Smoothed discrepancy principle as an early stopping rule in RKHS - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Smoothed discrepancy principle as an early stopping rule in RKHS

Résumé

In this paper we work on the estimation of a regression function that belongs to a polynomial decay reproducing kernel Hilbert space (RKHS). We describe spectral filter framework for our estimator that allows us to deal with several iterative algorithms: gradient descent, Tikhonov regularization, etc. The main goal of the paper is to propose a new early stopping rule by introducing smoothing parameter for empirical risk of the estimator in order to improve the previous results [1] on discrepancy principle. Theoretical justifications as well as simulations experiments for the proposed rule are provided.
Fichier principal
Vignette du fichier
sfds19.pdf (256.67 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02427696 , version 1 (03-01-2020)
hal-02427696 , version 2 (30-07-2020)
hal-02427696 , version 3 (24-08-2020)

Identifiants

  • HAL Id : hal-02427696 , version 1

Citer

Yaroslav Averyanov, Alain A. Celisse. Smoothed discrepancy principle as an early stopping rule in RKHS. 51es Journées de Statistique, Jun 2019, Nancy, France. ⟨hal-02427696v1⟩
221 Consultations
162 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More