Borch: A Deep Universal Probabilistic Programming Language

TL;DR

Borch is a scalable deep probabilistic programming language built on PyTorch that enables models to represent, learn, and report uncertainty in predictions, integrating probabilistic modeling with deep neural networks.

Contribution

This paper introduces Borch, a novel universal probabilistic programming language designed for deep learning, combining scalability with principled uncertainty modeling.

Findings

Borch effectively integrates probabilistic modeling with deep neural networks.

The language supports scalable and flexible uncertainty reporting.

Open-source implementation available for practical use.

Abstract

Ever since the Multilayered Perceptron was first introduced the connectionist community has struggled with the concept of uncertainty and how this could be represented in these types of models. This past decade has seen a lot of effort in trying to join the principled approach of probabilistic modeling with the scalable nature of deep neural networks. While the theoretical benefits of this consolidation are clear, there are also several important practical aspects of these endeavors; namely to force the models we create to represent, learn, and report uncertainty in every prediction that is made. Many of these efforts have been based on extending existing frameworks with additional structures. We present Borch, a scalable deep universal probabilistic programming language, built on top of PyTorch. The code is available for download and use in our repository https://gitlab.com/desupervised/borch.