Masked autoregressive flow (MAF) is a state-of-the-art non-parametric density estimation technique. It is based on the idea (known as a normalizing flow) that a simple base probability distribution can be mapped into a complicated target distribution that one wishes to approximate, using a sequence of bijective transformations. The denmarf package provides a scikit-learn-like interface in Python for researchers to effortlessly use MAF for density estimation in their applications to evaluate probability densities of the underlying distribution of a set of data and generate new samples from the data, on either a CPU or a GPU, as simple as "from denmarf import DensityEstimate; de = DensityEstimate().fit(X)". The package also implements logistic transformations to facilitate the fitting of bounded distributions.
@article{arxiv.2305.14379,
title = {denmarf: a Python package for density estimation using masked autoregressive flow},
author = {Rico K. L. Lo},
journal= {arXiv preprint arXiv:2305.14379},
year = {2023}
}