Inference for Delay Differential Equations Using Manifold-Constrained Gaussian Processes

TL;DR

This paper introduces a Bayesian Gaussian process approach to infer unknown parameters, including delays, in delay differential equations from noisy, sparse data, overcoming challenges of existing methods that require numerical solvers.

Contribution

We extend manifold-constrained Gaussian processes for DDE parameter inference, enabling delay estimation without numerical solvers and providing theoretical error bounds.

Findings

Effective inference demonstrated on Hutchinson's equation and lac operon system

Successful application to Ontario COVID-19 data

Method outperforms existing approaches in accuracy and efficiency

Abstract

Dynamic systems described by differential equations often involve feedback among system components. When there are time delays for components to sense and respond to feedback, delay differential equation (DDE) models are commonly used. This paper considers the problem of inferring unknown system parameters, including the time delays, from noisy and sparse experimental data observed from the system. We propose an extension of manifold-constrained Gaussian processes to conduct parameter inference for DDEs, whereas the time delay parameters have posed a challenge for existing methods that bypass numerical solvers. Our method uses a Bayesian framework to impose a Gaussian process model over the system trajectory, conditioned on the manifold constraint that satisfies the DDEs. For efficient computation, a linear interpolation scheme is developed to approximate the values of the time-delayed system outputs, along with corresponding theoretical error bounds on the approximated derivatives. Two simulation examples, based on Hutchinson's equation and the lac operon system, together with a real-world application using Ontario COVID-19 data, are used to illustrate the efficacy of our method.