Approximate K-Means++ in Sublinear Time

O. Bachem, M. Lucic, H. Hassani, A. Krause


The quality of K-Means clustering is extremely sensitive to proper initialization. The classic remedy is to apply k-means++ to obtain an initial set of centers that is provably competitive with the optimal solution. Unfortunately, k-means++ requires k full passes over the data which limits its applicability to massive datasets. We address this problem by proposing a simple and efficient seeding algorithm for K-Means clustering. The main idea is to replace the exact D2-sampling step in k-means++ with a substantially faster approximation based on Markov Chain Monte Carlo sampling. We prove that, under natural assumptions on the data, the proposed algorithm retains the full theoretical guarantees of k-means++ while its computational complexity is only sublinear in the number of data points. For such datasets, one can thus obtain a provably good clustering in sublinear time. Extensive experiments confirm that the proposed method is competitive with k-means++ on a variety of real-world, largescale datasets while offering a reduction in runtime of several orders of magnitude.


Type: Proceedings
Published in: Conference on Artificial Intelligence (AAAI)
Year: 2016
Publisher: Association for the Advancement of Artificial Intelligence