Abstract
We derive non-asymptotic minimax bounds for the Hausdorff estimation of d-dimensional submanifolds with (possibly) non-empty boundary . The model reunites and extends the most prevalent -type set estimation models: manifolds without boundary, and full-dimensional domains. We consider both the estimation of the manifold M itself and that of its boundary if non-empty. Given n samples, the minimax rates are of order if and if , up to logarithmic factors. In the process, we develop a Voronoi-based procedure that allows to identify enough points -close to for reconstructing it. Explicit constant derivations are given, showing that these rates do not depend on the ambient dimension .
Acknowledgments
We are grateful to the members of the Laboratoire de Probabilités, Statistique et Modélisation and the Laboratoire de Mathématiques Blaise Pascal for their insightful comments.
Citation
Eddie Aamari. Catherine Aaron. Clément Levrard. "Minimax boundary estimation and estimation with boundary." Bernoulli 29 (4) 3334 - 3368, November 2023. https://doi.org/10.3150/23-BEJ1585
Information