On Distributed Nonconvex Optimisation via Modified ADMM
- 11 December 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 7, 3699-3704
Abstract
This paper 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.Keywords
All Related Versions
Funding Information
- Australian Research Council through the Discovery Projects Funding Scheme (DP210102454)
This publication has 17 references indexed in Scilit:
- A Distributed, Asynchronous, and Incremental Algorithm for Nonconvex Optimization: An ADMM ApproachIEEE Transactions on Control of Network Systems, 2017
- Non-Convex Distributed OptimizationIEEE Transactions on Automatic Control, 2017
- Asynchronous Distributed ADMM for Large-Scale Optimization—Part I: Algorithm andConvergence AnalysisIEEE Transactions on Signal Processing, 2016
- Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex ProblemsSIAM Journal on Optimization, 2016
- On the Global and Linear Convergence of the Generalized Alternating Direction Method of MultipliersJournal of Scientific Computing, 2015
- Proximal AlgorithmsFoundations and Trends® in Optimization, 2014
- Distributed Subgradient Methods for Multi-Agent OptimizationIEEE Transactions on Automatic Control, 2009
- Distributed average consensus with least-mean-square deviationJournal of Parallel and Distributed Computing, 2007
- Variational Analysis1998
- Nonlinear ProgrammingJournal of the Operational Research Society, 1997