pith. sign in

arxiv: 1705.07070 · v1 · pith:IS4HFIOMnew · submitted 2017-05-19 · 💻 cs.LG · stat.ML

EE-Grad: Exploration and Exploitation for Cost-Efficient Mini-Batch SGD

classification 💻 cs.LG stat.ML
keywords mini-batchee-gradgradientsperformancestochasticestimateoptimaloracle
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.