Adrian Seyboldt

Not anymore. This included an updated progressbar: https://github.com/pymc-devs/nutpie/pull/105  It's not released yet though. The code is around here: https://github.com/pymc-devs/nutpie/blob/main/python/nutpie/sample.py#L308

Nice :D In the case of the ZeroSumNormal probably not really much, once we figure out the expression in the untransformed space it doesn't change too much, and I guess...

I just had a look at the generated graphs of each of those. Let's say we want the logp of the model: ```python with pm.Model(check_bounds=False) as model: pm.ZeroSumNormal("x", shape=(10, 10),...

That was with `check_bounds=False`. For most dists that only disables the checks on the parameters, not the domain of the value. But I don't think that's the main source for...

You are right, it seems check_bounds=False didn't do anything, because I wasn't compiling the pytensor functions in a model context. I had no idea I had to do that...

Thank you for the PR! It would be nice if we can come up with a test that this is in fact enough. Maybe we can arbitrarily introduce some nan...

I think checking that all samples are positive and the posterior variance is reasonable should be enough. The true posterior standard deviation should be $\sqrt{(1 + 1/100)^{-1}} \approx 0.1$, so...

I think we could do this by using a somewhat lower-level interface in nuts-rs. Right now we just call `sample_parallel`, which takes care of multithreading of the different chains and...

The code I used is here: https://github.com/aseyboldt/covadapt-paper/blob/main/notebooks/model-zoo.ipynb And in the same repo there is also a notebook with a couple of plots for the results.

Why not just `message="Cannot cache compiled function"`? `filterwarnings` accepts a regex for the message, so maybe something in the string is interpreted in a strange way? *Edit* On second though,...