Optimal Best Arm Identification with Fixed Confidence - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Optimal Best Arm Identification with Fixed Confidence


We give a complete characterization of the complexity of best-arm identification in one-parameter bandit problems. We prove a new, tight lower bound on the sample complexity. We propose the `Track-and-Stop' strategy, which we prove to be asymptotically optimal. It consists in a new sampling rule (which tracks the optimal proportions of arm draws highlighted by the lower bound) and in a stopping rule named after Chernoff, for which we give a new analysis.
Fichier principal
Vignette du fichier
MDLBAI.pdf (323.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01273838 , version 1 (14-02-2016)
hal-01273838 , version 2 (01-06-2016)



Aurélien Garivier, Emilie Kaufmann. Optimal Best Arm Identification with Fixed Confidence. 29th Annual Conference on Learning Theory (COLT), Jun 2016, New York, United States. ⟨hal-01273838v2⟩
669 View
342 Download



Gmail Facebook X LinkedIn More