Distributed Coupled Multi-Agent Stochastic Optimization

TL;DR

This paper introduces a distributed stochastic optimization method for multi-agent systems with coupled parameters and local constraints, applicable to various real-world problems like power systems and disease modeling.

Contribution

It proposes a novel coupled diffusion strategy for distributed learning that effectively tracks parameter drifts in stochastic, constrained multi-agent environments.

Findings

Converges linearly to a neighborhood of the optimal solution

Handles coupled parameters with local constraints effectively

Tracks parameter drifts in stochastic settings

Abstract

This work develops effective distributed strategies for the solution of constrained multi-agent stochastic optimization problems with coupled parameters across the agents. In this formulation, each agent is influenced by only a subset of the entries of a global parameter vector or model, and is subject to convex constraints that are only known locally. Problems of this type arise in several applications, most notably in disease propagation models, minimum-cost flow problems, distributed control formulations, and distributed power system monitoring. This work focuses on stochastic settings, where a stochastic risk function is associated with each agent and the objective is to seek the minimizer of the aggregate sum of all risks subject to a set of constraints. Agents are not aware of the statistical distribution of the data and, therefore, can only rely on stochastic approximations in their learning strategies. We derive an effective distributed learning strategy that is able to track drifts in the underlying parameter model. A detailed performance and stability analysis is carried out showing that the resulting coupled diffusion strategy converges at a linear rate to an $O(\mu)-$neighborhood of the true penalized optimizer.