A Recipe for Learning Variably Scaled Kernels via Discontinuous Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Audone, Gianluca, Della Santa, Francesco, Perracchione, Emma, Pieraccini, Sandra
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913847333355520
author Audone, Gianluca
Della Santa, Francesco
Perracchione, Emma
Pieraccini, Sandra
author_facet Audone, Gianluca
Della Santa, Francesco
Perracchione, Emma
Pieraccini, Sandra
contents The efficacy of interpolating via Variably Scaled Kernels (VSKs) is known to be dependent on the definition of a proper scaling function, but no numerical recipes to construct it are available. Previous works suggest that such a function should mimic the target one, but no theoretical evidence is provided. This paper fills both the gaps: it proves that a scaling function reflecting the target one may lead to enhanced approximation accuracy, and it provides a user-independent tool for learning the scaling function by means of Discontinuous Neural Networks ($δ$NN), i.e., NNs able to deal with possible discontinuities. Numerical evidence supports our claims, as it shows that the key features of the target function can be clearly recovered in the learned scaling function.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10651
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Recipe for Learning Variably Scaled Kernels via Discontinuous Neural Networks
Audone, Gianluca
Della Santa, Francesco
Perracchione, Emma
Pieraccini, Sandra
Numerical Analysis
65D15, 1A05, 68Q32
The efficacy of interpolating via Variably Scaled Kernels (VSKs) is known to be dependent on the definition of a proper scaling function, but no numerical recipes to construct it are available. Previous works suggest that such a function should mimic the target one, but no theoretical evidence is provided. This paper fills both the gaps: it proves that a scaling function reflecting the target one may lead to enhanced approximation accuracy, and it provides a user-independent tool for learning the scaling function by means of Discontinuous Neural Networks ($δ$NN), i.e., NNs able to deal with possible discontinuities. Numerical evidence supports our claims, as it shows that the key features of the target function can be clearly recovered in the learned scaling function.
title A Recipe for Learning Variably Scaled Kernels via Discontinuous Neural Networks
topic Numerical Analysis
65D15, 1A05, 68Q32
url https://arxiv.org/abs/2407.10651