Monte Carlo approximation certificates for k-means clustering
Mixon, Dustin G., Villar, Soledad
Efficient algorithms for $k$-means clustering frequently converge to suboptimal partitions, and given a partition, it is difficult to detect $k$-means optimality. In this paper, we develop an a posteriori certifier of approximate optimality for $k$-means clustering. The certifier is a sub-linear Monte Carlo algorithm based on Peng and Wei's semidefinite relaxation of $k$-means. In particular, solving the relaxation for small random samples of the dataset produces a high-confidence lower bound on the $k$-means objective, and being sub-linear, our algorithm is faster than $k$-means++ when the number of data points is large. We illustrate the performance of our algorithm with both numerical experiments and a performance guarantee: If the data points are drawn independently from any mixture of two Gaussians over $\mathbb{R}^m$ with identity covariance, then with probability $1-O(1/m)$, our $\operatorname{poly}(m)$-time algorithm produces a 3-approximation certificate with 99% confidence.
Oct-2-2017
- Country:
- North America > United States
- New York (0.14)
- Ohio (0.14)
- California (0.14)
- North America > United States
- Genre:
- Research Report (0.82)
- Industry:
- Government > Regional Government (0.46)
- Technology: