English

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.

Keywords

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}
}
R2 v1 2026-06-21T18:26:14.853Z