Minimax Rates for Estimating the Dimension of a Manifold
Résumé
Many algorithms in machine learning and computational geometry require, as input, the intrinsic dimension of the manifold that supports the probability distribution of the data. This parameter is rarely known and therefore has to be estimated. We characterize the statistical difficulty of this problem by deriving upper and lower bounds on the minimax rate for estimating the dimension. First, we consider the problem of testing the hypothesis that the support of the data-generating probability distribution is a well-behaved manifold of intrinsic dimension $d_1$ versus the alternative that it is of dimension $d_2$, with $d_{1}
Origine : Fichiers produits par l'(les) auteur(s)
Loading...
Jisu KIM : Connectez-vous pour contacter le contributeur
https://inria.hal.science/hal-02425684
Soumis le : mardi 31 décembre 2019-02:48:08
Dernière modification le : vendredi 19 avril 2024-13:31:10
Archivage à long terme le : mercredi 1 avril 2020-13:40:37
Dates et versions
Identifiants
- HAL Id : hal-02425684 , version 1
- ARXIV : 1605.01011
- DOI : 10.20382/jocg.v10i1a3
Citer
Jisu Kim, Alessandro Rinaldo, Larry Wasserman. Minimax Rates for Estimating the Dimension of a Manifold. Journal of Computational Geometry, 2019, 10 (1), ⟨10.20382/jocg.v10i1a3⟩. ⟨hal-02425684⟩
Collections
44
Consultations
106
Téléchargements