An ε-Best-Arm Identification Algorithm for ...
Document type :
Communication dans un congrès avec actes
Title :
An ε-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
Author(s) :
Jourdan, Marc [Auteur]
Scool [Scool]
Degenne, Rémy [Auteur]
Scool [Scool]
Kaufmann, Emilie [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Degenne, Rémy [Auteur]
Scool [Scool]
Kaufmann, Emilie [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Conference title :
Advances in Neural Information Processing Systems (NeurIPS)
City :
New Orleans
Country :
Etats-Unis d'Amérique
Start date of the conference :
2023-12-10
HAL domain(s) :
Statistiques [stat]/Autres [stat.ML]
English abstract : [en]
We propose EB-TC ε , a novel sampling rule for ε-best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TC ε is an anytime sampling ...
Show more >We propose EB-TC ε , a novel sampling rule for ε-best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TC ε is an anytime sampling rule that can therefore be employed without modification for fixed confidence or fixed budget identification (without prior knowledge of the budget). We provide three types of theoretical guarantees for EB-TC ε. First, we prove bounds on its expected sample complexity in the fixed confidence setting, notably showing its asymptotic optimality in combination with an adaptive tuning of its exploration parameter. We complement these findings with upper bounds on its probability of error at any time and for any error parameter, which further yield upper bounds on its simple regret at any time. Finally, we show through numerical simulations that EB-TC ε performs favorably compared to existing algorithms, in different settings.Show less >
Show more >We propose EB-TC ε , a novel sampling rule for ε-best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TC ε is an anytime sampling rule that can therefore be employed without modification for fixed confidence or fixed budget identification (without prior knowledge of the budget). We provide three types of theoretical guarantees for EB-TC ε. First, we prove bounds on its expected sample complexity in the fixed confidence setting, notably showing its asymptotic optimality in combination with an adaptive tuning of its exploration parameter. We complement these findings with upper bounds on its probability of error at any time and for any error parameter, which further yield upper bounds on its simple regret at any time. Finally, we show through numerical simulations that EB-TC ε performs favorably compared to existing algorithms, in different settings.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
ANR Project :
Collections :
Source :
Files
- document
- Open access
- Access the document
- TTeBAI.pdf
- Open access
- Access the document
- 2305.16041
- Open access
- Access the document