Best-Arm Identification in Unimodal Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Poiani, Riccardo, Jourdan, Marc, Kaufmann, Emilie, Degenne, Rémy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909622727606272
author Poiani, Riccardo
Jourdan, Marc
Kaufmann, Emilie
Degenne, Rémy
author_facet Poiani, Riccardo
Jourdan, Marc
Kaufmann, Emilie
Degenne, Rémy
contents We study the fixed-confidence best-arm identification problem in unimodal bandits, in which the means of the arms increase with the index of the arm up to their maximum, then decrease. We derive two lower bounds on the stopping time of any algorithm. The instance-dependent lower bound suggests that due to the unimodal structure, only three arms contribute to the leading confidence-dependent cost. However, a worst-case lower bound shows that a linear dependence on the number of arms is unavoidable in the confidence-independent cost. We propose modifications of Track-and-Stop and a Top Two algorithm that leverage the unimodal structure. Both versions of Track-and-Stop are asymptotically optimal for one-parameter exponential families. The Top Two algorithm is asymptotically near-optimal for Gaussian distributions and we prove a non-asymptotic guarantee matching the worse-case lower bound. The algorithms can be implemented efficiently and we demonstrate their competitive empirical performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01898
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Best-Arm Identification in Unimodal Bandits
Poiani, Riccardo
Jourdan, Marc
Kaufmann, Emilie
Degenne, Rémy
Machine Learning
Artificial Intelligence
We study the fixed-confidence best-arm identification problem in unimodal bandits, in which the means of the arms increase with the index of the arm up to their maximum, then decrease. We derive two lower bounds on the stopping time of any algorithm. The instance-dependent lower bound suggests that due to the unimodal structure, only three arms contribute to the leading confidence-dependent cost. However, a worst-case lower bound shows that a linear dependence on the number of arms is unavoidable in the confidence-independent cost. We propose modifications of Track-and-Stop and a Top Two algorithm that leverage the unimodal structure. Both versions of Track-and-Stop are asymptotically optimal for one-parameter exponential families. The Top Two algorithm is asymptotically near-optimal for Gaussian distributions and we prove a non-asymptotic guarantee matching the worse-case lower bound. The algorithms can be implemented efficiently and we demonstrate their competitive empirical performance.
title Best-Arm Identification in Unimodal Bandits
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.01898