Good (K-means) clusterings are unique (up to small perturbations)

Marina Meilă

Journal of Multivariate Analysis, 2019, vol. 173, issue C, 1-17

Abstract: If we have found a “good” clustering C of a data set, can we prove that C is not far from the (unknown) best clustering Copt of these data? Perhaps surprisingly, the answer to this question is sometimes yes. This paper gives spectral bounds on the distance d(C,Copt) for the case when “goodness” is measured by a quadratic cost, such as the squared distortion of K-means clustering or the Normalized Cut criterion of spectral clustering. The bounds exist only if the data admit a “good”, low-cost clustering. The results in this paper are non-asymptotic and model-free, in the sense that no assumptions are made on the data generating process. The bounds do not depend on undefined constants, and can be computed tractably from the data.

Keywords: K-means clustering; Spectral clustering; Cluster validation; Model free; Clusterability (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0047259X18300964
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jmvana:v:173:y:2019:i:c:p:1-17

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

DOI: 10.1016/j.jmva.2018.12.008

Access Statistics for this article

Journal of Multivariate Analysis is currently edited by de Leeuw, J.

More articles in Journal of Multivariate Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().