Adaptive black-box optimization got easier: HCT only needs local smoothness

Shang, Xuedong; Kaufmann, Emilie; Valko, Michal

Document type :

Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes

Title :

Adaptive black-box optimization got easier: HCT only needs local smoothness

Author(s) :

Shang, Xuedong [Auteur]
Sequential Learning [SEQUEL]
Kaufmann, Emilie [Auteur]

Sequential Learning [SEQUEL]
Valko, Michal [Auteur]

Sequential Learning [SEQUEL]

Conference title :

European Workshop on Reinforcement Learning

City :

Lille

Country :

France

Start date of the conference :

2018-10-01

Publication date :

2018

English keyword(s) :

continuously-armed bandits
global optimization
black-box optimization

HAL domain(s) :

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

English abstract : [en]

Hierarchical bandits is an approach for global optimization of extremely irregular functions. This paper provides new elements regarding POO, an adaptive meta-algorithm that does not require the knowledge of local smoothness ...
Show more >Hierarchical bandits is an approach for global optimization of extremely irregular functions. This paper provides new elements regarding POO, an adaptive meta-algorithm that does not require the knowledge of local smoothness of the target function. We first highlight the fact that the subroutine algorithm used in POO should have a small regret under the assumption of local smoothness with respect to the chosen partitioning, which is unknown if it is satisfied by the standard subroutine HOO. In this work, we establish such regret guarantee for HCT, which is another hierarchical optimistic optimization algorithm that needs to know the smoothness. This confirms the validity of POO. We show that POO can be used with HCT as a subroutine with a regret upper bound that matches the one of best-known algorithms using the knowledge of smoothness up to a √ log n factor.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Inférence bayésienne à ressources limitées - données massives et modèles coûteux
BANDITS MANCHOTS POUR SIGNAUX NON-STATIONNAIRES ET STRUCTURES
Extraction et transfert de connaissances dans l'apprentissage par renforcement

Collections :