AISTATS 2021poster22 citations
Top-m identification for linear bandits
Clémence Réda, Emilie Kaufmann, Andrée Delahaye-Duriez
Abstract
Motivated by an application to drug repurposing, we propose the first algorithms to tackle the identification of the m ≥ 1 arms with largest means in a linear bandit model, in the fixed-confidence setting. These algorithms belong to the generic family of Gap-Index Focused Algorithms (GIFA) that we introduce for Top-m identification in linear bandits. We propose a unified analysis of these algorithms, which shows how the use of contexts might decrease the sample complexity. We further validate these algorithms empirically on simulated data and on a simple drug repurposing task.
BibTeX
@InProceedings{pmlr-v130-reda21a,
title = { Top-m identification for linear bandits },
author = {R{\'e}da, Cl{\'e}mence and Kaufmann, Emilie and Delahaye-Duriez, Andr{\'e}e},
booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics},
pages = {1108--1116},
year = {2021},
editor = {Banerjee, Arindam and Fukumizu, Kenji},
volume = {130},
series = {Proceedings of Machine Learning Research},
month = {13--15 Apr},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v130/reda21a/reda21a.pdf},
url = {https://proceedings.mlr.press/v130/reda21a.html},
abstract = { Motivated by an application to drug repurposing, we propose the first algorithms to tackle the identification of the m ≥ 1 arms with largest means in a linear bandit model, in the fixed-confidence setting. These algorithms belong to the generic family of Gap-Index Focused Algorithms (GIFA) that we introduce for Top-m identification in linear bandits. We propose a unified analysis of these algorithms, which shows how the use of contexts might decrease the sample complexity. We further validate these algorithms empirically on simulated data and on a simple drug repurposing task. }
}