Fast rates for noisy clustering

arXiv1205.1417MaRDI QIDQ6232841FDOQ6232841

Authors: Sébastien Loustau 

Publication date: 7 May 2012

Abstract: The effect of errors in variables in empirical minimization is investigated. Given a loss $l$ and a set of decision rules $mathcalG$, we prove a general upper bound for an empirical minimization based on a deconvolution kernel and a noisy sample $Z_i=X_i+epsilo{n}_i,i=1,\mathrm{...},n$. We apply this general upper bound to give the rate of convergence for the expected excess risk in noisy clustering. A recent bound from citet{levrard} proves that this rate is $mathcalO(1/n)$ in the direct case, under Pollard's regularity assumptions. Here the effect of noisy measurements gives a rate of the form $$, where $gamma$ is the H"older regularity of the density of $X$ whereas $$ is the degree of illposedness.

This page was built for publication: Fast rates for noisy clustering

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6232841)