# Learning Probabilistic Programs Using Backpropagation

## TL;DR

This paper introduces a method for training probabilistic programs using backpropagation, enabling the development of deep probabilistic models trained similarly to neural networks, potentially improving learning efficiency.

## Contribution

It presents a novel approach to learn probabilistic program parameters via backpropagation, bridging probabilistic programming and deep learning techniques.

## Key findings

- Enables training probabilistic models with backpropagation
- Facilitates deep probabilistic programming models
- Potentially improves learning efficiency in probabilistic models

## Abstract

Probabilistic modeling enables combining domain knowledge with learning from data, thereby supporting learning from fewer training instances than purely data-driven methods. However, learning probabilistic models is difficult and has not achieved the level of performance of methods such as deep neural networks on many tasks. In this paper, we attempt to address this issue by presenting a method for learning the parameters of a probabilistic program using backpropagation. Our approach opens the possibility to building deep probabilistic programming models that are trained in a similar way to neural networks.