Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
Optimization and Control
2019-02-12 v3 Machine Learning
Machine Learning
Abstract
We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings, including delayed updates and parallel processing with intermittent communication. We highlight gaps between lower and upper bounds on the oracle complexity, and cases where the "natural" algorithms are not known to be optimal.
Cite
@article{arxiv.1805.10222,
title = {Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization},
author = {Blake Woodworth and Jialei Wang and Adam Smith and Brendan McMahan and Nathan Srebro},
journal= {arXiv preprint arXiv:1805.10222},
year = {2019}
}