Bayesian Inference for High-Dimensional ODE Models with Time-Varying Parameters via Relaxation

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Ordinary differential equation (ODE) models are widely used to analyze real-world data. However, they can be challenging to apply to high-dimensional problems with time-varying parameters. This paper introduces a relaxation technique for Bayesian inference of a high-dimensional ODE model resulting from incorporating time-varying parameters. The relaxation technique ensures reliable parameter estimation by enhancing efficiency and computational speed of the associated Bayesian inference algorithm. We demonstrate our developed methodology for the SEIRV (Susceptible-Exposed-Infected-Recovered-Vaccinated) epidemic model using Malaysian COVID-19 data. Since the SEIRV model is analytically intractable, Bayesian inference entails the development of a computational algorithm for obtaining samples from the posterior distribution on unknown parameters. The maximum-a-posteriori (MAP) estimate is shown to perform particularly well in terms of matching the observed disease trajectories. Furthermore, we develop model validation via predictive distributions and highlight the advantages of a data-driven strategy for optimizing prior hyperparameters.
Original languageEnglish
Title of host publication11th IEEE Conference on Systems, Process & Control (ICSPC)
Number of pages6
ISBN (Electronic)9798350340860
Publication statusPublished - 15 Feb 2024
Event11th IEEE Conference on Systems, Process & Control 2023 - Malacca, Malaysia
Duration: 16 Dec 2023 → …


Conference11th IEEE Conference on Systems, Process & Control 2023
Abbreviated titleICSPC 2023
Period16/12/23 → …


  • Bayesian Inference
  • COVID-19
  • Gibbs Sampling
  • Malaysia
  • Metropolis-Hastings algorithm
  • Ordinary differential equation (ODE) modelling
  • Relaxation

ASJC Scopus subject areas

  • Information Systems and Management
  • Artificial Intelligence
  • Control and Optimization
  • Information Systems
  • Safety, Risk, Reliability and Quality
  • Education
  • Computer Science Applications
  • Modelling and Simulation


Dive into the research topics of 'Bayesian Inference for High-Dimensional ODE Models with Time-Varying Parameters via Relaxation'. Together they form a unique fingerprint.

Cite this