The Community for Technology Leaders
RSS Icon
Subscribe
Brussels, Belgium Belgium
Dec. 10, 2012 to Dec. 10, 2012
ISBN: 978-1-4673-5164-5
pp: 474-480
ABSTRACT
We propose a method to extract row/column-wise heterogeneous elements between two precision matrices for an anomaly localization. We formulate the task as a convex optimization problem using a regularization term that penalizes row/column-wise differences between two matrices. The fundamental difficulties of the problem are that the proposed regularization term (1) is a sum of group-wise regularizations with overlapping supports between the groups, (2) penalizes matrices in a symmetric manner. Our proposed algorithm with an alternating direction method of multipliers can deal with these two difficulties efficiently resulting in a very simple formulation with each updating step computed analytically. We also show the validity of the proposed method through an anomaly localization simulation using a real world data.
INDEX TERMS
Conferences, Data mining, alternating direction method of multipliers, anomaly localization, precision matrix, graphical Gaussian model
CITATION
Satoshi Hara, Takashi Washio, "Anomalous Neighborhood Selection", ICDMW, 2012, 2013 IEEE 13th International Conference on Data Mining Workshops, 2013 IEEE 13th International Conference on Data Mining Workshops 2012, pp. 474-480, doi:10.1109/ICDMW.2012.10
31 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool