Fixed-confidence guarantees for Bayesian best-arm identification

Shang, Xuedong; de Heide, Rianne; Kaufmann, Emilie; Ménard, Pierre; Valko, Michal

Document type :

Communication dans un congrès avec actes

Title :

Fixed-confidence guarantees for Bayesian best-arm identification

Author(s) :

Shang, Xuedong [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Scool [Scool]
de Heide, Rianne [Auteur]
Universiteit Leiden = Leiden University
Centrum Wiskunde & Informatica [CWI]
Kaufmann, Emilie [Auteur]

Sequential Learning [SEQUEL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre National de la Recherche Scientifique [CNRS]
Scool [Scool]
Ménard, Pierre [Auteur]
Sequential Learning [SEQUEL]
Scool [Scool]
Valko, Michal [Auteur]

DeepMind [Paris]

Conference title :

International Conference on Artificial Intelligence and Statistics

City :

Palermo

Country :

Italie

Start date of the conference :

2020

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]

English abstract : [en]

We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification. We further propose a variant of TTTS ...
Show more >We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification. We further propose a variant of TTTS called Top-Two Transportation Cost (T3C), which disposes of the computational burden of TTTS. As our main contribution, we provide the first sample complexity analysis of TTTS and T3C when coupled with a very natural Bayesian stopping rule, for bandits with Gaussian rewards, solving one of the open questions raised by Russo (2016). We also provide new posterior convergence results for TTTS under two models that are commonly used in practice: bandits with Gaussian and Bernoulli rewards and conjugate priors.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

BANDITS MANCHOTS POUR SIGNAUX NON-STATIONNAIRES ET STRUCTURES
Au delà de l'apprentissage séquentiel pour de meilleures prises de décisions

Comment :

Due to COVID-19, the event has been postponed. AISTATS 2020 held online on August 26-28th.