Dealing with Unknown Variances in Best-Arm Identification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Dealing with Unknown Variances in Best-Arm Identification

Marc Jourdan
Rémy Degenne
  • Fonction : Auteur
  • PersonId : 748911
  • IdHAL : remydegenne

Résumé

The problem of identifying the best arm among a collection of items having Gaussian rewards distribution is well understood when the variances are known. Despite its practical relevance for many applications, few works studied it for unknown variances. In this paper we introduce and analyze two approaches to deal with unknown variances, either by plugging in the empirical variance or by adapting the transportation costs. In order to calibrate our two stopping rules, we derive new time-uniform concentration inequalities, which are of independent interest. Then, we illustrate the theoretical and empirical performances of our two sampling rule wrappers on Track-and-Stop and on a Top Two algorithm. Moreover, by quantifying the impact on the sample complexity of not knowing the variances, we reveal that it is rather small.

Domaines

Autres [stat.ML]
Fichier principal
Vignette du fichier
BAIUV.pdf (1.87 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04306221 , version 1 (24-11-2023)

Licence

Paternité

Identifiants

Citer

Marc Jourdan, Rémy Degenne, Emilie Kaufmann. Dealing with Unknown Variances in Best-Arm Identification. Algorithmic Learning Theory (ALT), Feb 2023, Singapore (SG), Singapore. ⟨hal-04306221⟩
20 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More