Gradient-free method for distributed multi-agent optimization via push-sum algorithms

SummaryThis paper studies the problem of minimizing the sum of convex functions that all share a common global variable, each function is known by one specific agent in the network. The underlying network topology is modeled as a time‐varying sequence of directed graphs, each of which is endowed wit...

Full description

Saved in:
Bibliographic Details
Published in:International journal of robust and nonlinear control 2015-07, Vol.25 (10), p.1569-1580
Main Authors: Yuan, Deming, Xu, Shengyuan, Lu, Junwei
Format: Article
Language:English
Subjects:
Algorithms
Approximation
average consensus
Convergence
distributed optimization
gradient-free method
Graph theory
Mathematical analysis
Mathematical models
multi-agent systems
Networks
Optimization
push-sum algorithm
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:SummaryThis paper studies the problem of minimizing the sum of convex functions that all share a common global variable, each function is known by one specific agent in the network. The underlying network topology is modeled as a time‐varying sequence of directed graphs, each of which is endowed with a non‐doubly stochastic matrix. We present a distributed method that employs gradient‐free oracles and push‐sum algorithms for solving this optimization problem. We establish the convergence by showing that the method converges to an approximate solution at the expected rate of O(lnT/T), where T is the iteration counter. A numerical example is also given to illustrate the proposed method. Copyright © 2014 John Wiley & Sons, Ltd.
ISSN:1049-8923
1099-1239
DOI:10.1002/rnc.3164