Translator Disclaimer
August 2010 Graphics Processing Units and High-Dimensional Optimization
Hua Zhou, Kenneth Lange, Marc A. Suchard
Statist. Sci. 25(3): 311-324 (August 2010). DOI: 10.1214/10-STS336

Abstract

This article discusses the potential of graphics processing units (GPUs) in high-dimensional optimization problems. A single GPU card with hundreds of arithmetic cores can be inserted in a personal computer and dramatically accelerates many statistical algorithms. To exploit these devices fully, optimization algorithms should reduce to multiple parallel tasks, each accessing a limited amount of data. These criteria favor EM and MM algorithms that separate parameters and data. To a lesser extent block relaxation and coordinate descent and ascent also qualify. We demonstrate the utility of GPUs in nonnegative matrix factorization, PET image reconstruction, and multidimensional scaling. Speedups of 100-fold can easily be attained. Over the next decade, GPUs will fundamentally alter the landscape of computational statistics. It is time for more statisticians to get on-board.

Citation

Download Citation

Hua Zhou. Kenneth Lange. Marc A. Suchard. "Graphics Processing Units and High-Dimensional Optimization." Statist. Sci. 25 (3) 311 - 324, August 2010. https://doi.org/10.1214/10-STS336

Information

Published: August 2010
First available in Project Euclid: 4 January 2011

zbMATH: 1329.62028
MathSciNet: MR2791670
Digital Object Identifier: 10.1214/10-STS336

Rights: Copyright © 2010 Institute of Mathematical Statistics

JOURNAL ARTICLE
14 PAGES


SHARE
Vol.25 • No. 3 • August 2010
Back to Top