Yinyang K-means is a drop-in replacement of the classic K-Means with an order of magnitude higher performance, and significantly outperforms prior K- means algorithms consistently across all experimented data sets, cluster numbers, and machine configurations. This paper presents Yinyang K-means, a new algorithm for K-means clustering. By clustering the centers in the initial stage, and leveraging efficiently maintained lower and upper bounds between a point and centers, it more effectively avoids unnecessary distance calculations than prior algorithms. It significantly outperforms prior K-means algorithms consistently across all experimented data sets, cluster numbers, and machine configurations. The consistent, superior performance--plus its simplicity, user-control of overheads, and guarantee in producing the same clustering results as the standard K-means--makes Yinyang K-means a drop-in replacement of the classic K-means with an order of magnitude higher performance.
PDF) Distance Weighted K-Means Algorithm for Center Selection in
A parallel algorithm for approximating the silhouette using a ball
Algorithms, Free Full-Text
Reuse-centric k-means configuration - ScienceDirect
PDF) Large scale K-means clustering using GPUs
Even Faster Exact k-Means Clustering
Using a Set of Triangle Inequalities to Accelerate K-means
PDF] On the Efficiency of K-Means Clustering: Evaluation
Large scale K-means clustering using GPUs
PDF] A Dual-Tree Algorithm for Fast k-means Clustering With Large