Communication Dans Un Congrès Année : 2024

Bandit Pareto Set Identification: the Fixed Budget Setting

Résumé

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.

Domaines

Autres [stat.ML]
Fichier principal
Vignette du fichier
KKR24.pdf (792.15 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

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

Licence

Identifiants

Citer

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

Altmetric

Partager

More