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

07/28/2020
by   Donsub Rim, et al.
0

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 ϵ with 𝒪(|log(ϵ)|) 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/31/2019

A Theoretical Analysis of Deep Neural Networks and Parametric PDEs

We derive upper bounds on the complexity of ReLU neural networks approxi...
research
04/30/2021

Model-Order Reduction For Hyperbolic Relaxation Systems

We propose a novel framework for model-order reduction of hyperbolic dif...
research
12/30/2019

Manifold Approximations via Transported Subspaces: Model reduction for transport-dominated problems

This work presents a method for constructing online-efficient reduced mo...
research
07/19/2021

Reduced order models for nonlinear radiative transfer based on moment equations and POD/DMD of Eddington tensor

A new group of reduced-order models (ROMs) for nonlinear thermal radiati...
research
03/22/2022

Learning Operators with Mesh-Informed Neural Networks

Thanks to their universal approximation properties and new efficient tra...
research
12/20/2021

Model order reduction strategies for weakly dispersive waves

We focus on the numerical modelling of water waves by means of depth ave...

Please sign up or login with your details

Forgot password? Click here to reset