MCMC sampler for inference for diffusion processes with the use of Guided Proposals using the package Bridge.jl. Currently under development.
The main function introduced by this package is
It finds the posterior distribution of the unknown parameters given discrete time observations of the underlying process. Please see the documentation (in development).
Use the built-in package manager
using Pkg Pkg.add("BridgeSDEInference")
This package is currently under development, some of the features that are scheduled to be introduced to a package are:
- Gradient based proposals (for parameter and initial state updates)
- Support for mixed-effects models
- GPU support for efficient treatment of high-dimensional examples
- see issue #18 (TODOs) for an up-to-date list of planned tasks
Contributions, issues and feature requests are welcome. Please use issues page if you want to contribute or discuss anything package-related.