jeremiecoullon / SGMCMCJax

Lightweight library of stochastic gradient MCMC algorithms written in JAX.
https://sgmcmcjax.readthedocs.io/en/latest/index.html
Apache License 2.0
95 stars 8 forks source link

Documentation: how to add a sampler #5

Closed jeremiecoullon closed 3 years ago

jeremiecoullon commented 3 years ago

Add a section in the docs for how to add a new sampler. This should have 3 steps:

  1. Build the diffusion solver
  2. build the transition kernel
  3. build the sampler
jeremiecoullon commented 3 years ago

Added the main bulk of this.

What's missing now is info on how to use different gradient estimators within new samplers.