numpyro
numpyro copied to clipboard
pyro-ppl
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
I was wondering whether there would an interest to add inference methods which support programs with stochastic support? If yes, I would be willing to add inference methods from the...
Minimal example: ```python import jax import jax.numpy as jnp from jax.random import PRNGKey import numpyro import numpyro.distributions as dist from numpyro.infer import MCMC, NUTS, Trace_ELBO, SVI from numpyro.infer.reparam import NeuTraReparam...
Pathfinder
Hi all, are there any plans to implement pathfinder ([arXiv:2108.03782](https://arxiv.org/abs/2108.03782)) ? If so, I would be up for implementing it. Cheers, Simon
NumPyro is quite a good package about probabilistic programming, I have seen there is a tutorial about AR(2). Cause VAR is quite important in economics, wish you and your team...
I'm a collaborator on this project https://github.com/JakobRobnik/MicroCanonicalHMC, and we're interested in either adding our algorithm to NumPyro, or using NumPyro in our codebase. With that in mind, we have a...
Currently, block hander does not expose message to outer seed handler. Users have to seed the blocked program explicitly. Hence the blocked program is no longer stochastic. To make it...
Hi all, I believe there is an issue with ``BlockNeuralAutoregressiveTransform``s not forming properly normalised densities when the inverse is used to transform a distribution (the same issue as we have...
Hi, In `Trace_ELBO`, the `num_particles` argument allows one to effectively introduce a batch size in estimating the ELBO gradient if `num_particles > 1`. By default, it's vectorized over the `num_particles`....
Hello, I am trying to build a Docker image from a model that I created using Numpyro. However, when I try to build the Dockerfile given [here](https://github.com/pyro-ppl/numpyro/blob/master/docker/release/Dockerfile) I get the...
One of the features not supported by `TraceEnum_ELBO` is that you cannot subsample a local variable when it depends on a global variable that is enumerated in the model because...
