Neural Controlled Differential Equations for Irregular Time Series
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Structural functional identifiability and model discovery in differential equation models
Extends structural identifiability analysis to functional components of differential equation models and characterizes conditions for unique recovery using differential algebra techniques.
-
Efficiently Modeling Long Sequences with Structured State Spaces
S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while bei...
-
Universal Differential Equations for Scientific Machine Learning
Universal Differential Equations unify scientific models with machine learning by embedding flexible approximators into differential equations, enabling applications from biological mechanism discovery to high-dimensi...
-
Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting
A Latent NCDE-based continuous-time probabilistic corrector wrapped around deterministic physics propagators like GMAT improves forecast accuracy and produces sharp calibrated full-covariance uncertainty estimates on ...
-
Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS
The paper proposes the ANJD flow and AVNSG operator to generate càdlàg trajectories via sequential MMD-gradient descent in Marcus-signature RKHS with generalisation bounds.
-
Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions
ARL lifts states into signature-augmented manifolds and employs self-consistent proxies of future path-laws to enable deterministic expected-return evaluation while preserving contraction mappings in jump-diffusion en...
-
The hidden risks of temporal resampling in clinical reinforcement learning
Resampling clinical time series into uniform bins for offline RL reduces performance by up to 60% and causes retrospective evaluations to overestimate returns by 1.5-3x versus unprocessed data.
-
Neural CDEs as Correctors for Learned Time Series Models
Neural CDEs serve as correctors that reduce error accumulation in multi-step forecasts from learned time-series models across synthetic, physics, and real-world data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.