Thresholding Bandit for Dose-ranging: The Impact of Monotonicity
Statistics Theory
2018-07-25 v2 Machine Learning
Statistics Theory
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 and any -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.
Cite
@article{arxiv.1711.04454,
title = {Thresholding Bandit for Dose-ranging: The Impact of Monotonicity},
author = {Aurélien Garivier and Pierre Ménard and Laurent Rossi and Pierre Menard},
journal= {arXiv preprint arXiv:1711.04454},
year = {2018}
}