Neural Conservation Laws: A Divergence-Free Perspective

We investigate the parameterization of deep neural networks that by design satisfy the continuity equation, a fundamental conservation law. This is enabled by the observation that any solution of the continuity equation can be represented as a divergence-free vector field. We hence propose building...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-12
Main Authors: Richter-Powell, Jack, Lipman, Yaron, Chen, Ricky T Q
Format: Article
Language:English
Subjects:
Artificial neural networks
Conservation laws
Continuity equation
Decomposition
Divergence
Fields (mathematics)
Machine learning
Mathematical models
Numerical methods
Parameterization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We investigate the parameterization of deep neural networks that by design satisfy the continuity equation, a fundamental conservation law. This is enabled by the observation that any solution of the continuity equation can be represented as a divergence-free vector field. We hence propose building divergence-free neural networks through the concept of differential forms, and with the aid of automatic differentiation, realize two practical constructions. As a result, we can parameterize pairs of densities and vector fields that always exactly satisfy the continuity equation, foregoing the need for extra penalty methods or expensive numerical simulation. Furthermore, we prove these models are universal and so can be used to represent any divergence-free vector field. Finally, we experimentally validate our approaches by computing neural network-based solutions to fluid equations, solving for the Hodge decomposition, and learning dynamical optimal transport maps.
ISSN:2331-8422