Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Minimax adaptive estimation in manifold inference

Vincent Divol 1, 2
1 DATASHAPE - Understanding the Shape of Data
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
Abstract : We focus on the problem of manifold estimation: given a set of observations sampled close to some unknown submanifold M , one wants to recover information about the geometry of M. Minimax estimators which have been proposed so far all depend crucially on the a priori knowledge of some parameters quantifying the regularity of M (such as its reach), whereas those quantities will be unknown in practice. Our contribution to the matter is twofold: first, we introduce a one-parameter family of manifold estimators (M t) t≥0 , and show that for some choice of t (depending on the regularity parameters), the corresponding estimator is minimax on the class of models of C 2 manifolds introduced in [Genovese et al., Manifold estimation and singular deconvolution under Hausdorff loss]. Second, we propose a completely data-driven selection procedure for the parameter t, leading to a minimax adaptive manifold estimator on this class of models. This selection procedure actually allows to recover the sample rate of the set of observations, and can therefore be used as an hyperparameter in other settings, such as tangent space estimation.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Vincent Divol <>
Submitted on : Monday, June 8, 2020 - 3:17:05 PM
Last modification on : Friday, April 30, 2021 - 10:02:33 AM


Files produced by the author(s)


  • HAL Id : hal-02440881, version 2


Vincent Divol. Minimax adaptive estimation in manifold inference. 2020. ⟨hal-02440881v2⟩



Record views


Files downloads