Consistency and Rates for Clustering with DBSCAN

Bharath Sriperumbudur, Ingo Steinwart ; JMLR W&CP 22: 1090-1098, 2012.

Abstract

We propose a simple and efficient modification of the popular DBSCAN clustering algorithm. This modification is able to detect the most interesting vertical threshold level in an automated, data-driven way. We establish both consistency and optimal learning rates for this modification.