Neural Flows: Efficient Alternative to Neural ODEs

Author name not available (Why is that?)

Publication date: 25 October 2021

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.

Has companion code repository: https://github.com/mbilos/neural-flows-experiments

This page was built for publication: Neural Flows: Efficient Alternative to Neural ODEs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6381221)