Irregular Sampling of High-Dimensional Functions in Reproducing Kernel Hilbert Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iske, Armin, Ohlsen, Lennart
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909584169369600
author Iske, Armin
Ohlsen, Lennart
author_facet Iske, Armin
Ohlsen, Lennart
contents We develop sampling formulas for high-dimensional functions in reproducing kernel Hilbert spaces, where we rely on irregular samples that are taken at determining sequences of data points. We place particular emphasis on sampling formulas for tensor product kernels, where we show that determining irregular samples in lower dimensions can be composed to obtain a tensor of determining irregular samples in higher dimensions. This in turn reduces the computational complexity of sampling formulas for high-dimensional functions quite significantly.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Irregular Sampling of High-Dimensional Functions in Reproducing Kernel Hilbert Spaces
Iske, Armin
Ohlsen, Lennart
Machine Learning
Information Theory
We develop sampling formulas for high-dimensional functions in reproducing kernel Hilbert spaces, where we rely on irregular samples that are taken at determining sequences of data points. We place particular emphasis on sampling formulas for tensor product kernels, where we show that determining irregular samples in lower dimensions can be composed to obtain a tensor of determining irregular samples in higher dimensions. This in turn reduces the computational complexity of sampling formulas for high-dimensional functions quite significantly.
title Irregular Sampling of High-Dimensional Functions in Reproducing Kernel Hilbert Spaces
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2504.13543