SDCA without duality, regularization, and individual convexity

Shai Shalev-Shwartz*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

19 Scopus citations

Abstract

Stochastic Dual Coordinate Ascent is a popular method for solving regularized loss minimization for the case of convex losses. We describe variants of SDCA that do not require explicit regularization and do not rely on duality. We prove linear convergence rates even if individual loss functions are non-convex, as long as the expected loss is strongly convex.

Original languageAmerican English
Title of host publication33rd International Conference on Machine Learning, ICML 2016
EditorsMaria Florina Balcan, Kilian Q. Weinberger
PublisherInternational Machine Learning Society (IMLS)
Pages1160-1167
Number of pages8
ISBN (Electronic)9781510829008
StatePublished - 2016
Event33rd International Conference on Machine Learning, ICML 2016 - New York City, United States
Duration: 19 Jun 201624 Jun 2016

Publication series

Name33rd International Conference on Machine Learning, ICML 2016
Volume2

Conference

Conference33rd International Conference on Machine Learning, ICML 2016
Country/TerritoryUnited States
CityNew York City
Period19/06/1624/06/16

Fingerprint

Dive into the research topics of 'SDCA without duality, regularization, and individual convexity'. Together they form a unique fingerprint.

Cite this