DeeProb-kit: a Python Library for Deep Probabilistic Modelling
This is an incremental contribution that provides a unified tool for researchers working on deep probabilistic models.
The authors introduced DeeProb-kit, a Python library for deep probabilistic modelling that provides tractable and exact representations of probability distributions, aiming to accelerate research and standardize evaluation in this field.
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.