Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
Machine Learning
2019-12-13 v2 Machine Learning
Abstract
This letter introduces an abstract learning problem called the "set embedding": The objective is to map sets into probability distributions so as to lose less information. We relate set union and intersection operations with corresponding interpolations of probability distributions. We also demonstrate a preliminary solution with experimental results on toy set embedding examples.
Cite
@article{arxiv.1911.12463,
title = {Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions},
author = {Ke Sun and Frank Nielsen},
journal= {arXiv preprint arXiv:1911.12463},
year = {2019}
}
Comments
To be presented at Sets & Partitions (NeurIPS 2019 workshop)