We resolve the min-max complexity of distributed stochastic convex optimization (up to a log factor) in the intermittent communication setting, where M machines work in parallel over the course of R rounds of communication to optimize the objective, and during each round of communication, each machine may sequentially compute K stochastic gradient estimates. We present a novel lower bound with a matching upper bound that establishes an optimal algorithm.
@article{arxiv.2102.01583,
title = {The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication},
author = {Blake Woodworth and Brian Bullins and Ohad Shamir and Nathan Srebro},
journal= {arXiv preprint arXiv:2102.01583},
year = {2021}
}