Conference proceeding
An Accelerated Proximal Coordinate Gradient Method
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), Vol.27
Advances in Neural Information Processing Systems
01/01/2014
Abstract
We develop an accelerated randomized proximal coordinate gradient (APCG) method, for solving a broad class of composite convex optimization problems. In particular, our method achieves faster linear convergence rates for minimizing strongly convex functions than existing randomized proximal coordinate gradient methods. We show how to apply the APCG method to solve the dual of the regularized empirical risk minimization (ERM) problem, and devise efficient implementations that avoid full-dimensional vector operations. For ill-conditioned ERM problems, our method obtains improved convergence rates than the state-of-the-art stochastic dual coordinate ascent (SDCA) method.
Details
- Title: Subtitle
- An Accelerated Proximal Coordinate Gradient Method
- Creators
- Qihang Lin - Univ Iowa, Iowa City, IA 52242 USAZhaosong Lu - Simon Fraser UniversityLin Xiao - Microsoft Res, Redmond, WA USA
- Contributors
- Z Ghahramani (Editor)M Welling (Editor)C Cortes (Editor)N D Lawrence (Editor)K Q Weinberger (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), Vol.27
- Publisher
- Neural Information Processing Systems (Nips)
- Series
- Advances in Neural Information Processing Systems
- ISSN
- 1049-5258
- Number of pages
- 9
- Language
- English
- Date published
- 01/01/2014
- Academic Unit
- Business Analytics
- Record Identifier
- 9984380455302771
Metrics
2 Record Views