Skip to content

Code for utilising VAE as means of doing exact MCMC inference in complex high-dimensional space

License

Notifications You must be signed in to change notification settings

MLGlobalHealth/pi-vae

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

πVAE

Code for utilising VAE as means of doing exact MCMC inference in complex high-dimensional space.

Accompanying paper is πVAE: a stochastic process prior for Bayesian deep learning with MCMC

The πVAE model has 2 parts :

  1. Learning / encoding a stochastic prior via a VAE.
  2. Then using the learnt basis, and decoder network , perform inference on our data to get a posterior.

To run the code :

  1. Run src_py/models/pi_vae.py . To choose the the type of prior learnt, modify the training dataset, the current default is 1D GP.
  2. To perform inference using stan, use the file notebooks/pivae.stan by passing the model parameters learnt in the above step. An example is given in the notebooks, notebooks/pivae.stan and notebooks/run_monotonic_mcmc.ipynb

About

Code for utilising VAE as means of doing exact MCMC inference in complex high-dimensional space

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •