Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Karvonen, Toni, Sørensen, Rasmus Kleist Hørlyck
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911723712151552
author Karvonen, Toni
Sørensen, Rasmus Kleist Hørlyck
author_facet Karvonen, Toni
Sørensen, Rasmus Kleist Hørlyck
contents We investigate the connection between Gaussian processes and Gaussian random elements in reproducing kernel Banach spaces. We show that the covariance operator of a weak second-order Radon probability measure on such a space is uniquely determined by a positive definite function. In the Gaussian case, we characterize those positive definite functions that arise from covariance operators in terms of $γ$-radonifying operators. Building on these results, we extend the classical Driscoll theorem to the Banach space setting.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28106
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
Karvonen, Toni
Sørensen, Rasmus Kleist Hørlyck
Probability
Functional Analysis
Machine Learning
We investigate the connection between Gaussian processes and Gaussian random elements in reproducing kernel Banach spaces. We show that the covariance operator of a weak second-order Radon probability measure on such a space is uniquely determined by a positive definite function. In the Gaussian case, we characterize those positive definite functions that arise from covariance operators in terms of $γ$-radonifying operators. Building on these results, we extend the classical Driscoll theorem to the Banach space setting.
title Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
topic Probability
Functional Analysis
Machine Learning
url https://arxiv.org/abs/2605.28106