Chaos propagation in genetic algorithms: An optimal transport approach
- 11 March 2026
- journal article
- Published by Wiley in Bulletin of the London Mathematical Society
- Vol. 58 (3) , e70333
Abstract
Genetic algorithms are high‐level heuristic optimization methods that enjoy great popularity thanks to their intuitive description, flexibility, and, of course, effectiveness. The optimization procedure is based on the evolution of possible solutions through three mechanisms: selection, mutation, and crossover. In this paper, we look at the algorithm as an interacting particle system and show that it is described by a Boltzmann‐type equation in the many‐particle limit. Specifically, we prove a propagation of chaos result using a technique that leverages the optimal transport formulation of the bounded Lipschitz norm and naturally incorporates the crossover mechanism into the analysis. The convergence admits a rate with respect to the number of particles, corresponding to the optimal rate in the Wasserstein‐1 distance.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Evolutionary optimization of model merging recipesNature Machine Intelligence, 2025
- A review on genetic algorithm: past, present, and futureMultimedia Tools and Applications, 2020
- On Properties of the Generalized Wasserstein DistanceArchive for Rational Mechanics and Analysis, 2016
- Introduction to Evolutionary Computing2015
- On the rate of convergence in Wasserstein distance of the empirical measureProbability Theory and Related Fields, 2014
- Generalized Wasserstein Distance and its Application to Transport Equations with SourceArchive for Rational Mechanics and Analysis, 2013
- Feynman-Kac Formulae2004
- On the convergence of numerical schemes for the Boltzmann equationAnnales de l'Institut Henri Poincaré C, Analyse non linéaire, 2003
- A Moran particle system approximation of Feynman–Kac formulaeStochastic Processes and their Applications, 2000
- On the spatially homogeneous Boltzmann equationAnnales de l'Institut Henri Poincaré C, Analyse non linéaire, 1999