Consistency and rates for clustering with DBSCAN

Research output: Contribution to journalConference article

7 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)1090-1098
Number of pages9
JournalJournal of Machine Learning Research
Volume22
StatePublished - Jan 1 2012
Event15th International Conference on Artificial Intelligence and Statistics, AISTATS 2012 - La Palma, Spain
Duration: Apr 21 2012Apr 23 2012

Fingerprint

Clustering algorithms
Clustering
Learning Rate
Data-driven
Clustering Algorithm
Vertical

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Cite this

@article{0106951d539447919a325afc8ca8accb,
title = "Consistency and rates for clustering with DBSCAN",
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.",
author = "Sriperumbudur, {Bharath Kumar} and Ingo Steinwart",
year = "2012",
month = "1",
day = "1",
language = "English (US)",
volume = "22",
pages = "1090--1098",
journal = "Journal of Machine Learning Research",
issn = "1532-4435",
publisher = "Microtome Publishing",

}

Consistency and rates for clustering with DBSCAN. / Sriperumbudur, Bharath Kumar; Steinwart, Ingo.

In: Journal of Machine Learning Research, Vol. 22, 01.01.2012, p. 1090-1098.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Consistency and rates for clustering with DBSCAN

AU - Sriperumbudur, Bharath Kumar

AU - Steinwart, Ingo

PY - 2012/1/1

Y1 - 2012/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84893267839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893267839&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84893267839

VL - 22

SP - 1090

EP - 1098

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

SN - 1532-4435

ER -