DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2020-05-20 - Article/Compte-rendu - Anglais - 13 page(s)

Ndjia Njike Boris Edgar , Siebert Xavier , "Nonparametric adaptive active learning under local smoothness condition" in arXiv preprint arXiv:2102.11077, 2021.

  • Codes CREF : Intelligence artificielle (DI1180)
Texte intégral :

Abstract(s) :

(Anglais) Active learning is typically used to label data, when the labeling process is expensive. Several active learning algorithms have been theoretically proved to perform better than their passive counterpart. However, these algorithms rely on some assumptions, which themselves contain some specic parameters. This paper adresses the problem of adaptive active learning in a nonparametric setting with minimal assumptions. We present a novel algorithm that is valid under more general assumptions than the previously known algorithms, and that can moreover adapt to the parameters used in these assumptions. This allows us to work with a larger class of distributions, thereby avoiding to exclude important densities like gaussians. Our algorithm achieves a minimax rate of convergence, and therefore performs almost as well as the best known non-adaptive algorithms.


Mots-clés :
  • (Anglais) Active learning