funsor
Functional tensors for probabilistic programming
view repo
It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the versatility of modern automatic differentiation frameworks is based in large part on the unifying concept of tensors, we describe a software abstraction –functional tensors– that captures many of the benefits of tensors, while also being able to describe continuous probability distributions. Moreover, functional tensors are a natural candidate for generalized variable elimination and parallel-scan filtering algorithms that enable parallel exact inference for a large family of tractable modeling motifs. We demonstrate the versatility of functional tensors by integrating them into the modeling frontend and inference backend of the Pyro programming language. In experiments we show that the resulting framework enables a large variety of inference strategies, including those that mix exact and approximate inference.
READ FULL TEXT
We introduce a new logic programming language T-PRISM based on tensor
em...
read it
Pyro is a probabilistic programming language built on Python as a platfo...
read it
We present new results on the classical algorithm of variable eliminatio...
read it
Reasoning on large and complex real-world models is a computationally
di...
read it
NumPyro is a lightweight library that provides an alternate NumPy backen...
read it
Researchers have recently proposed several systems that ease the process...
read it
Modern hardware platforms, from the very small to the very large,
increa...
read it
Functional tensors for probabilistic programming
Comments
There are no comments yet.