probabilistic-programming

Pyro's HMC and NUTS implementations are feature-complete and well-tested, but they are quite slow in models like the one in our Bayesian regression tutorial that operate on small tensors for reasons that are largely beyond our control (mostly having to do with the design and implementation of torch.autograd), which is unfortunate because these

tfd.Categorical.quantile not working

Ankit Shah and I are trying to use Gen to support a project and would love the addition of a dirichlet distribution

In SVI latent random variables sampled from the guide completely mask those sampled in the model during inference. However, nothing prevents us from specifying different shapes for such a sample site in model and guide respectively. This makes it easy to introduce confusing bugs when code in the model expects a certain shape that is different than what guide provides. This can easily happen if the

The current example on MDN from Edward tutorials needs small modifications to run on edward2. Documentation covering these modifications will be appreciated.

Hi,

Looks like there is support for lots of common distribution. There are a handful of other distributions which are not presently supported but could (fingers crossed) be easily implemented. Looking at [Stan's Function Reference] I see...

• Beta Binomial
• [Chi-Square](https://mc-stan.org/docs/2

There are a variety of interesting optimisations that can be performed on kernels of the form

k(x, z) = w_1 * k_1(x, z) + w_2 * k_2(x, z) + ... + w_L k_L(x, z)

A naive recursive implementation in terms of the current Sum and Scaled kernels hides opportunities for parallelism in the computation of each term, and the summation over terms.

Notable examples of kernels with th

See wikipedia table for example patterns: https://en.wikipedia.org/wiki/List_of_integrals_of_Gaussian_functions