An extension of Mercer theorem to matrix-valued measurable kernels

DOI10.1016/J.ACHA.2012.06.001zbMATH Open1283.46018arXiv1110.4017OpenAlexW2014857453MaRDI QIDQ1948593FDOQ1948593

Authors: Ernesto De Vito, Veronica Umanità, Silvia Villa 

Publication date: 24 April 2013

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Abstract: We extend the classical Mercer theorem to reproducing kernel Hilbert spaces whose elements are functions from a measurable space $X$into $mathbb{C}^n$. Given a finite measure $mu$ on $X$, we represent the reproducing kernel $K$ as convergent series in terms of the eigenfunctions of a suitable compact operator depending on $K$ and $mu$. Our result holds under the mild assumption that $K$ is measurable and the associated Hilbert space is separable. Furthermore, we show that $X$ has a natural second countable topology with respect to which the eigenfunctions are continuous and the series representing $K$ uniformly converges to $K$ on any compact subsets of $XimesX$, provided that the support of $mu$ is $X$.

Full work available at URL: https://arxiv.org/abs/1110.4017

Recommendations

• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• An extension of Mercer's theorem via Pontryagin spaces
• Mercer theorem for RKHS on noncompact sets
• Weighted \(p\)-regular kernels for reproducing kernel Hilbert spaces and Mercer theorem

zbMATH Keywords

eigenvaluesreproducing kernel Hilbert spacesintegral operatorsstatistical learning theory

Mathematics Subject Classification ID

Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Linear operators in reproducing-kernel Hilbert spaces (including de Branges, de Branges-Rovnyak, and other structured spaces) (47B32)

Cited In (17)

• Weighted \(p\)-regular kernels for reproducing kernel Hilbert spaces and Mercer theorem
• Multi-task learning in vector-valued reproducing kernel Banach spaces with the \(\ell^1\) norm
• Distributed learning with indefinite kernels
• Small scale CLTs for the nodal length of monochromatic waves
• Distributed learning with regularized least squares
• Separability of reproducing kernel spaces
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Experimental design for nonparametric correction of misspecified dynamical models
• Mercer theorem for RKHS on noncompact sets
• An extension of Mercer's theory to \(L^p\)
• An extension of Mercer's theorem via Pontryagin spaces
• The weighted norm for some Mercer kernel matrices
• Graphical Principal Component Analysis of Multivariate Functional Time Series
• Boosted kernel ridge regression: optimal learning rates and early stopping
• Reproducing kernel Hilbert spaces associated with kernels on topological spaces
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• Learning rates of multitask kernel methods

This page was built for publication: An extension of Mercer theorem to matrix-valued measurable kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1948593)