Skip to content

Reliable inference in Bayesian models which require numerical approximations

Notifications You must be signed in to change notification settings

jtimonen/numapprox-is

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

numapprox-is

An importance sampling framework for reliable and efficient inference in Bayesian models that require numerical approximations, such as solutions of implicitly defined functions. Ordinary differential equation (ODE) models are one example.

Experiments

Code for reproducing the experiments of the paper is in the experiments subdirectory. Running them requires the odemodeling R package, which was developed for these experiments. Experiments were run using version 0.2.0 of odemodeling.

References

Timonen, J., Siccha, N., Bales, B., Lähdesmäki, H., & Vehtari, A. (2023). An importance sampling approach for reliable and efficient inference in Bayesian ordinary differential equation models. Stat, 12(1), e614. https://doi.org/10.1002/sta4.614

About

Reliable inference in Bayesian models which require numerical approximations

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages