DocumentCode :
3239380
Title :
On the optimality of k-means clustering
Author :
Dalton, Lori
Author_Institution :
Dept. of Electr. & Comput. Eng., Ohio State Univ., Columbus, OH, USA
fYear :
2013
fDate :
17-19 Nov. 2013
Firstpage :
70
Lastpage :
71
Abstract :
Although it is typically accepted that cluster analysis is a subjective activity, without an objective framework it is impossible to understand, let alone guarantee, the predictive capacity of clustering. To address this, recent work utilizes random point process theory to develop a probabilistic theory of clustering. The theory fully parallels Bayes decision theory for classification: given a known underlying processes and specified cost function there exist Bayes clustering operators with minimum expected error. Clustering is hence transformed from a subjective activity to an objective operation. In this work, we present conditions under which the optimization function utilized in classical k-means clustering is optimal in the new Bayes clustering theory, and thus begin to understand this algorithm objectively.
Keywords :
Bayes methods; decision theory; optimisation; pattern clustering; Bayes clustering operators; Bayes decision theory; cost function; k-means clustering; objective operation; optimization function; predictive capacity; probabilistic theory; random point process theory; subjective activity; Clustering algorithms; Cost function; Decision theory; Indexes; Linear programming; Probabilistic logic; Silicon; Bayes decision theory; Optimal clustering; k-means clustering;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Genomic Signal Processing and Statistics (GENSIPS), 2013 IEEE International Workshop on
Conference_Location :
Houston, TX
Print_ISBN :
978-1-4799-3461-4
Type :
conf
DOI :
10.1109/GENSIPS.2013.6735934
Filename :
6735934
Link To Document :
بازگشت