Mini-batch primal and dual methods for SVMs

Martin Takáč, Avleen Bijral, Peter Richtárik, Nathan Srebro

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

74 Scopus citations

Abstract

We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss. Copyright 2013 by the author(s).
Original languageEnglish (US)
Title of host publication30th International Conference on Machine Learning, ICML 2013
PublisherInternational Machine Learning Society (IMLS)rasmussen@ptd.net
Pages2059-2067
Number of pages9
StatePublished - Jan 1 2013
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-25

Fingerprint

Dive into the research topics of 'Mini-batch primal and dual methods for SVMs'. Together they form a unique fingerprint.

Cite this