Home Page

Papers

Submissions

News

Scope

Editorial Board

Announcements

Proceedings

Open Source Software

Search

Login



RSS Feed

No more pesky learning rates

Tom Schaul, Sixin Zhang, Yann LeCun
;
JMLR W&CP 28 (3) : 343–351, 2013

Abstract

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any one time. The method relies on local gradient variations across samples. In our approach, learning rates can increase as well as decrease, making it suitable for non-stationary problems. Using a number of convex and non-convex learning tasks, we show that the resulting algorithm matches the performance of the best settings obtained through systematic search, and effectively removes the need for learning rate tuning.

Related Material