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

TL;DR

This paper introduces two distributed algorithms, DOT and DOP, for finding fixed points of multi-agent operators over directed networks, achieving linear convergence under weaker conditions than traditional methods.

Contribution

The paper proposes novel distributed algorithms, DOT and DOP, with proven linear convergence for fixed point problems in multi-agent networks, extending applicability beyond strong convexity assumptions.

Findings

Both algorithms converge linearly to fixed points.

The methods apply to distributed optimization and multi-player games.

Convergence is achieved under a weaker linear regularity condition.

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 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.