Bandit Pareto Set Identification: the Fixed Budget Setting

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kone, Cyrille, Kaufmann, Emilie, Richert, Laura
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913646909587456
author Kone, Cyrille
Kaufmann, Emilie
Richert, Laura
author_facet Kone, Cyrille
Kaufmann, Emilie
Richert, Laura
contents We study a multi-objective pure exploration problem in a multi-armed bandit model. Each arm is associated to an unknown multi-variate distribution and the goal is to identify the distributions whose mean is not uniformly worse than that of another distribution: the Pareto optimal set. We propose and analyze the first algorithms for the \emph{fixed budget} Pareto Set Identification task. We propose Empirical Gap Elimination, a family of algorithms combining a careful estimation of the ``hardness to classify'' each arm in or out of the Pareto set with a generic elimination scheme. We prove that two particular instances, EGE-SR and EGE-SH, have a probability of error that decays exponentially fast with the budget, with an exponent supported by an information theoretic lower-bound. We complement these findings with an empirical study using real-world and synthetic datasets, which showcase the good performance of our algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2311_03992
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bandit Pareto Set Identification: the Fixed Budget Setting
Kone, Cyrille
Kaufmann, Emilie
Richert, Laura
Machine Learning
We study a multi-objective pure exploration problem in a multi-armed bandit model. Each arm is associated to an unknown multi-variate distribution and the goal is to identify the distributions whose mean is not uniformly worse than that of another distribution: the Pareto optimal set. We propose and analyze the first algorithms for the \emph{fixed budget} Pareto Set Identification task. We propose Empirical Gap Elimination, a family of algorithms combining a careful estimation of the ``hardness to classify'' each arm in or out of the Pareto set with a generic elimination scheme. We prove that two particular instances, EGE-SR and EGE-SH, have a probability of error that decays exponentially fast with the budget, with an exponent supported by an information theoretic lower-bound. We complement these findings with an empirical study using real-world and synthetic datasets, which showcase the good performance of our algorithms.
title Bandit Pareto Set Identification: the Fixed Budget Setting
topic Machine Learning
url https://arxiv.org/abs/2311.03992