It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework.
To exploit efficient tensor algebra in graphs with plates of variables, we generalize undirected factor graphs to plated factor graphs and variable elimination to a tensor variable elimination algorithm that operates directly on plated factor graphs.
Our algorithm outperforms our current production baseline based on k-means clustering.
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research.
We observe that gradients computed via the reparameterization trick are in direct correspondence with solutions of the transport equation in the formalism of optimal transport.
This new algorithm learns nonparametric latent structure over a growing and constantly churning subsample of training data, where the portion of data subsampled can be interpreted as the inverse temperature beta(t) in an annealing schedule.