A central tenet of probabilistic programming is that a model is specified exactly once in a canonical representation which is usable by inference algorithms. We describe JointDistributions, a family of declarative representations of directed graphical models in TensorFlow Probability.
@article{arxiv.2001.11819,
title = {Joint Distributions for TensorFlow Probability},
author = {Dan Piponi and Dave Moore and Joshua V. Dillon},
journal= {arXiv preprint arXiv:2001.11819},
year = {2020}
}
Comments
Based on extended abstract submitted to PROBPROG 2020