DeeProb-kit: a Python Library for Deep Probabilistic Modelling

TL;DR

DeeProb-kit is a comprehensive Python library that offers a collection of deep probabilistic models with efficient algorithms, facilitating research, standardization, and understanding of probabilistic deep learning methods.

Contribution

It provides a unified, well-documented library of tractable deep probabilistic models with integrated learning and inference tools, advancing research and standardization in the field.

Findings

Enables straightforward combination of different DPMs.

Includes efficient algorithms for learning and inference.

Facilitates research and comparison of probabilistic models.

Abstract

DeeProb-kit is a unified library written in Python consisting of a collection of deep probabilistic models (DPMs) that are tractable and exact representations for the modelled probability distributions. The availability of a representative selection of DPMs in a single library makes it possible to combine them in a straightforward manner, a common practice in deep learning research nowadays. In addition, it includes efficiently implemented learning techniques, inference routines, statistical algorithms, and provides high-quality fully-documented APIs. The development of DeeProb-kit will help the community to accelerate research on DPMs as well as to standardise their evaluation and better understand how they are related based on their expressivity.