Neural Controlled Differential Equations for Irregular Time Series

Patrick Kidger, James Morrill, James Foster, Terry Lyons

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding


Neural ordinary differential equations are an attractive option for modelling temporal dynamics. However, a fundamental issue is that the solution to an ordinary differential equation is determined by its initial condition, and there is no mechanism for adjusting the trajectory based on subsequent observations. Here, we demonstrate how this may be resolved through the well-understood mathematics of \emph{controlled differential equations}. The resulting \emph{neural controlled differential equation} model is directly applicable to the general setting of partially-observed irregularly-sampled multivariate time series, and (unlike previous work on this problem) it may utilise memory-efficient adjoint-based backpropagation even across observations. We demonstrate that our model achieves state-of-the-art performance against similar (ODE or RNN based) models in empirical studies on a range of datasets. Finally we provide theoretical results demonstrating universal approximation, and that our model subsumes alternative ODE models.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 33
Subtitle of host publicationNeurIPS 2020
PublisherNeurIPS Proceedings
Publication statusPublished - 6 Dec 2020
Externally publishedYes
EventNeurIPS 2020: Conference on Neural Information Processing Systems -
Duration: 6 Dec 202012 Dec 2020


ConferenceNeurIPS 2020: Conference on Neural Information Processing Systems


Dive into the research topics of 'Neural Controlled Differential Equations for Irregular Time Series'. Together they form a unique fingerprint.

Cite this