Geometric descent method for convex composite minimization
Refereed conference paper presented and published in conference proceedings

CUHK Authors
Author(s) no longer affiliated with CUHK

Full Text

Times Cited

Other information
AbstractIn this paper, we extend the geometric descent method recently proposed by Bubeck, Lee and Singh to tackle nonsmooth and strongly convex composite problems. We prove that our proposed algorithm, dubbed geometric proximal gradient method (GeoPG), converges with a linear rate (1-1/\sqrt{\kappa}) and thus achieves the optimal rate among first-order methods, where \kappa is the condition number of the problem. Numerical results on linear regression and logistic regression with elastic net regularization show that GeoPG compares favorably with Nesterov's accelerated proximal gradient method, especially when the problem is ill-conditioned.
Acceptance Date05/09/2017
All Author(s) ListShixiang Chen, Shiqian Ma, Wei Liu
Name of ConferenceThirty-first Conference on Neural Information Processing Systems
Start Date of Conference04/12/2017
End Date of Conference09/12/2017
Place of ConferenceLong Beach
Country/Region of ConferenceUnited States of America
Proceedings TitleAdvances in Neural Information Processing Systems 30 (NIPS 2017)
Volume Number30
LanguagesEnglish-United States

Last updated on 2021-21-01 at 02:18