期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 70, 期 -, 页码 3312-3327出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2022.3184772
关键词
Distributed optimization; non-convex optimization; vertical learning problems; distributed features
资金
- Shenzhen Science and Technology Program [JCYJ20190813171003723, RCJC20210609104448114]
- NSFC, China [61731018, 62071409]
- Guangdong Provincial Key Laboratory of Big Data Computing
Motivated by the need for decentralized learning, this paper proposes a distributed algorithm for solving non-convex problems with general linear constraints over a multi-agent network. The proposed prox anal dual consensus (PDC) algorithm combines proximal technique and dual consensus method. Numerical results show the good performance of the proposed algorithms for solving two vertical learning problems in machine learning over a multi-agent network.
Motivated by the need for decentralized learning, this paper aims at designing a distributed algorithm for solving non-convex problems with general linear constraints over a multi-agent network. In the considered problem, each agent owns some local information and a local variable for jointly minimizing a cost function, but local variables are coupled by linear constraints. Most of the existing methods for such problems are only applicable for convex problems or problems with specific linear constraints. There still lacks a distributed algorithm for solving such problems with general linear constraints under the nonconvex setting. To tackle this problem, we propose a new algorithm, called prox anal dual consensus (PDC) algorithm, which combines a proximal technique and a dual consensus method. We show that under certain conditions the proposed PDC algorithm can generate an epsilon-Karush-Kuhn-Tucker solution in O (1/epsilon) iterations, achieving the lower bound for distributed non-convex problems up to a constant. Numerical results are presented to demonstrate the good performance of the proposed algorithms for solving two vertical learning problems in machine learning over a multi-agent network.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据