Depth separation for reduced deep networks in nonlinear model reduction: Distilling shock waves in nonlinear hyperbolic problems

arXiv2007.13977MaRDI QIDQ6345972FDOQ6345972

Authors: Donsub Rim, Luca Venturi, Joan Bruna, Benjamin Peherstorfer 

Publication date: 27 July 2020

Abstract: Classical reduced models are low-rank approximations using a fixed basis designed to achieve dimensionality reduction of large-scale systems. In this work, we introduce reduced deep networks, a generalization of classical reduced models formulated as deep neural networks. We prove depth separation results showing that reduced deep networks approximate solutions of parametrized hyperbolic partial differential equations with approximation error $epsilon$ with $mathcalO(|log(epsilon)|)$ degrees of freedom, even in the nonlinear setting where solutions exhibit shock waves. We also show that classical reduced models achieve exponentially worse approximation rates by establishing lower bounds on the relevant Kolmogorov $N$-widths.

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Numerical solution of discretized equations for initial value and initial-boundary value problems involving PDEs (65M22)

This page was built for publication: Depth separation for reduced deep networks in nonlinear model reduction: Distilling shock waves in nonlinear hyperbolic problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6345972)