Detection of low dimensionality and data denoising via set estimation techniques

DOI10.1214/17-EJS1370zbMATH Open1383.62078arXiv1702.05193OpenAlexW2963997082WikidataQ125339363 ScholiaQ125339363MaRDI QIDQ1684151FDOQ1684151

Authors: C. Aaron, Alejandro Cholaquidis, Antonio Cuevas Edit this on Wikidata

Publication date: 8 December 2017

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: This work is closely related to the theories of set estimation and manifold estimation. Our object of interest is a, possibly lower-dimensional, compact set $Ssubset{mathbbR}^d$. The general aim is to identify (via stochastic procedures) some qualitative or quantitative features of $S$, of geometric or topological character. The available information is just a random sample of points drawn on $S$. The term "to identify" means here to achieve a correct answer almost surely (a.s.) when the sample size tends to infinity. More specifically the paper aims at giving some partial answers to the following questions: is $S$ full dimensional? Is $S$ "close to a lower dimensional set" $mathcalM$? If so, can we estimate $mathcalM$ or some functionals of $mathcalM$ (in particular, the Minkowski content of $mathcalM$)? As an important auxiliary tool in the answers of these questions, a denoising procedure is proposed in order to partially remove the noise in the original data. The theoretical results are complemented with some simulations and graphical illustrations.

Full work available at URL: https://arxiv.org/abs/1702.05193

Recommendations

• Set estimation and nonparametric detection.
• On signal detection and confidence sets for low rank inference problems
• A confidence-set approach to signal denoising
• Denoising point sets via \(L_0\) minimization
• Detecting weak signals in high dimensions
• Low-rank outlier detection
• A computable plug-in estimator of minimum volume sets for novelty detection
• scientific article; zbMATH DE number 5901171

zbMATH Keywords

Minkowski contentboundary estimationdenoising procedure

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Geometric probability and stochastic geometry (60D05)

Cited In (6)

• Universally consistent estimation of the reach
• On boundary detection
• On semi-supervised learning
• On the notion of polynomial reach: a statistical application
• Estimation of surface area
• Deconvolution of spherical data corrupted with unknown noise

This page was built for publication: Detection of low dimensionality and data denoising via set estimation techniques

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1684151)