Open Access
2019 Estimating the reach of a manifold
Eddie Aamari, Jisu Kim, Frédéric Chazal, Bertrand Michel, Alessandro Rinaldo, Larry Wasserman
Electron. J. Statist. 13(1): 1359-1399 (2019). DOI: 10.1214/19-EJS1551

Abstract

Various problems in manifold estimation make use of a quantity called the reach, denoted by $\tau_{M}$, which is a measure of the regularity of the manifold. This paper is the first investigation into the problem of how to estimate the reach. First, we study the geometry of the reach through an approximation perspective. We derive new geometric results on the reach for submanifolds without boundary. An estimator $\hat{\tau }$ of $\tau_{M}$ is proposed in an oracle framework where tangent spaces are known, and bounds assessing its efficiency are derived. In the case of i.i.d. random point cloud $\mathbb{X}_{n}$, $\hat{\tau }(\mathbb{X}_{n})$ is showed to achieve uniform expected loss bounds over a $\mathcal{C}^{3}$-like model. Finally, we obtain upper and lower bounds on the minimax rate for estimating the reach.

Citation

Download Citation

Eddie Aamari. Jisu Kim. Frédéric Chazal. Bertrand Michel. Alessandro Rinaldo. Larry Wasserman. "Estimating the reach of a manifold." Electron. J. Statist. 13 (1) 1359 - 1399, 2019. https://doi.org/10.1214/19-EJS1551

Information

Received: 1 March 2018; Published: 2019
First available in Project Euclid: 12 April 2019

zbMATH: 07056154
MathSciNet: MR3938326
Digital Object Identifier: 10.1214/19-EJS1551

Subjects:
Primary: 62G05
Secondary: 62C20 , 68U05

Keywords: Geometric inference , minimax risk , reach

Vol.13 • No. 1 • 2019
Back to Top