Stochastic dual coordinate ascent with adaptive probabilities

Dominik Csiba, Zheng Qu, Peter Richtarik

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

38 Scopus citations

Abstract

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method to adaptively change the probability distribution over the dual variables throughout the iterative process. AdaSDCA achieves provably better complexity bound than SDCA with the best fixed probability distribution, known as importance sampling. However, it is of a theoretical character as it is expensive to implement. We also propose AdaSDCA+: a practical variant which in our experiments outperforms existing non-adaptive methods.
Original languageEnglish (US)
Title of host publication32nd International Conference on Machine Learning, ICML 2015
PublisherInternational Machine Learning Society (IMLS)rasmussen@ptd.net
Pages674-683
Number of pages10
ISBN (Print)9781510810587
StatePublished - Jan 1 2015
Externally publishedYes

Fingerprint

Dive into the research topics of 'Stochastic dual coordinate ascent with adaptive probabilities'. Together they form a unique fingerprint.

Cite this