Neural Flows: Efficient Alternative to Neural ODEs

Neural ordinary differential equations describe how values change in time. This is the reason why they gained importance in modeling sequential data, especially when the observations are made at irregular intervals. In this paper we propose an alternative by directly modeling the solution curves - t...

Full description

Saved in:
Bibliographic Details
Main Authors Biloš, Marin, Sommer, Johanna, Rangapuram, Syama Sundar, Januschowski, Tim, Günnemann, Stephan
Format Journal Article
LanguageEnglish
Published 25.10.2021
Subjects
Computer Science - Learning
Computer Science - Numerical Analysis
Mathematics - Numerical Analysis
Online AccessGet full text

Cover

More Information
Summary:Neural ordinary differential equations describe how values change in time. This is the reason why they gained importance in modeling sequential data, especially when the observations are made at irregular intervals. In this paper we propose an alternative by directly modeling the solution curves - the flow of an ODE - with a neural network. This immediately eliminates the need for expensive numerical solvers while still maintaining the modeling capability of neural ODEs. We propose several flow architectures suitable for different applications by establishing precise conditions on when a function defines a valid flow. Apart from computational efficiency, we also provide empirical evidence of favorable generalization performance via applications in time series modeling, forecasting, and density estimation.
DOI:10.48550/arxiv.2110.13040