Smoothed discrepancy principle as an early ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
Smoothed discrepancy principle as an early stopping rule in RKHS
Author(s) :
Averyanov, Yaroslav [Auteur]
Inria Lille - Nord Europe
Celisse, Alain [Auteur]
Inria Lille - Nord Europe
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Inria Lille - Nord Europe
Celisse, Alain [Auteur]
Inria Lille - Nord Europe
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Conference title :
51es Journées de Statistique
City :
Nancy
Country :
France
Start date of the conference :
2019-06
English keyword(s) :
Non-parametric regression
Regularization
Kernels
Stopping rules
regularization
kernels
stopping rules
Regularization
Kernels
Stopping rules
regularization
kernels
stopping rules
HAL domain(s) :
Statistiques [stat]
Statistiques [stat]/Machine Learning [stat.ML]
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- document
- Open access
- Access the document
- sfds2019-1.pdf
- Open access
- Access the document