Minimax boundary estimation and estimation with boundary
Bernoulli · 01.11.2023 · 29 (4) · 3334-3368
DOI: 10.3150/23-bej1585 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bernoulli, erschienen am 01.11.2023. Verfasst von Eddie Aamari und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben.
Abstract (Originalsprache)
We derive non-asymptotic minimax bounds for the Hausdorff estimation of d-dimensional submanifolds M⊂RD with (possibly) non-empty boundary ∂M. The model reunites and extends the most prevalent C2-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 ∂M if non-empty. Given n samples, the minimax rates are of order O((logn∕n)2∕d) if ∂M=∅ and O((logn∕n)2∕(d+1)) if ∂M≠∅, up to logarithmic factors. In the process, we develop a Voronoi-based procedure that allows to identify enough points O((logn∕n)2∕(d+1))-close to ∂M for reconstructing it. Explicit constant derivations are given, showing that these rates do not depend on the ambient dimension D≫d.
Zitieren
APA
Aamari, E., Aaron, C., & Levrard, C. (2023). Minimax boundary estimation and estimation with boundary. Bernoulli, 29(4), 3334-3368. https://doi.org/10.3150/23-bej1585
Vancouver
Aamari E, Aaron C, Levrard C. Minimax boundary estimation and estimation with boundary. Bernoulli. 2023;29(4):3334-3368. doi:10.3150/23-bej1585
BibTeX
@article{Aamari2023,
author = {Aamari, Eddie and Aaron, Catherine and Levrard, Clément},
title = {Minimax boundary estimation and estimation with boundary},
journal = {Bernoulli},
year = {2023},
volume = {29},
number = {4},
pages = {3334--3368},
doi = {10.3150/23-bej1585}
}
EUVIMED