On Fast Leverage Score Sampling and Optimal Learning
Résumé
Leverage score sampling provides an appealing way to perform approximate computations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adapted to the problem at hand. Yet, performing leverage scores sampling is a challenge in its own right requiring further approximations. In this paper, we study the problem of leverage score sampling for positive definite matrices defined by a kernel. Our contribution is twofold. First we provide a novel algorithm for leverage score sampling and second, we exploit the proposed method in statistical learning by deriving a novel solver for kernel ridge regression. Our main technical contribution is showing that the proposed algorithms are currently the most efficient and accurate for these problems.
Domaines
Apprentissage [cs.LG]
Fichier principal
BLESS_flattened.pdf (789.2 Ko)
Télécharger le fichier
imgs/HIGGSAUC.pdf (21.75 Ko)
Télécharger le fichier
imgs/RACCLS.pdf (39.96 Ko)
Télécharger le fichier
imgs/SUSYAUC.pdf (21.3 Ko)
Télécharger le fichier
imgs/cerr_vs_lambda.pdf (17.58 Ko)
Télécharger le fichier
imgs/timecomparison.pdf (19.86 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)