No more pesky learning rates

Tom Schaul, Sixin Zhang, Yann LeCun

Research output: Contribution to conferencePaper

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 SGD or other adaptive approaches with their best settings obtained through systematic search, and effectively removes the need for learning rate tuning.

Original languageEnglish (US)
Pages1380-1388
Number of pages9
StatePublished - Jan 1 2013
Event30th International Conference on Machine Learning, ICML 2013 - Atlanta, GA, United States
Duration: Jun 16 2013Jun 21 2013

Other

Other30th International Conference on Machine Learning, ICML 2013
CountryUnited States
CityAtlanta, GA
Period6/16/136/21/13

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Sociology and Political Science

Cite this

Schaul, T., Zhang, S., & LeCun, Y. (2013). No more pesky learning rates. 1380-1388. Paper presented at 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, United States.