Distributed Momentum-Based Multiagent Optimization With Different Constraint Sets

• 成果类型: Article
• 署名作者: Zhou, Xu; Ma, Zhongjing; Zou, Suli; Margellos, Kostas
• 署名单位: University of Oxford
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2024.3445575
• 发表日期: 2025
• 页码: 963-978
• 关键词: convergence; optimization; linear programming; Distributed algorithms; Heuristic algorithms; vectors; reviews; distributed optimization; heavy-ball momentum; multiagent networks; subgradient averaging consensus

摘要

In this article, we consider a class of consensus optimization problems over a time-varying communication network wherein each agent can only interact with its neighbors. The target is to minimize the summation of all local and possibly nonsmooth objectives in the presence of different constraint sets per agent. To achieve this goal, we propose a novel distributed heavy-ball algorithm that combines the subgradient tracking technique with a momentum term related to history information. This algorithm promotes the distributed application of existing centralized accelerated momentum methods, especially for constrained nonsmooth problems. Under certain assumptions and conditions on the step-size and momentum coefficient, the convergence and optimality of the proposed algorithm can be guaranteed through a rigorous theoretical analysis, and a convergence rate of O(InK/root K) in objective value is also established. Simulations on an & ell;(1)-regularized logistic-regression problem show that the proposed algorithm can achieve faster convergence than existing related distributed algorithms, while a case study involving a building energy management problem further demonstrates its efficacy.