From the archives

Thresholding Bandit for Dose-ranging: The Impact of Monotonicity

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

Date:  October, 2017

Authors:  Aurélien GarivierPierre MénardLaurent Rossi

Abstract: 

We analyze the sample complexity of the thresholding bandit problem, with and without the assumption that the mean values of the arms are increasing. In each case, we provide a lower bound valid for any risk δ and any δ-correct algorithm; in addition, we propose an algorithm whose sample complexity is of the same order of magnitude for small risks. This work is motivated by phase 1 clinical trials, a practically important setting where the arm means are increasing by nature, and where no satisfactory solution is available so far.

Arxiv Number:  1711.04454

Hal Number:  01629479

Keywords: