Efficient generalized conditional gradient with gradient sliding for composite optimization

Yiu Ming CHEUNG, Jian Lou

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Generalized conditional gradient method has regained increasing research interest as an alternative to another popular proximal gradient method for sparse optimization problems. For particular tasks, its low computation cost of linear subproblem evaluation on each iteration leads to superior practical performance. However, the inferior iteration complexity incurs excess number of gradient evaluations, which can counteract the efficiency gained by solving low cost linear subproblem. In this paper, we therefore propose a novel algorithm that requires optimal graduate evaluations as proximal gradient. We also present a refined variant for a type of gauge regularized problem where approximation techniques are allowed to further accelerate linear subproblem computation. Experiments of CUR-like matrix factorization problem with group lasso penalty on four real-world datasets demonstrate the efficiency of the proposed method.

Original languageEnglish
Title of host publicationIJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence
EditorsMichael Wooldridge, Qiang Yang
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3409-3415
Number of pages7
ISBN (Electronic)9781577357384
Publication statusPublished - 2015
Event24th International Joint Conference on Artificial Intelligence, IJCAI 2015 - Buenos Aires, Argentina, Buenos Aires, Argentina
Duration: 25 Jul 201531 Jul 2015

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2015-January
ISSN (Print)1045-0823

Conference

Conference24th International Joint Conference on Artificial Intelligence, IJCAI 2015
Country/TerritoryArgentina
CityBuenos Aires
Period25/07/1531/07/15

Scopus Subject Areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Efficient generalized conditional gradient with gradient sliding for composite optimization'. Together they form a unique fingerprint.

Cite this