From the archives

The Complexity of Best-Arm Identification

Historical material. Affiliations, schedules and roles on this page describe their original context.

Context:  Barcelona, FoCM2017

Resume: 

We consider the problem of finding the highest mean among a set of probability distributions that can be sampled sequentially. We provide a complete characterization of the complexity of this task in simple parametric settings: we give a tight lower bound on the sample complexity, and we propose the 'Track-and-Stop' strategy, which we prove to be asymptotically optimal. This algorithm 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.

Slides:  FOCM17_garivier.pdf

Date:  July, 2017

Event url:  Workshop on Stochastic Computation (archive lookup)

Keywords: