Fourier Basis Density Model
Machine Learning
2024-02-26 v1 Machine Learning
Abstract
We introduce a lightweight, flexible and end-to-end trainable probability density model parameterized by a constrained Fourier basis. We assess its performance at approximating a range of multi-modal 1D densities, which are generally difficult to fit. In comparison to the deep factorized model introduced in [1], our model achieves a lower cross entropy at a similar computational budget. In addition, we also evaluate our method on a toy compression task, demonstrating its utility in learned compression.
Cite
@article{arxiv.2402.15345,
title = {Fourier Basis Density Model},
author = {Alfredo De la Fuente and Saurabh Singh and Johannes Ballé},
journal= {arXiv preprint arXiv:2402.15345},
year = {2024}
}