On K-means algorithm with the use of Mahalanobis distances

Melnykov, Igor; Melnykov, Volodymyr; Igor, Melnykov

On K-means algorithm with the use of Mahalanobis distances

Date

2014-01-01

Authors

Melnykov, Igor

Igor, Melnykov

Melnykov, Volodymyr

Publisher

Statistics & Probability Letters

Abstract

Abstract The K-means algorithm is commonly used with the Euclidean metric. While the use of Mahalanobis distances seems to be a straightforward extension of the algorithm, the initial estimation of covariance matrices can be complicated. We propose a novel approach for initializing covariance matrices.

Keywords

K-means algorithm, Mahalanobis distance, Initialization

Citation

Igor Melnykov, Volodymyr Melnykov, On K-means algorithm with the use of Mahalanobis distances, In Statistics & Probability Letters, Volume 84, 2014, Pages 88-95