On Robustness of Kernel Clustering
arXiv:1606.01869
Abstract
Clustering is one of the most important unsupervised problems in machine learning and statistics. Among many existing algorithms, kernel k-means has drawn much research attention due to its ability to find non-linear cluster boundaries and its inherent simplicity. There are two main approaches for kernel k-means: SVD of the kernel matrix and convex relaxations. Despite the attention kernel clustering has received both from theoretical and applied quarters, not much is known about robustness of the methods. In this paper we first introduce a semidefinite programming relaxation for the kernel clustering problem, then prove that under a suitable model specification, both the K-SVD and SDP approaches are consistent in the limit, albeit SDP is strongly consistent, i.e. achieves exact recovery, whereas K-SVD is weakly consistent, i.e. the fraction of misclassified nodes vanish.
20 pages, 3 figures
Cited by in corpus (6)
- Kernel k-Means, By All Means: Algorithms and Strong Consistency
- Covariate Regularized Community Detection in Sparse Graphs
- On the optimality of kernels for high-dimensional clustering
- Convergence Analysis of Gradient EM for Multi-component Gaussian Mixture
- Robust Data-driven Profile-based Pricing Schemes
- Near-Optimal Comparison Based Clustering