TY - GEN
T1 - Neural Flows
T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
AU - Biloš, Marin
AU - Sommer, Johanna
AU - Rangapuram, Syama Sundar
AU - Januschowski, Tim
AU - Günnemann, Stephan
N1 - Publisher Copyright:
© 2021 Neural information processing systems foundation. All rights reserved.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85131786376&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85131786376
T3 - Advances in Neural Information Processing Systems
SP - 21325
EP - 21337
BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
A2 - Ranzato, Marc'Aurelio
A2 - Beygelzimer, Alina
A2 - Dauphin, Yann
A2 - Liang, Percy S.
A2 - Wortman Vaughan, Jenn
PB - Neural information processing systems foundation
Y2 - 6 December 2021 through 14 December 2021
ER -