Normalizing Flows on Tori and Spheres
Abstract
Normalizing flows are a powerful tool for building expressive distributions in high dimensions. So far, most of the literature has concentrated on learning flows on Euclidean spaces. Some problems however, such as those involving angles, are defined on spaces with more complex geometries, such as tori or spheres. In this paper, we propose and compare expressive and numerically stable flows on such spaces. Our flows are built recursively on the dimension of the space, starting from flows on circles, closed intervals or spheres.
Cite
Text
Rezende et al. "Normalizing Flows on Tori and Spheres." International Conference on Machine Learning, 2020.Markdown
[Rezende et al. "Normalizing Flows on Tori and Spheres." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/rezende2020icml-normalizing/)BibTeX
@inproceedings{rezende2020icml-normalizing,
title = {{Normalizing Flows on Tori and Spheres}},
author = {Rezende, Danilo Jimenez and Papamakarios, George and Racaniere, Sebastien and Albergo, Michael and Kanwar, Gurtej and Shanahan, Phiala and Cranmer, Kyle},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {8083-8092},
volume = {119},
url = {https://mlanthology.org/icml/2020/rezende2020icml-normalizing/}
}