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

Abstract

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 bounded 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 bounded 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, feasible point seeking for convex inequalities, and multi-player games under partial-decision information. Finally, numerical examples are presented to corroborate the theoretical results.

A Survey on Distributed Online Optimization and Game

“…Also note that time-varying operator is now only addressed in the centralized manner. Nonetheless, the time-invariant scenario has been taken into account in the decentralized fashion in recent years [62]- [65], leaving the time-varying case as one of future directions.…”