DMCA
Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems
Cached
Download Links
by
Aaron J. Defazio
,
Tibério S. Caetano
,
Justin Domke
| Citations: | 6 - 1 self |
BibTeX
@MISC{Defazio_finito:a,
author = {Aaron J. Defazio and Tibério S. Caetano and Justin Domke},
title = {Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box ”batch ” problem. In this work we introduce a new method in this class with a theo-retical convergence rate four times faster than ex-isting methods, for sums with sufficiently many terms. This method is also amendable to a sam-pling without replacement scheme that in prac-tice gives further speed-ups. We give empirical results showing state of the art performance. 1.
