English

Clustering Semi-Random Mixtures of Gaussians

Data Structures and Algorithms 2017-11-27 v1 Machine Learning

Abstract

Gaussian mixture models (GMM) are the most widely used statistical model for the kk-means clustering problem and form a popular framework for clustering in machine learning and data analysis. In this paper, we propose a natural semi-random model for kk-means clustering that generalizes the Gaussian mixture model, and that we believe will be useful in identifying robust algorithms. In our model, a semi-random adversary is allowed to make arbitrary "monotone" or helpful changes to the data generated from the Gaussian mixture model. Our first contribution is a polynomial time algorithm that provably recovers the ground-truth up to small classification error w.h.p., assuming certain separation between the components. Perhaps surprisingly, the algorithm we analyze is the popular Lloyd's algorithm for kk-means clustering that is the method-of-choice in practice. Our second result complements the upper bound by giving a nearly matching information-theoretic lower bound on the number of misclassified points incurred by any kk-means clustering algorithm on the semi-random model.

Keywords

Cite

@article{arxiv.1711.08841,
  title  = {Clustering Semi-Random Mixtures of Gaussians},
  author = {Pranjal Awasthi and Aravindan Vijayaraghavan},
  journal= {arXiv preprint arXiv:1711.08841},
  year   = {2017}
}