Variationally Informed Parameterization

[ferrine]

This PR adds a tool to autoparameterize your model in the following way: https://arxiv.org/abs/1906.03028

The intended api is like this

You need to convert tour model to change its structure

Then you use your samplers

For stability, you might want to turn on clipping for lambdas

[ferrine]

Anything else I should do in this PR?

[ricardoV94]

Content looks good. Perhaps add an entry on the docs (we have to start introducing headers and sections though)

[ricardoV94]

Oh and a copy pastable example in the docstrings?

[ferrine]

Ah, sure, docs are needed

[ferrine]

@ricardoV94 this is failing for some unknown reason

[ricardoV94]

@ricardoV94 this is failing for some unknown reason

I think a rewrite from the most recent PyTensor is leading to an error in the R2D2 prior tests. Either a rewrite bug or an issue with the R2D2. Will have to investigate

[ricardoV94]

Ah seems to be just a warning probably by numpy when doing something with -inf... Have to check if it's inoffensive and just ignore/catch it in the test

[ferrine]

@ricardoV94 what are the next steps?

[ricardoV94]

Need to check why the warning is being triggered and see if it can be safely ignored

[ferrine]

it should be all good now