Universally consistent estimation of the reach

10/23/2021
by   Alejandro Cholaquidis, et al.
0

The reach of a set M ⊂ℝ^d, also known as condition number when M is a manifold, was introduced by Federer in 1959 and is a central concept in geometric measure theory, set estimation, manifold learning, among others areas. We introduce a universally consistent estimate of the reach, just assuming that the reach is positive. A necessary condition for the universal convergence of the reach is that the Haussdorf distance between the sample and the set converges to zero. Without further assumptions we show that the convergence rate of this distance can be arbitrarily slow. However, under a weak additional assumption, we provide rates of convergence for the reach estimator. We also show that it is not possible to determine if the reach of the support of a density is zero or not based on a finite sample. We provide a small simulation study and a bias correction method for the case when M is a manifold.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/13/2022

Optimal Reach Estimation and Metric Learning

We study the estimation of the reach, an ubiquitous regularity parameter...
research
07/01/2023

On the notion of polynomial reach: a statistical application

The volume function V(t) of a compact set S∈R^d is just the Lebesgue mea...
research
06/28/2023

On standardness and the non-estimability of certain functionals of a set

Standardness is a popular assumption in the literature on set estimation...
research
06/21/2022

Optimal homotopy reconstruction results à la Niyogi, Smale, and Weinberger

In this article we show that the proof of the homotopy reconstruction re...
research
06/03/2022

Is an encoder within reach?

The encoder network of an autoencoder is an approximation of the nearest...
research
09/05/2022

Effective Estimation of the Dimensions of a Manifold from Random Samples

We give explicit theoretical and heuristical bounds for how big does a d...
research
07/16/2021

Non-Parametric Manifold Learning

We introduce an estimator for manifold distances based on graph Laplacia...

Please sign up or login with your details

Forgot password? Click here to reset