Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2022

Abstract

Communication efficiency has been widely recognized as the bottleneck for large-scale decentralized machine learning applications in multi-agent or federated environments. To tackle the communication bottleneck, there have been many efforts to design communication-compressed algorithms for decentralized nonconvex optimization, where the clients are only allowed to communicate a small amount of quantized information (aka bits) with their neighbors over a predefined graph topology. Despite significant efforts, the state-of-the-art algorithm in the nonconvex setting still suffers from a slower rate of convergence $O((G/T)^{2/3})$ compared with their uncompressed counterpart, where $G$ measures the data heterogeneity across different clients, and $T$ is the number of communication rounds. This paper proposes BEER, which adopts communication compression with gradient tracking, and shows it converges at a faster rate of $O(1/T)$. This significantly improves over the state-of-the-art rate, by matching the rate without compression even under arbitrary data heterogeneity. Numerical experiments are also provided to corroborate our theory and confirm the practical superiority of beer in the data heterogeneous regime.

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Publication

Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Hybrid Conference, November 28 - December 9

First Page

1

Last Page

26

Publisher

Neural Information Processing Systems Foundation

City or Country

New Orleans, USA

Additional URL

https://proceedings.neurips.cc/paper_files/paper/2022/hash/cd86c6a804d925c4cbc5a7b96843f6d5-Abstract-Conference.html

Share

COinS