On the Existence of a Complexity in Fixed Budget Bandit Identification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

On the Existence of a Complexity in Fixed Budget Bandit Identification

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

Résumé

In fixed budget bandit identification, an algorithm sequentially observes samples from several distributions up to a given final time. It then answers a query about the set of distributions. A good algorithm will have a small probability of error. While that probability decreases exponentially with the final time, the best attainable rate is not known precisely for most identification tasks. We show that if a fixed budget task admits a complexity, defined as a lower bound on the probability of error which is attained by the same algorithm on all bandit problems, then that complexity is determined by the best non-adaptive sampling procedure for that problem. We show that there is no such complexity for several fixed budget identification tasks including Bernoulli best arm identification with two arms: there is no single algorithm that attains everywhere the best possible rate.
Fichier principal
Vignette du fichier
2303.09468.pdf (277.85 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04337726 , version 1 (12-12-2023)

Licence

Identifiants

Citer

Rémy Degenne. On the Existence of a Complexity in Fixed Budget Bandit Identification. Thirty Sixth Conference on Learning Theory, Jul 2023, Bengaluru (Bangalore), India. ⟨hal-04337726⟩
15 Consultations
3 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More