Certified Multi-Fidelity Zeroth-Order Optimization - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Certified Multi-Fidelity Zeroth-Order Optimization

Résumé

We consider the problem of multi-fidelity zeroth-order optimization, where one can evaluate a function $f$ at various approximation levels (of varying costs), and the goal is to optimize $f$ with the cheapest evaluations possible. In this paper, we study \emph{certified} algorithms, which are additionally required to output a data-driven upper bound on the optimization error. We first formalize the problem in terms of a min-max game between an algorithm and an evaluation environment. We then propose a certified variant of the MFDOO algorithm and derive a bound on its cost complexity for any Lipschitz function $f$. We also prove an $f$-dependent lower bound showing that this algorithm has a near-optimal cost complexity. We close the paper by addressing the special case of noisy (stochastic) evaluations as a direct example.
Fichier principal
Vignette du fichier
main.pdf (406.65 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04174484 , version 1 (01-08-2023)

Identifiants

Citer

Étienne de Montbrun, Sébastien Gerchinovitz. Certified Multi-Fidelity Zeroth-Order Optimization. 2023. ⟨hal-04174484⟩
83 Consultations
30 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More