EE-Grad: Exploration and Exploitation for Cost-Efficient Mini-Batch SGD
Abstract
We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates them to estimate the true gradient. Since the optimal mini-batch size depends on the unknown cost-fidelity function, we propose an algorithm, {\it EE-Grad}, that sequentially explores the performance of mini-batch oracles and exploits the accumulated knowledge to estimate the one achieving the best performance in terms of cost-efficiency. We provide performance guarantees for EE-Grad with respect to the optimal mini-batch oracle, and illustrate these results in the case of strongly convex objectives. We also provide a simple numerical example that corroborates our theoretical findings.
Cite
@article{arxiv.1705.07070,
title = {EE-Grad: Exploration and Exploitation for Cost-Efficient Mini-Batch SGD},
author = {Mehmet A. Donmez and Maxim Raginsky and Andrew C. Singer},
journal= {arXiv preprint arXiv:1705.07070},
year = {2017}
}