Improved Spectral-Norm Bounds for Clustering

TL;DR

This paper enhances spectral-norm bounds for clustering, weakening separation and proximity conditions while maintaining guarantees, thus broadening applicability to various mixture models.

Contribution

It introduces weaker separation and proximity bounds for clustering, enabling effective clustering under less restrictive conditions than prior work.

Findings

Achieves the same guarantees with a factor of √k weaker separation bound.

Provides better guarantees when only a fraction of points satisfy the proximity condition.

Matches and improves upon results in planted partition and Gaussian mixture models.

Abstract

Aiming to unify known results about clustering mixtures of distributions under separation conditions, Kumar and Kannan[2010] introduced a deterministic condition for clustering datasets. They showed that this single deterministic condition encompasses many previously studied clustering assumptions. More specifically, their proximity condition requires that in the target $k$-clustering, the projection of a point $x$ onto the line joining its cluster center $\mu$ and some other center $\mu'$, is a large additive factor closer to $\mu$ than to $\mu'$. This additive factor can be roughly described as $k$ times the spectral norm of the matrix representing the differences between the given (known) dataset and the means of the (unknown) target clustering. Clearly, the proximity condition implies center separation -- the distance between any two centers must be as large as the above mentioned bound. In this paper we improve upon the work of Kumar and Kannan along several axes. First, we weaken the center separation bound by a factor of $\sqrt{k}$, and secondly we weaken the proximity condition by a factor of $k$. Using these weaker bounds we still achieve the same guarantees when all points satisfy the proximity condition. We also achieve better guarantees when only $(1-\epsilon)$-fraction of the points satisfy the weaker proximity condition. The bulk of our analysis relies only on center separation under which one can produce a clustering which (i) has low error, (ii) has low $k$-means cost, and (iii) has centers very close to the target centers. Our improved separation condition allows us to match the results of the Planted Partition Model of McSherry[2001], improve upon the results of Ostrovsky et al[2006], and improve separation results for mixture of Gaussian models in a particular setting.