Electronic Journal of Statistics
- Electron. J. Statist.
- Volume 10, Number 2 (2016), 2243-2286.
Rates of convergence for robust geometric inference
Distances to compact sets are widely used in the field of Topological Data Analysis for inferring geometric and topological features from point clouds. In this context, the distance to a probability measure (DTM) has been introduced by Chazal et al., 2011b as a robust alternative to the distance a compact set. In practice, the DTM can be estimated by its empirical counterpart, that is the distance to the empirical measure (DTEM). In this paper we give a tight control of the deviation of the DTEM. Our analysis relies on a local analysis of empirical processes. In particular, we show that the rate of convergence of the DTEM directly depends on the regularity at zero of a particular quantile function which contains some local information about the geometry of the support. This quantile function is the relevant quantity to describe precisely how difficult is a geometric inference problem. Several numerical experiments illustrate the convergence of the DTEM and also confirm that our bounds are tight.
Electron. J. Statist., Volume 10, Number 2 (2016), 2243-2286.
Received: March 2016
First available in Project Euclid: 25 August 2016
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Primary: 62G05: Estimation
Secondary: 62G30: Order statistics; empirical distribution functions 68U05: Computer graphics; computational geometry [See also 65D18] 62-07: Data analysis 28A33: Spaces of measures, convergence of measures [See also 46E27, 60Bxx]
Chazal, Frédéric; Massart, Pascal; Michel, Bertrand. Rates of convergence for robust geometric inference. Electron. J. Statist. 10 (2016), no. 2, 2243--2286. doi:10.1214/16-EJS1161. https://projecteuclid.org/euclid.ejs/1472125729