Approximation bounds for convolutional neural networks in operator learning

DOI10.1016/J.NEUNET.2023.01.029MaRDI QIDQ6403941zbMATH OpenOpenAlexFDO

Authors Nicola Rares Franco, Stefania Fresca, Andrea Manzoni, Paolo Zunino

Publication date 4 July 2022

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1016/j.neunet.2023.01.029

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical analysis (65-XX) Approximations and expansions (41-XX)

Abstract: Recently, deep Convolutional Neural Networks (CNNs) have proven to be successful when employed in areas such as reduced order modeling of parametrized PDEs. Despite their accuracy and efficiency, the approaches available in the literature still lack a rigorous justification on their mathematical foundations. Motivated by this fact, in this paper we derive rigorous error bounds for the approximation of nonlinear operators by means of CNN models. More precisely, we address the case in which an operator maps a finite dimensional input $$ onto a functional output $$, and a neural network model is used to approximate a discretized version of the input-to-output map. The resulting error estimates provide a clear interpretation of the hyperparameters defining the neural network architecture. All the proofs are constructive, and they ultimately reveal a deep connection between CNNs and the Fourier transform. Finally, we complement the derived error bounds by numerical experiments that illustrate their application.

Cites work

• scientific article; zbMATH DE number 7626805 (Why is no real title available?)
• scientific article; zbMATH DE number 3271087 (Why is no real title available?)
• A Generalization of Hermite's Interpolation Formula
• A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
• A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
• Approximation by superpositions of a sigmoidal function
• Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• Error estimates for DeepONets: a deep learning framework in infinite dimensions
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Numerical approximation of parametrized problems in cardiac electrophysiology by a local reduced basis method
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• Reduced basis methods for partial differential equations. An introduction
• Universality of deep convolutional neural networks

Cited in

(6)

• Application of adjoint operators to neural learning
• Operator learning using random features: a tool for scientific computing
• Improved architectures and training algorithms for deep operator networks
• On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fields
• Application of deep learning reduced-order modeling for single-phase flow in faulted porous media
• On Lipschitz Bounds of General Convolutional Neural Networks

This page was built for publication: Approximation bounds for convolutional neural networks in operator learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6403941)