Conference Papers Year : 2024

Bandit Pareto Set Identification: the Fixed Budget Setting

Abstract

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.
Fichier principal
Vignette du fichier
KKR24.pdf (792.15 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04877368 , version 1 (09-01-2025)

Licence

Identifiers

Cite

Cyrille Kone, Emilie Kaufmann, Laura Richert. Bandit Pareto Set Identification: the Fixed Budget Setting. AISTATS, May 2024, Valencia (Espagne), Spain. ⟨hal-04877368⟩
0 View
0 Download

Altmetric

Share

More