Accelerated mini-batch stochastic dual coordinate ascent

Research output: Contribution to journalConference articlepeer-review

75 Scopus citations

Abstract

Stochastic dual coordinate ascent (SDCA) is an effective technique for solving regularized loss minimization problems in machine learning. This paper considers an extension of SDCA under the mini-batch setting that is often used in practice. Our main contribution is to introduce an accelerated mini-batch version of SDCA and prove a fast convergence rate for this method. We discuss an implementation of our method over a parallel computing system, and compare the results to both the vanilla stochastic dual coordinate ascent and to the accelerated deterministic gradient descent method of Nesterov [2007].

Original languageAmerican English
JournalAdvances in Neural Information Processing Systems
StatePublished - 2013
Event27th Annual Conference on Neural Information Processing Systems, NIPS 2013 - Lake Tahoe, NV, United States
Duration: 5 Dec 201310 Dec 2013

Fingerprint

Dive into the research topics of 'Accelerated mini-batch stochastic dual coordinate ascent'. Together they form a unique fingerprint.

Cite this