Solving ridge regression using sketched preconditioned SVRG

Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.
Original languageEnglish (US)
Title of host publication33rd International Conference on Machine Learning, ICML 2016
PublisherInternational Machine Learning Society (IMLS)rasmussen@ptd.net
Pages2102-2111
Number of pages10
ISBN (Print)9781510829008
StatePublished - Jan 1 2016
Externally publishedYes

Fingerprint

Dive into the research topics of 'Solving ridge regression using sketched preconditioned SVRG'. Together they form a unique fingerprint.

Cite this