Summary
The 2018 International Symposium on Information Theory and Its Applications (ISITA2018)
2018
Session Number:Mo-AM-1-3
Session:
Number:Mo-AM-1-3.1
Generalized Dirichlet-Process-Means for Robust and Maximum Distortion Criteria
Masahiro Kobayashi, Kazuho Watanabe,
pp.45-49
Publication Date:2018/10/18
Online ISSN:2188-5079
DOI:10.34385/proc.55.Mo-AM-1-3.1
PDF download
Summary:
DP-means clustering was obtained as an extension of K-means clustering. While it is implemented with a simple and efficient algorithm, it can estimate the number of clusters simultaneously. However, DP-means is specifically designed for the average distortion criterion. Therefore, it is vulnerable to outliers in data, and can cause large maximum distortion in clusters. This study introduces a new parameter to the objective function of DPmeans to provide an extension of DP-means, which bridges robust estimation of cluster centers and minimization of the maximum distortion criterion.