Guardado en:
Detalles Bibliográficos
Autor principal: Glasmachers, Tobias
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.10987
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909612426395648
author Glasmachers, Tobias
author_facet Glasmachers, Tobias
contents We present a hybrid algorithm between an evolution strategy and a quasi Newton method. The design is based on the Hessian Estimation Evolution Strategy, which iteratively estimates the inverse square root of the Hessian matrix of the problem. This is akin to a quasi-Newton method and corresponding derivative-free trust-region algorithms like NEWUOA. The proposed method therefore replaces the global recombination step commonly found in non-elitist evolution strategies with a quasi-Newton step. Numerical results show superlinear convergence, resulting in improved performance in particular on smooth convex problems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10987
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Superlinearly Convergent Evolution Strategy
Glasmachers, Tobias
Optimization and Control
Neural and Evolutionary Computing
We present a hybrid algorithm between an evolution strategy and a quasi Newton method. The design is based on the Hessian Estimation Evolution Strategy, which iteratively estimates the inverse square root of the Hessian matrix of the problem. This is akin to a quasi-Newton method and corresponding derivative-free trust-region algorithms like NEWUOA. The proposed method therefore replaces the global recombination step commonly found in non-elitist evolution strategies with a quasi-Newton step. Numerical results show superlinear convergence, resulting in improved performance in particular on smooth convex problems.
title A Superlinearly Convergent Evolution Strategy
topic Optimization and Control
Neural and Evolutionary Computing
url https://arxiv.org/abs/2505.10987