The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication
Blake E Woodworth , Brian Bullins , Ohad Shamir , Nathan Srebro
Session: Paper Awards
Poster: Poster Session 4
Abstract:
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.