undark-lab
support dependent priors
This is done within dynesty in the following manner: https://dynesty.readthedocs.io/en/latest/quickstart.html#example-conditional-priors
It's a bit more complicated for us to do this because we have to consider marginalizing over them.
For inspiration, consider the dynesty implementation of Priors.
We need to be able to collect several distributions together for a prior, including dependent ones... but still have access to cdf, icdf, and log_prob at a minimum.
One option is to require that new distributions subclass pytorch distribution, but that seems a bit excessive to me.
In v0.4 hierarchical models with dependent priors can be straightforwardly implemented.
