Indexed Minimum Empirical Divergence for ...
Document type :
Communication dans un congrès avec actes
Title :
Indexed Minimum Empirical Divergence for Unimodal Bandits
Author(s) :
Saber, Hassan [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Ménard, Pierre [Auteur]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Maillard, Odalric Ambrym [Auteur]
Scool [Scool]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Ménard, Pierre [Auteur]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Maillard, Odalric Ambrym [Auteur]
Scool [Scool]
Conference title :
NeurIPS 2021 - International Conference on Neural Information Processing Systems
City :
Virtual-only Conference
Country :
Etats-Unis d'Amérique
Start date of the conference :
2021-12-06
Book title :
NeurIPS 2021 - International Conference on Neural Information Processing Systems
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
Mathématiques [math]/Statistiques [math.ST]
Mathématiques [math]/Optimisation et contrôle [math.OC]
Mathématiques [math]/Statistiques [math.ST]
Mathématiques [math]/Optimisation et contrôle [math.OC]
English abstract : [en]
We consider a multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure. We introduce IMED-UB, a algorithm that optimally exploits the unimodal-structure, ...
Show more >We consider a multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure. We introduce IMED-UB, a algorithm that optimally exploits the unimodal-structure, by adapting to this setting the Indexed Minimum Empirical Divergence (IMED) algorithm introduced by Honda and Takemura [2015]. Owing to our proof technique, we are able to provide a concise finite-time analysis of IMED-UB algorithm. Numerical experiments show that IMED-UB competes with the state-of-the-art algorithms.Show less >
Show more >We consider a multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure. We introduce IMED-UB, a algorithm that optimally exploits the unimodal-structure, by adapting to this setting the Indexed Minimum Empirical Divergence (IMED) algorithm introduced by Honda and Takemura [2015]. Owing to our proof technique, we are able to provide a concise finite-time analysis of IMED-UB algorithm. Numerical experiments show that IMED-UB competes with the state-of-the-art algorithms.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-03446617/document
- Open access
- Access the document
- http://arxiv.org/pdf/2112.01452
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03446617/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03446617/document
- Open access
- Access the document
- document
- Open access
- Access the document
- UnimodalBandits.pdf
- Open access
- Access the document
- 2112.01452
- Open access
- Access the document