Distributed Optimization With Uncertain Communications

• 成果类型: Article
• 署名作者: Rezaeinia, Pouya; Gharesifard, Bahman; Linder, Tamas
• 署名单位: Queens University - Canada; University of California System; University of California Los Angeles
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2024.3495456
• 发表日期: 2025
• 页码: 2746-2753
• 关键词: Directed graphs; CONVERGENCE; vectors; optimization; communication networks; Convex functions; Heuristic algorithms; Protocols; uncertainty; Statistical learning; Distributed control; distributed optimization; ergodic chains; random networks

摘要

In this article, we consider a distributed optimization problem for the sum of convex functions where the underlying communication network connecting nodes at each time epoch is drawn at random from a collection of directed graphs. We propose a modified version of the subgradient-push algorithm that provably almost surely converges to an optimizer on any such sequence of random directed graphs. We also prove that the convergence rate of our proposed algorithm is upper bounded as O(1/root t), where t is the time horizon.