Gabriel Stechschulte

KL_VALUES variable in elbo_interactive_plot

1

In the [elbo_interactive_plot.py](https://github.com/GStechschulte/machine-learning-and-simulation/blob/main/english/probabilistic_machine_learning/elbo_interactive_plot.py) script, the values in the variable KL_VALUES were computed using approximate KL-Divergence. In the tutorial on approximating the KL-Divergence, scalar values were returned, and not multiple values...

Use `bayeux` to access a wide range of samplers

17

I have been following @ColCarroll [bayeux](https://github.com/jax-ml/bayeux) library and thought it would be interesting to see how Bambi could incorporate it to offer the users a wide range of samplers (more...

Add `MultinomialRV` JAX implementation

7

This draft PR is a work in progress and contains a JAX implementation of `MultinomialRV` for issue #1326. The implementation builds off the `Multinomial Distribution` [implementation](https://num.pyro.ai/en/v0.2.4/_modules/numpyro/distributions/util.html) in NumPyro. Likewise, the...

Prior predictive checks with `interpret`

2

See Vincent's [Prior Predictive Checks (ppc) with marginaleffects and brms](https://arelbundock.com/posts/marginaleffects_priors/) blog post. The idea is to simulate from the model, without using the data, in order to refine the model...

Sampler parameters not used when calling JAX samplers

1

To change `bayeux` based sampler parameter values, we require passing `kwargs` like ```python3 kwargs = { "adapt.run": {"num_steps": 500}, "num_chains": 4, "num_draws": 250, "num_adapt_draws": 250 } blackjax_nuts_idata = model.fit(inference_method="blackjax_nuts", **kwargs)...

The `include_group_specific` parameter of the method [predict](https://github.com/bambinos/bambi/blob/d5746143731d2f04d37c23f8e69901af76b5cbc4/bambi/models.py#L831) is not rendering in the [parameters](https://bambinos.github.io/bambi/api/Model.html#parameters-5) table of our online docs.

plot predictions shape error with multinomial model

4

@AlexAndorra raised a question/issue in the LB stats Slack. Posting here. --- I'm doing something like this: ```python3 bmb.interpret.predictions( multinomial_model_bambi, idata_multinomial_bambi, conditional={ "cat1": ["A", "B"], "name": ["name1", ..., "name10"], },...