A Distributed Proximal Alternating Direction Multiplier Method for Multiblock Nonsmooth Composite Optimization

In this article, we address a composite optimization problem in a distributed network. Each agent in the network possesses a private local convex function consisting of a differentiable term, a nonsmooth term, and a nonsmooth term combined with a linear operator. The objective is to minimize the sum...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on control of network systems Ročník 12; číslo 1; s. 202 - 215
Hlavní autoři: Zhou, Yuan, Guo, Luyao, Shi, Xinli, Cao, Jinde
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.03.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Artificial neural networks
Asynchronous algorithm
Convergence
Convex functions
distributed composite optimization
Linear operators
Linear programming
Machine learning algorithms
Multipliers
Network topologies
Operators (mathematics)
Optimization
proximal alternating direction multiplier method (ADMM)
Vectors
ISSN:2325-5870, 2372-2533
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this article, we address a composite optimization problem in a distributed network. Each agent in the network possesses a private local convex function consisting of a differentiable term, a nonsmooth term, and a nonsmooth term combined with a linear operator. The objective is to minimize the sum of all local functions while achieving consensus among the local states through information exchange with neighboring agents. To tackle this problem, we propose a novel distributed proximal alternating direction multiplier method (ADMM). By introducing the proximal operator of the nonsmooth term, linearizing the smooth term, and incorporating an additional proximal term, the ADMM subproblem can be solved more efficiently. One key advantage of the proposed algorithm is that it allows each agent to select parameters without being constrained by the network topology. In some instances, the algorithm can be transformed into some classical optimization algorithms. The algorithm is further extended to an asynchronous version by introducing randomized block coordinate. We further analyze the convergence of the proposed asynchronous algorithm and establish the sublinear convergence rate under synchronous conditions. Finally, several numerical experiments are conducted to verify the effectiveness of the proposed algorithm.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2325-5870
2372-2533
DOI:10.1109/TCNS.2024.3462519