Classification in asymmetric spaces via sample compression
Machine Learning
2019-09-24 v1 Machine Learning
Abstract
We initiate the rigorous study of classification in quasi-metric spaces. These are point sets endowed with a distance function that is non-negative and also satisfies the triangle inequality, but is asymmetric. We develop and refine a learning algorithm for quasi-metrics based on sample compression and nearest neighbor, and prove that it has favorable statistical properties.
Cite
@article{arxiv.1909.09969,
title = {Classification in asymmetric spaces via sample compression},
author = {Lee-Ad Gottlieb and Shira Ozeri},
journal= {arXiv preprint arXiv:1909.09969},
year = {2019}
}