English

Communication-Efficient Network-Distributed Optimization with Differential-Coded Compressors

Distributed, Parallel, and Cluster Computing 2019-12-09 v1 Optimization and Control

Abstract

Network-distributed optimization has attracted significant attention in recent years due to its ever-increasing applications. However, the classic decentralized gradient descent (DGD) algorithm is communication-inefficient for large-scale and high-dimensional network-distributed optimization problems. To address this challenge, many compressed DGD-based algorithms have been proposed. However, most of the existing works have high complexity and assume compressors with bounded noise power. To overcome these limitations, in this paper, we propose a new differential-coded compressed DGD (DC-DGD) algorithm. The key features of DC-DGD include: i) DC-DGD works with general SNR-constrained compressors, relaxing the bounded noise power assumption; ii) The differential-coded design entails the same convergence rate as the original DGD algorithm; and iii) DC-DGD has the same low-complexity structure as the original DGD due to a {\em self-noise-reduction effect}. Moreover, the above features inspire us to develop a hybrid compression scheme that offers a systematic mechanism to minimize the communication cost. Finally, we conduct extensive experiments to verify the efficacy of the proposed DC-DGD and hybrid compressor.

Keywords

Cite

@article{arxiv.1912.03208,
  title  = {Communication-Efficient Network-Distributed Optimization with Differential-Coded Compressors},
  author = {Xin Zhang and Jia Liu and Zhengyuan Zhu and Elizabeth S. Bentley},
  journal= {arXiv preprint arXiv:1912.03208},
  year   = {2019}
}

Comments

10 pages, 15 figures, IEEE INFOCOM 2020

R2 v1 2026-06-23T12:38:14.856Z