Error estimates for DeepOnets: A deep learning framework in infinite dimensions

02/18/2021
by   Samuel Lanthaler, et al.
0

DeepOnets have recently been proposed as a framework for learning nonlinear operators mapping between infinite dimensional Banach spaces. We analyze DeepOnets and prove estimates on the resulting approximation and generalization errors. In particular, we extend the universal approximation property of DeepOnets to include measurable mappings in non-compact spaces. By a decomposition of the error into encoding, approximation and reconstruction errors, we prove both lower and upper bounds on the total error, relating it to the spectral decay properties of the covariance operators, associated with the underlying measures. We derive almost optimal error bounds with very general affine reconstructors and with random sensor locations as well as bounds on the generalization error, using covering number arguments. We illustrate our general framework with four prototypical examples of nonlinear operators, namely those arising in a nonlinear forced ODE, an elliptic PDE with variable coefficients and nonlinear parabolic and hyperbolic PDEs. In all these examples, we prove that DeepOnets break the curse of dimensionality, thus demonstrating the efficient approximation of infinite-dimensional operators with this machine learning framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/15/2021

On universal approximation and error bounds for Fourier Neural Operators

Fourier neural operators (FNOs) have recently been proposed as an effect...
research
06/29/2020

Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs

Physics informed neural networks (PINNs) have recently been widely used ...
research
01/11/2020

Prediction with eventual almost sure guarantees

We study the problem of predicting the properties of a probabilistic mod...
research
03/28/2023

Operator learning with PCA-Net: upper and lower complexity bounds

PCA-Net is a recently proposed neural operator architecture which combin...
research
01/01/2022

Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces

Learning operators between infinitely dimensional spaces is an important...
research
06/06/2019

A Look at the Effect of Sample Design on Generalization through the Lens of Spectral Analysis

This paper provides a general framework to study the effect of sampling ...
research
10/12/2021

Computing semigroups with error control

We develop an algorithm that computes strongly continuous semigroups on ...

Please sign up or login with your details

Forgot password? Click here to reset