Campus Units

Statistics, Computer Science

Document Type

Conference Proceeding

Conference

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications

Publication Version

Published Version

Publication Date

2019

Journal or Book Title

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications

First Page

2431

Last Page

2439

DOI

10.1109/INFOCOM.2019.8737489

Conference Title

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications

Conference Date

April 29-May 2, 2019

City

Paris, France

Abstract

Network consensus optimization has received increasing attention in recent years and has found important applications in many scientific and engineering fields. To solve network consensus optimization problems, one of the most well-known approaches is the distributed gradient descent method (DGD). However, in networks with slow communication rates, DGD's performance is unsatisfactory for solving high-dimensional network consensus problems due to the communication bottleneck. This motivates us to design a communication-efficient DGD-type algorithm based on compressed information exchanges. Our contributions in this paper are three-fold: i) We develop a communication-efficient algorithm called amplified-differential compression DGD (ADC-DGD) and show that it converges under any unbiased compression operator; ii) We rigorously prove the convergence performances of ADC-DGD and show that they match with those of DGD without compression; iii) We reveal an interesting phase transition phenomenon in the convergence speed of ADC-DGD. Collectively, our findings advance the state-of-the-art of network consensus optimization theory.

Comments

This proceeding was published as Zhang, Xin, Jia Liu, Zhengyuan Zhu, and Elizabeth S. Bentley. "Compressed distributed gradient descent: Communication-efficient consensus over networks." In IEEE INFOCOM 2019-IEEE Conference on Computer Communications. (2019): 2431-2439. DOI: 10.1109/INFOCOM.2019.8737489.

Rights

Works produced by employees of the U.S. Government as part of their official duties are not copyrighted within the U.S. The content of this document is not copyrighted.

Language

en

File Format

application/pdf

Share

Article Location

 
COinS