Top-M Identification for Linear Bandits

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.

Cite

Text

Réda et al. "Top-M Identification for Linear Bandits." Artificial Intelligence and Statistics, 2021.

Markdown

[Réda et al. "Top-M Identification for Linear Bandits." Artificial Intelligence and Statistics, 2021.](https://mlanthology.org/aistats/2021/reda2021aistats-topm/)

BibTeX

@inproceedings{reda2021aistats-topm,
  title     = {{Top-M Identification for Linear Bandits}},
  author    = {Réda, Clémence and Kaufmann, Emilie and Delahaye-Duriez, Andrée},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2021},
  pages     = {1108-1116},
  volume    = {130},
  url       = {https://mlanthology.org/aistats/2021/reda2021aistats-topm/}
}