Neural Flows: Efficient Alternative to Neural ODEs

Marin Biloš, Johanna Sommer, Syama Sundar Rangapuram, Tim Januschowski, Stephan Günnemann

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

31 Zitate (Scopus)

Abstract

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.

OriginalspracheEnglisch
TitelAdvances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Redakteure/-innenMarc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Herausgeber (Verlag)Neural information processing systems foundation
Seiten21325-21337
Seitenumfang13
ISBN (elektronisch)9781713845393
PublikationsstatusVeröffentlicht - 2021
Veranstaltung35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online
Dauer: 6 Dez. 202114 Dez. 2021

Publikationsreihe

NameAdvances in Neural Information Processing Systems
Band26
ISSN (Print)1049-5258

Konferenz

Konferenz35th Conference on Neural Information Processing Systems, NeurIPS 2021
OrtVirtual, Online
Zeitraum6/12/2114/12/21

Fingerprint

Untersuchen Sie die Forschungsthemen von „Neural Flows: Efficient Alternative to Neural ODEs“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren