Fixed-confidence guarantees for Bayesian best-arm identification - Archive ouverte HAL Access content directly
Conference Papers Year :

Fixed-confidence guarantees for Bayesian best-arm identification

Abstract

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.
Fichier principal
Vignette du fichier
main.pdf (801.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02330187 , version 1 (23-10-2019)
hal-02330187 , version 2 (24-10-2019)

Identifiers

Cite

Xuedong Shang, Rianne de Heide, Emilie Kaufmann, Pierre Ménard, Michal Valko. Fixed-confidence guarantees for Bayesian best-arm identification. International Conference on Artificial Intelligence and Statistics, 2020, Palermo, Italy. ⟨hal-02330187v2⟩
153 View
117 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More