arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.06636math.OC
收藏

DOT和DOP:求解多智能体算子不动点的线性收敛算法

DOT and DOP: Linearly Convergent Algorithms for Finding Fixed Points of Multi-Agent Operators

Xiuxian Li, Min Meng, Lihua Xie

摘要:

研究了有向非平衡多智能体网络上全局算子的分布式不动点寻找问题,其中全局算子是拟非扩张的,每个智能体只能部分地访问全局算子.讨论了两种情况,即全局算子是和可分的块可分的。对于第一种情况,全局算子是局部算子的和,假设局部算子是Lipschitz,每个局部算子都是每个个体Agent所私有的。针对这种情况,提出了一种分布式(或分散式)算法,称为分布式拟平均算子跟踪算法(DOT),并对其进行了严格的分析,证明了该算法在线性正则条件下能够以线性速率收敛到全局算子的不动点,这比现有凸优化文献中对费用函数的强凸性假设要弱.对于第二种情况,全局算子由一组局部块算子组成,这些局部块算子是Lipschitz算子,并且只能由每个个体代理访问。在此基础上,提出了一种分布式算法,称为分布式拟平均算子播放算法(DOP),并证明了在线性正则性条件下,该算法线性收敛于全局算子的一个不动点.上述研究问题为许多有趣的问题提供了一个统一的框架。作为例子,建议DOT和DOP被用来处理分布式优化和多人博弈下的部分决策信息。最后,数值例子来证实理论结果。

英文摘要:

This paper investigates the distributed fixed point finding problem for a global operator over a directed and unbalanced multi-agent network, where the global operator is quasinonexpansive and only partially accessible to each individual agent. Two cases are addressed, that is, the global operator is sum separable and block separable. For this first case, the global operator is the sum of local operators, which are assumed to be Lipschitz, and each local operator is privately known to each individual agent. To deal with this scenario, a distributed (or decentralized) algorithm, called Distributed quasi-averaged Operator Tracking algorithm (DOT), is proposed and rigorously analyzed, and it is shown that the algorithm can converge to a fixed point of the global operator at a linear rate under a linear regularity condition, which is strictly weaker than the strong convexity assumption on cost functions in existing convex optimization literature. For the second scenario, the global operator is composed of a group of local block operators which are Lipschitz and can be accessed only by each individual agent. In this setup, a distributed algorithm, called Distributed quasiaveraged Operator Playing algorithm (DOP), is developed and shown to be linearly convergent to a fixed point of the global operator under the linear regularity condition. The above studied problems provide a unified framework for many interesting problems. As examples, the proposed DOT and DOP are exploited to deal with distributed optimization and multi-player games under partial-decision information. Finally, numerical examples are presented to corroborate the theoretical results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑