Asymptotic convergence rates for averaging strategies - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Asymptotic convergence rates for averaging strategies

Laurent Meunier
  • Fonction : Auteur
  • PersonId : 1080147
Iskander Legheraba
  • Fonction : Auteur

Résumé

Parallel black box optimization consists in estimating the optimum of a function using $\lambda$ parallel evaluations of $f$. Averaging the $\mu$ best individuals among the $\lambda$ evaluations is known to provide better estimates of the optimum of a function than just picking up the best. In continuous domains, this averaging is typically just based on (possibly weighted) arithmetic means. Previous theoretical results were based on quadratic objective functions. In this paper, we extend the results to a wide class of functions, containing three times continuously differentiable functions with unique optimum. We prove formal rate of convergences and show they are indeed better than pure random search asymptotically in $\lambda$. We validate our theoretical findings with experiments on some standard black box functions.

Dates et versions

hal-03345019 , version 1 (15-09-2021)

Identifiants

Citer

Laurent Meunier, Iskander Legheraba, Yann Chevaleyre, Olivier Teytaud. Asymptotic convergence rates for averaging strategies. 2021. ⟨hal-03345019⟩
36 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More