A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

Résumé

This article characterizes the exact asymptotics of random Fourier feature (RFF) regression, in the realistic setting where the number of data samples $n$, their dimension $p$, and the dimension of feature space $N$ are all large and comparable. In this regime, the random RFF Gram matrix no longer converges to the well-known limiting Gaussian kernel matrix (as it does when $N \to \infty$ alone), but it still has a tractable behavior that is captured by our analysis. This analysis also provides accurate estimates of training and test regression errors for large $n,p,N$. Based on these estimates, a precise characterization of two qualitatively different phases of learning, including the phase transition between them, is provided; and the corresponding double descent test error curve is derived from this phase transition behavior. These results do not depend on strong assumptions on the data distribution, and they perfectly match empirical results on real-world data sets.
Fichier principal
Vignette du fichier
main.pdf (436.21 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02971807 , version 1 (19-10-2020)

Identifiants

  • HAL Id : hal-02971807 , version 1

Citer

Zhenyu Liao, Romain Couillet, Michael W Mahoney. A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent. NeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver (virtual), Canada. ⟨hal-02971807⟩
95 Consultations
165 Téléchargements

Partager

Gmail Facebook X LinkedIn More