Online Nonparametric Learning, Chaining, and the Role of Partial Feedback - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2017

Online Nonparametric Learning, Chaining, and the Role of Partial Feedback

Résumé

We investigate contextual online learning with nonparametric (Lipschitz) comparison classes under different assumptions on losses and feedback information. For full information feedback and Lipschitz losses, we characterize the minimax regret up to log factors by proving an upper bound matching a previously known lower bound. In a partial feedback model motivated by second-price auctions, we prove upper bounds for Lipschitz and semi-Lipschitz losses that improve on the known bounds for standard bandit feedback. Our analysis combines novel results for contextual second-price auctions with a novel algorithmic approach based on chaining. When the context space is Euclidean, our chaining approach is efficient and delivers an even better regret bound.
Fichier principal
Vignette du fichier
NonparametricLearning.pdf (435.22 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01476771 , version 1 (25-02-2017)
hal-01476771 , version 2 (23-06-2017)

Identifiants

Citer

Nicolò Cesa-Bianchi, Pierre Gaillard, Claudio Gentile, Sébastien Gerchinovitz. Online Nonparametric Learning, Chaining, and the Role of Partial Feedback. 2017. ⟨hal-01476771v1⟩
490 Consultations
411 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More