On Kernel Derivative Approximation with Random Fourier Features

Abstract : Random Fourier features (RFF) represent one of the most popular and widespread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applications of RFFs, unfortunately, quite little is understood theoretically on their optimality and limitations of their performance. To the best of our knowledge, the only existing areas where precise statistical-computational trade-offs have been established are approximation of kernel values, kernel ridge regression, and kernel principal component analysis. Our goal is to spark the investigation of optimality of RFF-based approximations in tasks involving not only function values but derivatives, which naturally lead to optimization problems with kernel derivatives. Particularly, in this paper, we focus on the approximation quality of RFFs for kernel derivatives and prove that the existing finite-sample guarantees can be improved exponentially in terms of the domain where they hold, using recent tools from unbounded empirical process theory. Our result implies that the same approximation guarantee is achievable for kernel derivatives using RFF as for kernel values.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

Contributeur : Zoltan Szabo <>
Soumis le : vendredi 2 novembre 2018 - 22:11:59
Dernière modification le : mercredi 14 novembre 2018 - 01:12:21


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01897996, version 2


Zoltán Szabó, Bharath Sriperumbudur. On Kernel Derivative Approximation with Random Fourier Features. 2018. 〈hal-01897996v2〉