An Asynchronous Distributed ADMM Algorithm and Efficient Communication Model

被引：7

作者：

Fang, Ling ^{[1
]}

Lei, Yongmei ^{[1
]}

机构：

[1] Shanghai Univ, Sch Comp Engn & Sci, Shanghai, Peoples R China

来源：

2016 IEEE 14TH INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, 14TH INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, 2ND INTL CONF ON BIG DATA INTELLIGENCE AND COMPUTING AND CYBER SCIENCE AND TECHNOLOGY CONGRESS (DASC/PICOM/DATACOM/CYBERSC | 2016年

关键词：

ADMM; asynchronous; hierarchical communication model; butterfly;

D O I：

10.1109/DASC-PICom-DataCom-CyberSciTec.2016.41

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we present a hierarchical butterfly communication model, which is applied to an asynchronous distributed ADMM algorithm. The goal is to minimize the communication overhead of the distributed ADMM algorithm in the fully connected network. We give a theoretical analysis of the convergence of the algorithm with hierarchical butterfly communication model. Experiments show that hierarchical butterfly communication model does not have a great impact on the convergence of the algorithm with the increase of computing nodes and thus effectively improve the performance and scalability of the algorithm.

引用

页码：136 / 140

页数：5

共 13 条

[1]

[Anonymous], 2012, J SCI COMPUTING

[2]

[Anonymous], 2014, P INT C MACH LEARN

[3] Distributed optimization and statistical learning via the alternating direction method of multipliers [J].

Boyd S. ;

Parikh N. ;

Chu E. ;

Peleato B. ;

Eckstein J. .

Foundations and Trends in Machine Learning, 2010, 3 (01) :1-122

[4]

Dean J, 2004, USENIX ASSOCIATION PROCEEDINGS OF THE SIXTH SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION (OSDE '04), P137

[5]

Forero PA, 2010, J MACH LEARN RES, V11, P1663

[6]

Gropp W., 1996, SCI PROGRAMMING-NETH, V5, P275

[7]

Ho Qirong, 2013, Adv Neural Inf Process Syst, V2013, P1223

[8]

Lubell-Doughtie Peter, 2013, 2013 IEEE International Conference on Big Data, P773, DOI 10.1109/BigData.2013.6691651

[9] Distributed Sparse Linear Regression [J].

Mateos, Gonzalo ;

Bazerque, Juan Andres ;

Giannakis, Georgios B. .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2010, 58 (10) :5262-5276

[10] D-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization [J].

Mota, Joao F. C. ;

Xavier, Joao M. F. ;

Aguiar, Pedro M. Q. ;

Pueschel, Markus .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2013, 61 (10) :2718-2723

← 1 2 →