Skip to Main content Skip to Navigation
Journal articles

Minimax Rates for Estimating the Dimension of a Manifold

Abstract : 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}
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-02425684
Contributor : Jisu Kim <>
Submitted on : Tuesday, December 31, 2019 - 2:48:08 AM
Last modification on : Friday, April 30, 2021 - 9:51:59 AM
Long-term archiving on: : Wednesday, April 1, 2020 - 1:40:37 PM

File

DimensionEstimator_arxiv.pdf
Files produced by the author(s)

Identifiers

Citation

Jisu Kim, Alessandro Rinaldo, Larry Wasserman. Minimax Rates for Estimating the Dimension of a Manifold. Journal of Computational Geometry, Carleton University, Computational Geometry Laboratory, 2019, 10 (1), ⟨10.20382/jocg.v10i1a3⟩. ⟨hal-02425684⟩

Share

Metrics

Record views

61

Files downloads

168