TY - GEN
T1 - Outlier-aware robust clustering
AU - Forero, Pedro A.
AU - Kekatos, Vassilis
AU - Giannakis, Georgios B.
PY - 2011
Y1 - 2011
N2 - Clustering is a basic task in a variety of machine learning applications. Partitioning a set of input vectors into compact, well-separated subsets can be severely affected by the presence of model-incompatible inputs called outliers. The present paper develops robust clustering algorithms for jointly partitioning the data and identifying the outliers. The novel approach relies on translating scarcity of outliers to sparsity in a judiciously defined domain, to robustify three widely used clustering schemes: hard K-means, fuzzy K-means, and probabilistic clustering. Cluster centers and assignments are iteratively updated in closed form. The developed outlier-aware algorithms are guaranteed to converge, while their computational complexity is of the same order as their outlier-agnostic counterparts. Preliminary simulations validate the analytical claims.
AB - Clustering is a basic task in a variety of machine learning applications. Partitioning a set of input vectors into compact, well-separated subsets can be severely affected by the presence of model-incompatible inputs called outliers. The present paper develops robust clustering algorithms for jointly partitioning the data and identifying the outliers. The novel approach relies on translating scarcity of outliers to sparsity in a judiciously defined domain, to robustify three widely used clustering schemes: hard K-means, fuzzy K-means, and probabilistic clustering. Cluster centers and assignments are iteratively updated in closed form. The developed outlier-aware algorithms are guaranteed to converge, while their computational complexity is of the same order as their outlier-agnostic counterparts. Preliminary simulations validate the analytical claims.
KW - K-means
KW - block coordinate descent
KW - convex relaxation
KW - expectation maximization
KW - robust clustering
UR - http://www.scopus.com/inward/record.url?scp=80051612439&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80051612439&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2011.5946928
DO - 10.1109/ICASSP.2011.5946928
M3 - Conference contribution
AN - SCOPUS:80051612439
SN - 9781457705397
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2244
EP - 2247
BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Y2 - 22 May 2011 through 27 May 2011
ER -