A Low Rank Neural Representation of Entropy Solutions

Abstract

We construct a new representation of entropy solutions to nonlinear scalar conservation laws with a smooth convex flux function in a single spatial dimension. The representation is a generalization of the method of characteristics and posseses a compositional form. While it is a nonlinear representation, the embedded dynamics of the solution in the time variable is linear. This representation is then discretized as a manifold of implicit neural representations where the feedforward neural network architecture has a low rank structure. Finally, we show that the low rank neural representation with a fixed number of layers and a small number of coefficients can approximate any entropy solution regardless of the complexity of the shock topology, while retaining the linearity of the embedded dynamics.

47 pages, 10 figures

References in corpus (15)

• Solving high-dimensional partial differential equations using deep learning
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
• Solving parametric PDE problems with artificial neural networks
• The method of freezing as a new tool for nonlinear reduced basis approximation of parameterized evolution equations
• The Modern Mathematics of Deep Learning
• Operator inference for non-intrusive model reduction with quadratic manifolds
• Generating Random Earthquake Events for PTHA
• Double Greedy Algorithms: Reduced Basis Methods for Transport Dominated Problems
• Approximated Lax Pairs for the Reduced Order Integration of Nonlinear Evolution Equations
• Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
• Nonlinear model reduction on metric spaces. Application to one-dimensional conservative PDEs in Wasserstein spaces
• Dimensional splitting of hyperbolic partial differential equations using the Radon transform
• Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities
• Displacement interpolation using monotone rearrangement
• FastLRNR and Sparse Physics Informed Backpropagation

Cited by in corpus (1)

• FastLRNR and Sparse Physics Informed Backpropagation