Deep ReLU neural networks overcome the curse of dimensionality when approximating semilinear partial integro-differential equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Neufeld, Ariel, Nguyen, Tuan Anh, Wu, Sizhou
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909461763850240
author Neufeld, Ariel
Nguyen, Tuan Anh
Wu, Sizhou
author_facet Neufeld, Ariel
Nguyen, Tuan Anh
Wu, Sizhou
contents In this paper we consider PIDEs with gradient-independent Lipschitz continuous nonlinearities and prove that deep neural networks with ReLU activation function can approximate solutions of such semilinear PIDEs without curse of dimensionality in the sense that the required number of parameters in the deep neural networks increases at most polynomially in both the dimension $ d $ of the corresponding PIDE and the reciprocal of the prescribed accuracy $ε$.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15581
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep ReLU neural networks overcome the curse of dimensionality when approximating semilinear partial integro-differential equations
Neufeld, Ariel
Nguyen, Tuan Anh
Wu, Sizhou
Numerical Analysis
Analysis of PDEs
Probability
In this paper we consider PIDEs with gradient-independent Lipschitz continuous nonlinearities and prove that deep neural networks with ReLU activation function can approximate solutions of such semilinear PIDEs without curse of dimensionality in the sense that the required number of parameters in the deep neural networks increases at most polynomially in both the dimension $ d $ of the corresponding PIDE and the reciprocal of the prescribed accuracy $ε$.
title Deep ReLU neural networks overcome the curse of dimensionality when approximating semilinear partial integro-differential equations
topic Numerical Analysis
Analysis of PDEs
Probability
url https://arxiv.org/abs/2310.15581