An Algorithmic Introduction to Clustering

TL;DR

This paper offers a unified perspective on clustering algorithms, clarifying their relationships and introducing a novel interpretation of DBSCAN as a climbing procedure linked to Mean shift.

Contribution

It presents a simplified, unified view of five clustering algorithms and introduces a new interpretation of DBSCAN as a climbing procedure, connecting it to Mean shift.

Findings

DBSCAN interpreted as a climbing procedure

Connections established between five clustering algorithms

Simplified and unified presentation of clustering methods

Abstract

This paper tries to present a more unified view of clustering, by identifying the relationships between five different clustering algorithms. Some of the results are not new, but they are presented in a cleaner, simpler and more concise way. To the best of my knowledge, the interpretation of DBSCAN as a climbing procedure, which introduces a theoretical connection between DBSCAN and Mean shift, is a novel result.