Faithful global convergence for the rescaled Consensus-Based Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Hui, Kouhkouh, Hicham, Sun, Lukang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909992324431872
author Huang, Hui
Kouhkouh, Hicham
Sun, Lukang
author_facet Huang, Hui
Kouhkouh, Hicham
Sun, Lukang
contents We analyze the Consensus-Based Optimization (CBO) algorithm with a consensus point rescaled by a small fixed parameter $κ\in (0,1)$. Under minimal assumptions on the objective function and the initial data, we establish its unconditional convergence to the global minimizer. Our results hold in the asymptotic regime where both the time--horizon $t \to \infty$ and the inverse--temperature $α\to \infty$, providing a rigorous theoretical foundation for the algorithm's global convergence. Furthermore, our findings extend to the case of multiple and non--discrete set of minimizers.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08578
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Faithful global convergence for the rescaled Consensus-Based Optimization
Huang, Hui
Kouhkouh, Hicham
Sun, Lukang
Optimization and Control
Analysis of PDEs
We analyze the Consensus-Based Optimization (CBO) algorithm with a consensus point rescaled by a small fixed parameter $κ\in (0,1)$. Under minimal assumptions on the objective function and the initial data, we establish its unconditional convergence to the global minimizer. Our results hold in the asymptotic regime where both the time--horizon $t \to \infty$ and the inverse--temperature $α\to \infty$, providing a rigorous theoretical foundation for the algorithm's global convergence. Furthermore, our findings extend to the case of multiple and non--discrete set of minimizers.
title Faithful global convergence for the rescaled Consensus-Based Optimization
topic Optimization and Control
Analysis of PDEs
url https://arxiv.org/abs/2503.08578