Communication Dans Un Congrès Année : 2020

Gamification of pure exploration for linear bandits

Résumé

We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist for standard multi-arm bandits, the existence of such algorithms for the best-arm identification in linear bandits has been elusive despite several attempts to address it. First, we provide a thorough comparison and new insight over different notions of optimality in the linear case, including G-optimality, transductive optimality from optimal experimental designand asymptotic optimality. Second, we design the first asymptotically optimal algorithm for fixed-confidence pure exploration in linear bandits. As a consequence, our algorithm naturally bypasses the pitfall caused by a simple but difficult instance, that most prior algorithms had to be engineered to deal with explicitly. Finally, we avoid the need to fully solve an optimal design problem by providing an approach that entails an efficient implementation.

Fichier principal
Vignette du fichier
supp.pdf (792.27 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02884330 , version 1 (29-06-2020)

Licence

Identifiants

  • HAL Id : hal-02884330 , version 1

Citer

Rémy Degenne, Pierre Ménard, Xuedong Shang, Michal Valko. Gamification of pure exploration for linear bandits. ICML 2020 - International Conference on Machine Learning, Aug 2020, Vienna / Virtual, Austria. ⟨hal-02884330⟩
2327 Consultations
494 Téléchargements

Partager

  • More