Numerical Methods for Kernel Slicing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rux, Nicolaj, Hertrich, Johannes, Neumayer, Sebastian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912645070716928
author Rux, Nicolaj
Hertrich, Johannes
Neumayer, Sebastian
author_facet Rux, Nicolaj
Hertrich, Johannes
Neumayer, Sebastian
contents Kernels are key in machine learning for modeling interactions. Unfortunately, brute-force computation of the related kernel sums scales quadratically with the number of samples. Recent Fourier-slicing methods lead to an improved linear complexity, provided that the kernel can be sliced and its Fourier coefficients are known. To obtain these coefficients, we view the slicing relation as an inverse problem and present two algorithms for their recovery. Extensive numerical experiments demonstrate the speed and accuracy of our methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11478
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Numerical Methods for Kernel Slicing
Rux, Nicolaj
Hertrich, Johannes
Neumayer, Sebastian
Numerical Analysis
65R32, 45Q05
Kernels are key in machine learning for modeling interactions. Unfortunately, brute-force computation of the related kernel sums scales quadratically with the number of samples. Recent Fourier-slicing methods lead to an improved linear complexity, provided that the kernel can be sliced and its Fourier coefficients are known. To obtain these coefficients, we view the slicing relation as an inverse problem and present two algorithms for their recovery. Extensive numerical experiments demonstrate the speed and accuracy of our methods.
title Numerical Methods for Kernel Slicing
topic Numerical Analysis
65R32, 45Q05
url https://arxiv.org/abs/2510.11478