Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication CompressionDownload PDF

Published: 31 Oct 2022, Last Modified: 11 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: Distributed Learning, Communication Compression, Optimal Complexity, Non-convex Optimization
TL;DR: This paper establishes the lower bounds for distributed algorithms using unbiased/contractive compressors with unidirectional/bidirectional compression, and develops algorithms to achieve this rate.
Abstract: Recent advances in distributed optimization and learning have shown that communication compression is one of the most effective means of reducing communication. While there have been many results for convergence rates with compressed communication, a lower bound is still missing. Analyses of algorithms with communication compression have identified two abstract properties that guarantee convergence: the unbiased property or the contractive property. They can be applied either unidirectionally (compressing messages from worker to server) or bidirectionally. In the smooth and non-convex stochastic regime, this paper establishes a lower bound for distributed algorithms whether using unbiased or contractive compressors in unidirection or bidirection. To close the gap between this lower bound and the best existing upper bound, we further propose an algorithm, NEOLITHIC, that almost reaches our lower bound (except for a logarithm factor) under mild conditions. Our results also show that using contractive compressors in bidirection can yield iterative methods that converge as fast as those using unbiased compressors unidirectionally. We report experimental results that validate our findings.
Supplementary Material: pdf
21 Replies