Re:Pyro: PyTorch-Based Deep Universal Probabilistic Programming
by marmaduke on Friday November 03, 2017 @02:48PM
(#15621414)
I think Stan internally decouples the model from the algorithm. In other words, a model is just an implementation of an interface, providing log probability values (and gradient) for a given proposal. To wit it supports optimization in addition to sampling.
[ Parent
| on HN ]
There are no comments on this comment yet.