Minimax Hausdorff estimation of density level sets

05/07/2019
by   Alberto Rodríguez-Casal, et al.
0

Given a random sample of points from some unknown density, we propose a data-driven method for estimating density level sets under the r-convexity assumption. This shape condition generalizes the convexity property. However, the main problem in practice is that r is an unknown geometric characteristic of the set related to its curvature. A stochastic algorithm is proposed for selecting its optimal value from the data. The resulting reconstruction of the level set is able to achieve minimax rates for Hausdorff metric and distance in measure, up to log factors, uniformly on the level of the set.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset