numpyro
numpyro copied to clipboard
pyro-ppl
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
# Description I am submitting a feature request to enhance the capabilities of Numpyro in handling mixture models with component distributions having different supports. Currently, when attempting to construct a...
I notice that after warmup, the `mean_accept_prob` significantly higher than both `target_accept_prob` and the `mean_accept_prob` observed during warmup, even on a trivial isotropic gaussian example. Minimum working example: ```python import...
I was noticing some very erratic and unexpected behaviour from the `effective_sample_size` diagnostic, which was due to some extreme values in the far right tail of the `autocorrelation` function. This...
When I tried to import numpyro, I got the following error: `ImportError: cannot import name 'CAR' from 'numpyro.distributions.continuous'` I checked the .distributions.continuous module that lives in Lib/site-packages but there is...
I would like to write a short tutorial on using numpyro for factor analysis and probabilistic principal components analysis (PPCA), following the exposition in Murphy (2012) chapter 12. Opening an...
I'm trying to implement this Pyro model in NumPyro, and I'm running into issues with the conditional `feeling_lazy`. The guide I'm trying to follow is [here](https://willcrichton.net/notes/probabilistic-programming-under-the-hood/) # Pyro model ```python...
I'm currently working on a project where I'm partially conditioning a large set of latent variables. Here's a toy example: ```python dat = dist.Normal(10, 1).sample(random.PRNGKey(0), (100,)) mask = jnp.concatenate([jnp.ones(50, jnp.bool_),...
Fixes https://github.com/pyro-ppl/numpyro/issues/1446
This PR contains the implementation of Power Law distributions, that fixes #1806. There are two different types of power law implementations based on their truncation. 1. `DoublyTruncatedPowerLaw` 2. `LowerTruncatedPowerLaw` They...
The Pareto Smoothed Importance Sampling $\hat{k}$ diagnostic (as described by [Yao et al. (2018)](https://arxiv.org/pdf/1802.02538)) can be used to determine if a surrogate posterior determined with variational inference is a good...
