Adaptive Algorithms for Relaxed Pareto Set ...
Document type :
Communication dans un congrès avec actes
Title :
Adaptive Algorithms for Relaxed Pareto Set Identification
Author(s) :
Kone, Cyrille [Auteur]
Scool [Scool]
Kaufmann, Emilie [Auteur]
Scool [Scool]
Richert, Laura [Auteur]
Statistics In System biology and Translational Medicine [SISTM]
Scool [Scool]
Kaufmann, Emilie [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Scool [Scool]
Richert, Laura [Auteur]
Statistics In System biology and Translational Medicine [SISTM]
Conference title :
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems
City :
La Nouvelle Orléans, LA
Country :
Etats-Unis d'Amérique
Start date of the conference :
2023-12-10
HAL domain(s) :
Statistiques [stat]/Autres [stat.ML]
Computer Science [cs]/Operations Research [math.OC]
Computer Science [cs]/Operations Research [math.OC]
English abstract : [en]
In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model. As the sample complexity to identify the exact Pareto set can be very large, a relaxation ...
Show more >In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model. As the sample complexity to identify the exact Pareto set can be very large, a relaxation allowing to output some additional near-optimal arms has been studied. In this work we also tackle alternative relaxations that allow instead to identify a relevant subset of the Pareto set. Notably, we propose a single sampling strategy, called Adaptive Pareto Exploration, that can be used in conjunction with different stopping rules to take into account different relaxations of the Pareto Set Identification problem. We analyze the sample complexity of these different combinations, quantifying in particular the reduction in sample complexity that occurs when one seeks to identify at most k Pareto optimal arms. We showcase the good practical performance of Adaptive Pareto Exploration on a real-world scenario, in which we adaptively explore several vaccination strategies against Covid-19 in order to find the optimal ones when multiple immunogenicity criteria are taken into account.Show less >
Show more >In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model. As the sample complexity to identify the exact Pareto set can be very large, a relaxation allowing to output some additional near-optimal arms has been studied. In this work we also tackle alternative relaxations that allow instead to identify a relevant subset of the Pareto set. Notably, we propose a single sampling strategy, called Adaptive Pareto Exploration, that can be used in conjunction with different stopping rules to take into account different relaxations of the Pareto Set Identification problem. We analyze the sample complexity of these different combinations, quantifying in particular the reduction in sample complexity that occurs when one seeks to identify at most k Pareto optimal arms. We showcase the good practical performance of Adaptive Pareto Exploration on a real-world scenario, in which we adaptively explore several vaccination strategies against Covid-19 in order to find the optimal ones when multiple immunogenicity criteria are taken into account.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
ANR Project :
Collections :
Source :
Files
- document
- Open access
- Access the document
- KKR23.pdf
- Open access
- Access the document
- 2307.00424
- Open access
- Access the document