Adaptive multi-fidelity optimization with fast learning rates - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Adaptive multi-fidelity optimization with fast learning rates

Michal Valko

Résumé

In multi-fidelity optimization, we have access to biased approximations of varying costs of the target function. In this work, we study the setting of optimizing a locally smooth function with a limited budget Λ, where the learner has to make a trade-off between the cost and the bias of these approximations. We first prove lower bounds for the simple regret under different assumptions on the fidelities, based on a cost-to-bias function. We then present the Kometo algorithm which achieves, with additional logarithmic factors, the same rates without any knowledge of the function smoothness and fidelity assumptions and improving prior results. Finally, we empirically show that our algorithm outperforms prior multi-fidelity optimization methods without the knowledge of problem-dependent parameters.
Fichier principal
Vignette du fichier
fiegel2020adaptive.pdf (1.31 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03288879 , version 1 (16-07-2021)

Identifiants

  • HAL Id : hal-03288879 , version 1

Citer

Côme Fiegel, Victor Gabillon, Michal Valko. Adaptive multi-fidelity optimization with fast learning rates. International Conference on Artificial Intelligence and Statistics, 2020, Palermo, Italy. ⟨hal-03288879⟩
71 Consultations
63 Téléchargements

Partager

Gmail Facebook X LinkedIn More