Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits

Résumé

In the fixed budget thresholding bandit problem, an algorithm sequentially allocates a budgeted number of samples to different distributions. It then predicts whether the mean of each distribution is larger or lower than a given threshold. We introduce a large family of algorithms (containing most existing relevant ones), inspired by the Frank-Wolfe algorithm, and provide a thorough yet generic analysis of their performance. This allowed us to construct new explicit algorithms, for a broad class of problems, whose losses are within a small constant factor of the non-adaptive oracle ones. Quite interestingly, we observed that adaptive methods empirically greatly out-perform non-adaptive oracles, an uncommon behavior in standard online learning settings, such as regret minimization. We explain this surprising phenomenon on an insightful toy problem.
Fichier principal
Vignette du fichier
neurips_2021.pdf (626.98 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03363014 , version 1 (04-10-2021)

Identifiants

  • HAL Id : hal-03363014 , version 1

Citer

Reda Ouhamma, Rémy Degenne, Pierre Gaillard, Vianney Perchet. Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits. NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Canada. pp.1-25. ⟨hal-03363014⟩
261 Consultations
170 Téléchargements

Partager

Gmail Facebook X LinkedIn More