Saved in:
Bibliographic Details
Main Authors: Jacimovic, Vladimir, Markovic, Marijan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.16733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914883475341312
author Jacimovic, Vladimir
Markovic, Marijan
author_facet Jacimovic, Vladimir
Markovic, Marijan
contents We introduce the novel family of probability distributions on hyperbolic disc. The distinctive property of the proposed family is invariance under the actions of the group of disc-preserving conformal mappings. The group-invariance property renders it a convenient and tractable model for encoding uncertainties in hyperbolic data. Potential applications in Geometric Deep Learning and bioinformatics are numerous, some of them are briefly discussed. We also emphasize analogies with hyperbolic coherent states in quantum physics.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16733
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Conformally Natural Families of Probability Distributions on Hyperbolic Disc with a View on Geometric Deep Learning
Jacimovic, Vladimir
Markovic, Marijan
Machine Learning
Complex Variables
We introduce the novel family of probability distributions on hyperbolic disc. The distinctive property of the proposed family is invariance under the actions of the group of disc-preserving conformal mappings. The group-invariance property renders it a convenient and tractable model for encoding uncertainties in hyperbolic data. Potential applications in Geometric Deep Learning and bioinformatics are numerous, some of them are briefly discussed. We also emphasize analogies with hyperbolic coherent states in quantum physics.
title Conformally Natural Families of Probability Distributions on Hyperbolic Disc with a View on Geometric Deep Learning
topic Machine Learning
Complex Variables
url https://arxiv.org/abs/2407.16733