Kernel k-Means, By All Means: Algorithms and Strong Consistency

by   Debolina Paul, et al.

Kernel k-means clustering is a powerful tool for unsupervised learning of non-linearly separable data. Since the earliest attempts, researchers have noted that such algorithms often become trapped by local minima arising from non-convexity of the underlying objective function. In this paper, we generalize recent results leveraging a general family of means to combat sub-optimal local solutions to the kernel and multi-kernel settings. Called Kernel Power k-Means, our algorithm makes use of majorization-minimization (MM) to better solve this non-convex problem. We show the method implicitly performs annealing in kernel feature space while retaining efficient, closed-form updates, and we rigorously characterize its convergence properties both from computational and statistical points of view. In particular, we characterize the large sample behavior of the proposed method by establishing strong consistency guarantees. Its merits are thoroughly validated on a suite of simulated datasets and real data benchmarks that feature non-linear and multi-view separation.


page 1

page 2

page 3

page 4


Entropy Regularized Power k-Means Clustering

Despite its well-known shortcomings, k-means remains one of the most wid...

Bregman Power k-Means for Clustering Exponential Family Data

Recent progress in center-based clustering algorithms combats poor local...

Biconvex Clustering

Convex clustering has recently garnered increasing interest due to its a...

Multiple Kernel k-Means Clustering by Selecting Representative Kernels

To cluster data that are not linearly separable in the original feature ...

Statistical and Computational Trade-Offs in Kernel K-Means

We investigate the efficiency of k-means in terms of both statistical an...

Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization

Most recently, tensor-SVD is implemented on multi-view self-representati...

Efficient Alternating Minimization Solvers for Wyner Multi-View Unsupervised Learning

In this work, we adopt Wyner common information framework for unsupervis...

Please sign up or login with your details

Forgot password? Click here to reset