General reproducing properties in RKHS with application to derivative and integral operators
Comptes Rendus. Mathématique · 2026-07-27 · 364 (G3) · 549-561
DOI: 10.5802/crmath.847 ↗At a glance
Journal article in Comptes Rendus. Mathématique, published online on 2026-07-27. Written by Fatima-Zahrae El-Boukkouri and 2 co-authors. Cited 1 times so far (Crossref); 19 references.
Abstract (original language)
In this paper, we consider the reproducing property in Reproducing Kernel Hilbert Spaces (RKHS). We establish a reproducing property for the closure of the class of combinations of composition operators under minimal conditions. This allows to revisit the sufficient conditions for the reproducing property to hold for the derivative operator, as well as for the existence of the mean embedding function. These results provide a framework of application of the representer theorem for regularized learning algorithms that involve data for function values, gradients, or any other operator from the considered class.
Cite
APA
El-Boukkouri, F., Garnier, J., & Roustant, O. (2026). General reproducing properties in RKHS with application to derivative and integral operators. Comptes Rendus. Mathématique, 364(G3), 549-561. https://doi.org/10.5802/crmath.847
Vancouver
El-Boukkouri F, Garnier J, Roustant O. General reproducing properties in RKHS with application to derivative and integral operators. Comptes Rendus. Mathématique. 2026;364(G3):549-561. doi:10.5802/crmath.847
BibTeX
@article{ElBoukkouri2026,
author = {El-Boukkouri, Fatima-Zahrae and Garnier, Josselin and Roustant, Olivier},
title = {General reproducing properties in RKHS with application to derivative and integral operators},
journal = {Comptes Rendus. Mathématique},
year = {2026},
volume = {364},
number = {G3},
pages = {549--561},
doi = {10.5802/crmath.847}
}
EUVIMED