PreprintarXiv licencearXiv
Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
Abstract
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 symmetric positive-definite function. In the Gaussian case, we characterize those functions that arise from covariance operators in terms of γ-radonifying operators. Building on these results, we extend Driscoll's theorem to the reproducing kernel Banach space setting.
Related
- Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
- New hierarchical matrices for fast kernel matrix-vector products with Applications to Gaussian processes and kernel ridge regression
- The strong reproducing kernel thesis for Hankel operators and the Garsia norm
- Norm-optimal model order reduction in reproducing kernel Hilbert spaces
- Multiplicative linear functionals on reproducing kernel Hilbert spaces
BibTeX
@misc{karvonen2026gaussian,
title = {{Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces}},
author = {Toni Karvonen and Rasmus Kleist Hørlyck Sørensen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.28106},
eprint = {2605.28106},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.28106},
}
RIS
TY - UNPB
TI - Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
AU - Toni Karvonen
AU - Rasmus Kleist Hørlyck Sørensen
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2605.28106
UR - https://arxiv.org/abs/2605.28106
AB - 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 symmetric positive-definite function. In the Gaussian case, we characterize those functions that arise from covariance operators in terms of γ-radonifying operators. Building on these results, we extend Driscoll's theorem to the reproducing kernel Banach space setting.
ER -