Better Mini-Batch Algorithms via Accelerated Gradient Methods
Machine Learning
2011-06-24 v1
Abstract
Mini-batch algorithms have been proposed as a way to speed-up stochastic convex optimization problems. We study how such algorithms can be improved using accelerated gradient methods. We provide a novel analysis, which shows how standard gradient methods may sometimes be insufficient to obtain a significant speed-up and propose a novel accelerated gradient algorithm, which deals with this deficiency, enjoys a uniformly superior guarantee and works well in practice.
Cite
@article{arxiv.1106.4574,
title = {Better Mini-Batch Algorithms via Accelerated Gradient Methods},
author = {Andrew Cotter and Ohad Shamir and Nathan Srebro and Karthik Sridharan},
journal= {arXiv preprint arXiv:1106.4574},
year = {2011}
}