Rong Ge - What 2-layer neural nets can we optimize?

From Katie Gentilello November 12th, 2019

31 plays 0 comments

Optimizing neural networks is a highly nonconvex problem, and even optimizing a 2-layer neural network can be challenging. In the recent years many different approaches were proposed to learn 2-layer neural networks under different assumptions. This talk will give a brief survey on these approaches, and discuss some new results using spectral methods and optimization landscape.

Tags: arc colloquiumgeorgia techalgorithms and randomness centerrecorded by gtlibraryfall 2019

name: Rong Ge
Date: October 28th, 2019
Appears In: Open Scholarship

Comments
Related Media

Loading…

Rong Ge - What 2-layer neural nets can we optimize?

Related Media