On Distributed Nonconvex Optimisation via Modified ADMM
No Preview Available
Citations
Altmetric:
Altmetric::
Associated Records
Authors
File Licence
Editors
Date
2023-01-01
Source Title
IEEE Control Systems Letters
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Melbourne Authors
Affiliation
Electrical and Electronic Engineering
Document Type
Journal Article
Subject Code
Citation
Mafakheri, B., Manton, J. H. & Shames, I. (2023). On Distributed Nonconvex Optimisation via Modified ADMM. IEEE Control Systems Letters, 7, pp.3699-3704. https://doi.org/10.1109/LCSYS.2023.3341100.
Access Status
This item is currently not available from this repository
Access URL
Open Access URL
Open Access at PMC
Linked Resource URL
NHMRC Grant Code
ARC Grant Code
Description
Abstract
This letter addresses the problem of nonconvex nonsmooth decentralised optimisation in multi-agent networks with undirected connected communication graphs. Our contribution lies in introducing an algorithmic framework designed for the distributed minimisation of the sum of a smooth (possibly nonconvex and non-separable) function and a convex (possibly nonsmooth and non-separable) regulariser. The proposed algorithm can be seen as a modified version of the ADMM algorithm where, at each step, an “inner loop” needs to be iterated for a number of iterations. The role of the inner loop is to aggregate and disseminate information across the network. We observe that a naive decentralised approach (one iteration of the inner loop) may not converge. We establish the asymptotic convergence of the proposed algorithm to the set of stationary points of the nonconvex problem where the number of iterations of the inner loop increases logarithmically with the step count of the ADMM algorithm. We present numerical results demonstrating the proposed method’s correctness and performance.