Deep Probabilistic Programming Languages: A Qualitative Study

2018/04/17 by Guillaume Baudart, Martin Hirzel, Baudart, Guillaume +3 · 2 voices · 1 citation
#cs.AI #cs.PL

paper · pdf · doi:10.48550/arxiv.1804.06458

Abstract

Deep probabilistic programming languages try to combine the advantages of deep learning with those of probabilistic programming languages. If successful, this would be a big step forward in machine learning and programming languages. Unfortunately, as of now, this new crop of languages is hard to use and understand. This paper addresses this problem directly by explaining deep probabilistic programming languages and indirectly by characterizing their current strengths and weaknesses.

Cited by

• A multi-dimensional quantum estimation and model learning framework based on variational Bayesian inference

Discussions

• Deep Probabilistic Programming Languages: A Qualitative Study [hn, 53 points, 2 comments]
• Deep Probabilistic Programming Languages: A Qualitative Study [lobsters, 5 points, 0 comments]

Related

• Probabilistic Programming Concepts
• An Introduction to Probabilistic Programming
• Foundations of Probabilistic Programming
• A Survey of Machine Learning for Big Code and Naturalness
• Automated learning with a probabilistic programming language: Birch