Timezone: »

 
Poster
Neural Flows: Efficient Alternative to Neural ODEs
Marin Biloš · Johanna Sommer · Syama Sundar Rangapuram · Tim Januschowski · Stephan Günnemann

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @
in Poster Session 8 »

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.

Keywords: Deep Learning · Generative Model

Author Information

Marin Biloš (Technical University of Munich)
Johanna Sommer (TU Munich)
Syama Sundar Rangapuram (Amazon Research)
Tim Januschowski (Amazon Research)

- Director Pricing Platform, Zalando SE - Head of Time Series ML at AWS AI

Stephan Günnemann (Technical University of Munich)

More from the Same Authors