Title:
What 2-layer neural nets can we optimize?

Thumbnail Image
Authors
Ge, Rong
Authors
Advisors
Advisors
Associated Organizations
Organizational Unit
Organizational Unit
Series
Collections
Supplementary to
Abstract
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.
Sponsor
Date Issued
2019-10-28
Extent
55:49 minutes
Resource Type
Moving Image
Resource Subtype
Lecture
Rights Statement
Rights URI