Asymptotic normality in density support estimation.
A graph-based estimator of the number of clusters
Assessing the number of clusters of a statistical population is one of the essential issues of unsupervised learning. Given independent observations drawn from an unknown multivariate probability density , we propose a new approach to estimate the number of connected components, or clusters, of the -level set . The basic idea is to form a rough skeleton of the set using any preliminary estimator of , and to count the number of connected components of the resulting graph. Under mild analytic...
Page 1