A New Function Space from Barron Class and Application to Neural Network Approximation

A New Function Space from Barron Class and Application to Neural Network Approximation

Year:    2022

Author:    Yan Meng, Pingbing Ming

Communications in Computational Physics, Vol. 32 (2022), Iss. 5 : pp. 1361–1400

Abstract

We introduce a new function space, dubbed as the Barron spectrum space, which arises from the target function space for the neural network approximation. We give a Bernstein type sufficient condition for functions in this space, and clarify the embedding among the Barron spectrum space, the Bessel potential space, the Besov space and the Sobolev space. Moreover, the unexpected smoothness and the decaying behavior of the radial functions in the Barron spectrum space have been investigated. As an application, we prove a dimension explicit $L^q$ error bound for the two-layer neural network with the Barron spectrum space as the target function space, the rate is dimension independent.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/cicp.OA-2022-0151

Communications in Computational Physics, Vol. 32 (2022), Iss. 5 : pp. 1361–1400

Published online:    2022-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    40

Keywords:    Fourier transform Besov space Sobolev space radial function neural network.

Author Details

Yan Meng

Pingbing Ming