Communication Dans Un Congrès Année : 2025

Constrained Pareto Set Identification with Bandit Feedback

Résumé

In this paper, we address the problem of identifying the Pareto Set under feasibility constraints in a multivariate bandit setting. Specifically, given a K-armed bandit with unknown means in R^d , the goal is to identify the set of arms whose mean is not uniformly worse than that of another arm (i.e., not smaller for all objectives), while satisfying some known set of linear constraints, expressing, for example, some minimal performance on each objective. Our focus lies in fixed-confidence identification, for which we introduce an algorithm that significantly outperforms racing-like algorithms and the intuitive two-stage approach that first identifies feasible arms and then their Pareto Set. We further prove an information-theoretic lower bound on the sample complexity of any algorithm for constrained Pareto Set identification, showing that the sample complexity of our approach is near-optimal. Our theoretical results are supported by an extensive empirical evaluation on a series of benchmarks.

Domaines

Fichier principal
Vignette du fichier
safe_psi_icml25.pdf (786.98 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05125339 , version 1 (23-06-2025)

Licence

Identifiants

Citer

Cyrille Kone, Emilie Kaufmann, Laura Richert. Constrained Pareto Set Identification with Bandit Feedback. ICML 2025 - 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada. ⟨hal-05125339⟩
319 Consultations
130 Téléchargements

Altmetric

Partager

  • More