Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems

author: Christopher De Sa, Department of Computer Science, Stanford University
published: Dec. 5, 2015,   recorded: October 2015,   views: 1969
Categories

See Also:

Download slides icon Download slides: icml2015_de_sa_matrix_problems_01.pdf (278.0 KB)


Help icon Streaming Video Help

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Delicious Bibliography

Description

Stochastic gradient descent (SGD) on a low-rank factorization is commonly employed to speed up matrix problems including matrix completion, subspace tracking, and SDP relaxation. In this paper, we exhibit a step size scheme for SGD on a low-rank least-squares problem, and we prove that, under broad sampling conditions, our method converges globally from a random starting point within O(ϵ−1nlogn) steps with constant probability for constant-rank problems. Our modification of SGD relates it to stochastic power iteration. We also show some experiments to illustrate the runtime and convergence of the algorithm.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: