by , , ,
Abstract:
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, large-scale datasets while offering a reduction in runtime of several orders of magnitude.
Reference:
Approximate K-Means++ in Sublinear Time O. Bachem, M. Lucic, S. H. Hassani, A. KrauseIn Proc. Conference on Artificial Intelligence (AAAI), 2016
Bibtex Entry:
@inproceedings{bachem16approximate,
	Author = {Olivier Bachem and Mario Lucic and S. Hamed Hassani and Andreas Krause},
	Booktitle = {Proc. Conference on Artificial Intelligence (AAAI)},
	Month = {February},
	Title = {Approximate K-Means++ in Sublinear Time},
	Year = 2016}