The MinMax k-Means clustering algorithm
作者：
Highlights：
• We propose the MinMax k-Means algorithm to minimize the maximum intra-cluster variance objective.
• Weights are assigned to the clusters relative to their intra-cluster variance.
• Our method prevents the occurrence of clusters with large intra-cluster variances in the solution.
• Our method systematically uncovers high quality solutions, irrespective of the initialization.
• MinMax k-Means constitutes a sound approach for initializing k-Means.
摘要
Highlights•We propose the MinMax k-Means algorithm to minimize the maximum intra-cluster variance objective.•Weights are assigned to the clusters relative to their intra-cluster variance.•Our method prevents the occurrence of clusters with large intra-cluster variances in the solution.•Our method systematically uncovers high quality solutions, irrespective of the initialization.•MinMax k-Means constitutes a sound approach for initializing k-Means.
论文关键词：Clustering,k-Means,k-Means initialization,Balanced clusters
论文评审过程：Received 18 February 2013, Revised 20 January 2014, Accepted 28 January 2014, Available online 6 February 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2014.01.015
