Convergence Properties of Message-Passing Algorithm for Distributed Convex Optimisation with Scaled Diagonal Dominance

Title: Convergence Properties of Message-Passing Algorithm for Distributed Convex Optimisation with Scaled Diagonal Dominance
Creator: Zhang, Zhaorong; Fu, Minyue
Relation: ARC.DP200103507 http://purl.org/au-research/grants/arc/DP200103507
Relation: IEEE Transactions on Signal Processing Vol. 69, Issue 9 July 2021, p. 3868-3877
Publisher Link: http://dx.doi.org/10.1109/TSP.2021.3092352
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Resource Type: journal article
Date: 2021
Description: This paper studies the convergence properties of the well-known message-passing algorithm for convex optimisation. Under the assumption of pairwise separability and scaled diagonal dominance, asymptotic convergence is established and a simple bound for the convergence rate is provided for message-passing. In comparison with previous results, our results do not require the given convex program to have known convex pairwise components and that our bound for the convergence rate is tighter and simpler. When specialised to quadratic optimisation, we generalise known results by providing a very simple bound for the convergence rate.
Subject: distributed optimisation; message passing; belief propagation; min-sum algorithm; convex optimisation
Identifier: http://hdl.handle.net/1959.13/1438582
Identifier: uon:40660
Identifier: ISSN:1053-587X
Language: eng
Reviewed

		Thumbnail	File	Description	Size	Format