Skip to Main content Skip to Navigation
Conference papers

Optimal Best Arm Identification with Fixed Confidence

Abstract : 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.
Complete list of metadata

Cited literature [29 references]  Display  Hide  Download
Contributor : Aurélien Garivier Connect in order to contact the contributor
Submitted on : Wednesday, June 1, 2016 - 2:25:34 PM
Last modification on : Wednesday, October 27, 2021 - 12:59:41 PM
Long-term archiving on: : Friday, September 2, 2016 - 10:27:56 AM


Files produced by the author(s)


  • HAL Id : hal-01273838, version 2
  • ARXIV : 1602.04589


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⟩



Record views


Files downloads