, Undergraduate students
No keywords were submitted.
  • Created By: Tess Malone
  • Workflow Status: Published
  • Created On: Jan 10, 2019 - 2:19pm
  • Last Updated: Jan 10, 2019 - 2:22pm