A Flocking-based Approach for Distributed Stochastic Optimization

TL;DR

This paper introduces a flocking-inspired distributed stochastic optimization algorithm that reduces noise and improves performance without synchronization, suitable for convex and non-convex problems.

Contribution

It proposes a novel flocking-based scheme for distributed stochastic optimization that requires minimal communication and no synchronization, outperforming centralized methods under certain conditions.

Findings

Flocking approach reduces noise similar to centralized averaging.

Outperforms centralized algorithms when communication overhead is significant.

Encourages diversity to escape local optima in non-convex problems.

Abstract

In recent years, the paradigm of cloud computing has emerged as an architecture for computing that makes use of distributed (networked) computing resources. In this paper, we consider a distributed computing algorithmic scheme for stochastic optimization which relies on modest communication requirements amongst processors and most importantly, does not require synchronization. Specifically, we analyze a scheme with $N>1$ independent threads implementing each a stochastic gradient algorithm. The threads are coupled via a perturbation of the gradient (with attractive and repulsive forces) in a similar manner to mathematical models of flocking, swarming and other group formations found in nature with mild communication requirements. When the objective function is convex, we show that a flocking-like approach for distributed stochastic optimization provides a noise reduction effect similar to that of a centralized stochastic gradient algorithm based upon the average of $N$ gradient samples at each step. The distributed nature of flocking makes it an appealing computational alternative. We show that when the overhead related to the time needed to gather $N$ samples and synchronization is not negligible, the flocking implementation outperforms a centralized stochastic gradient algorithm based upon the average of $N$ gradient samples at each step. When the objective function is not convex, the flocking-based approach seems better suited to escape locally optimal solutions due to the repulsive force which enforces a certain level of diversity in the set of candidate solutions. Here again, we show that the noise reduction effect is similar to that associated to the centralized stochastic gradient algorithm based upon the average of $N$ gradient samples at each step.