On the Global Convergence of Particle Swarm Optimization Methods

TL;DR

This paper rigorously analyzes the convergence of particle swarm optimization using stochastic calculus and PDEs, proving global convergence under certain conditions and demonstrating effectiveness on high-dimensional machine learning benchmarks.

Contribution

It provides the first rigorous convergence proof for PSO using mean-field analysis and stochastic calculus, including convergence rates and conditions for global optimality.

Findings

Proves convergence to global minimizers for nonconvex, nonsmooth functions.

Establishes mean-field approximation accuracy for PSO.

Demonstrates effectiveness on high-dimensional machine learning problems.

Abstract

In this paper we provide a rigorous convergence analysis for the renowned particle swarm optimization method by using tools from stochastic calculus and the analysis of partial differential equations. Based on a time-continuous formulation of the particle dynamics as a system of stochastic differential equations, we establish convergence to a global minimizer of a possibly nonconvex and nonsmooth objective function in two steps. First, we prove consensus formation of an associated mean-field dynamics by analyzing the time-evolution of the variance of the particle distribution. We then show that this consensus is close to a global minimizer by employing the asymptotic Laplace principle and a tractability condition on the energy landscape of the objective function. These results allow for the usage of memory mechanisms, and hold for a rich class of objectives provided certain conditions of well-preparation of the hyperparameters and the initial datum. In a second step, at least for the case without memory effects, we provide a quantitative result about the mean-field approximation of particle swarm optimization, which specifies the convergence of the interacting particle system to the associated mean-field limit. Combining these two results allows for global convergence guarantees of the numerical particle swarm optimization method with provable polynomial complexity. To demonstrate the applicability of the method we propose an efficient and parallelizable implementation, which is tested in particular on a competitive and well-understood high-dimensional benchmark problem in machine learning.