Adaptive multi-fidelity optimization with fast learning rates

Fiegel, Côme; Gabillon, Victor; Valko, Michal

Type de document :

Communication dans un congrès avec actes

Titre :

Adaptive multi-fidelity optimization with fast learning rates

Auteur(s) :

Fiegel, Côme [Auteur]
Scool [Scool]
Département d'informatique - ENS-PSL [DI-ENS]
Gabillon, Victor [Auteur]
Huawei R&D [United Kingdom]
Valko, Michal [Auteur]

Titre de la manifestation scientifique :

International Conference on Artificial Intelligence and Statistics

Ville :

Palermo

Pays :

Italie

Date de début de la manifestation scientifique :

2020

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]

Résumé en anglais : [en]

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 ...
Lire la suite >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.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

https://hal.inria.fr/hal-03288879/document
Accès libre
Accéder au document

https://hal.inria.fr/hal-03288879/document
Accès libre
Accéder au document

https://hal.inria.fr/hal-03288879/document
Accès libre
Accéder au document

document
Accès libre
Accéder au document

fiegel2020adaptive.pdf
Accès libre
Accéder au document

document
Accès libre
Accéder au document

fiegel2020adaptive.pdf
Accès libre
Accéder au document

Adaptive multi-fidelity optimization with ... BibTeX CSV Excel RIS

Fichiers

Adaptive multi-fidelity optimization with ...

BibTeX

CSV

Excel

RIS