Interpretable clustering with the Distinguishability criterion

arXiv:2404.15967v1 Announce Type: cross
Abstract: Cluster analysis is a popular unsupervised learning tool used in many disciplines to identify heterogeneous sub-populations within a sample. However, validating cluster analysis results and determining the number of clusters in a data set remains an outstanding problem. In this work, we present a global criterion called the Distinguishability criterion to quantify the separability of identified clusters and validate inferred cluster configurations. Our computational implementation of the Distinguishability criterion corresponds to the Bayes risk of …

abstract analysis arxiv cluster clustering criterion cs.lg data data set global however identify popular results sample set stat.me stat.ml tool type unsupervised unsupervised learning work