Hanson-Wright inequality in Hilbert spaces with application to K-means clustering for non-Euclidean data

10/26/2018

∙

by   Xiaohui Chen, et al.

∙

0

∙

share

We derive a dimensional-free Hanson-Wright inequality for quadratic forms of independent sub-gaussian random variables in a separable Hilbert space. Our inequality is an infinite-dimensional generalization of the classical Hanson-Wright inequality for finite-dimensional Euclidean random vectors. We illustrate an application to the generalized K-means clustering problem for non-Euclidean data. Specifically, we establish the exponential rate of convergence for a semidefinite relaxation of the generalized K-means, which together with a simple rounding algorithm imply the exact recovery of the true clustering structure.