Deep Neural Network Approximation of Composition Functions: with application to PINNs

04/17/2023
by   Chenguang Duan, et al.
0

In this paper, we focus on approximating a natural class of functions that are compositions of smooth functions. Unlike the low-dimensional support assumption on the covariate, we demonstrate that composition functions have an intrinsic sparse structure if we assume each layer in the composition has a small degree of freedom. This fact can alleviate the curse of dimensionality in approximation errors by neural networks. Specifically, by using mathematical induction and the multivariate Faa di Bruno formula, we extend the approximation theory of deep neural networks to the composition functions case. Furthermore, combining recent results on the statistical error of deep learning, we provide a general convergence rate analysis for the PINNs method in solving elliptic equations with compositional solutions. We also present two simple illustrative numerical examples to demonstrate the effect of the intrinsic sparse structure in regression and solving PDEs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/10/2021

Deep Quantile Regression: Mitigating the Curse of Dimensionality Through Composition

This paper considers the problem of nonparametric quantile regression un...
research
01/13/2020

Approximation smooth and sparse functions by deep neural networks without saturation

Constructing neural networks for function approximation is a classical a...
research
03/15/2021

Function approximation by deep neural networks with parameters {0,±1/2, ± 1, 2}

In this paper it is shown that C_β-smooth functions can be approximated ...
research
07/30/2021

Error Analysis of Deep Ritz Methods for Elliptic Equations

Using deep neural networks to solve PDEs has attracted a lot of attentio...
research
02/27/2023

Nonparametric regression for repeated measurements with deep neural networks

Analysis of repeated measurements for a sample of subjects has been inte...
research
12/10/2021

Constant rank factorizations of smooth maps

Sonar systems are frequently used to classify objects at a distance by u...
research
05/01/2023

Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression

We study the properties of differentiable neural networks activated by r...

Please sign up or login with your details

Forgot password? Click here to reset