Approximation of RKHS Functionals by Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Tian-Yi, Suh, Namjoon, Cheng, Guang, Huo, Xiaoming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911801554239488
author Zhou, Tian-Yi
Suh, Namjoon
Cheng, Guang
Huo, Xiaoming
author_facet Zhou, Tian-Yi
Suh, Namjoon
Cheng, Guang
Huo, Xiaoming
contents Motivated by the abundance of functional data such as time series and images, there has been a growing interest in integrating such data into neural networks and learning maps from function spaces to R (i.e., functionals). In this paper, we study the approximation of functionals on reproducing kernel Hilbert spaces (RKHS's) using neural networks. We establish the universality of the approximation of functionals on the RKHS's. Specifically, we derive explicit error bounds for those induced by inverse multiquadric, Gaussian, and Sobolev kernels. Moreover, we apply our findings to functional regression, proving that neural networks can accurately approximate the regression maps in generalized functional linear models. Existing works on functional learning require integration-type basis function expansions with a set of pre-specified basis functions. By leveraging the interpolating orthogonal projections in RKHS's, our proposed network is much simpler in that we use point evaluations to replace basis function expansions.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Approximation of RKHS Functionals by Neural Networks
Zhou, Tian-Yi
Suh, Namjoon
Cheng, Guang
Huo, Xiaoming
Machine Learning
Statistics Theory
Motivated by the abundance of functional data such as time series and images, there has been a growing interest in integrating such data into neural networks and learning maps from function spaces to R (i.e., functionals). In this paper, we study the approximation of functionals on reproducing kernel Hilbert spaces (RKHS's) using neural networks. We establish the universality of the approximation of functionals on the RKHS's. Specifically, we derive explicit error bounds for those induced by inverse multiquadric, Gaussian, and Sobolev kernels. Moreover, we apply our findings to functional regression, proving that neural networks can accurately approximate the regression maps in generalized functional linear models. Existing works on functional learning require integration-type basis function expansions with a set of pre-specified basis functions. By leveraging the interpolating orthogonal projections in RKHS's, our proposed network is much simpler in that we use point evaluations to replace basis function expansions.
title Approximation of RKHS Functionals by Neural Networks
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2403.12187