Rate of convergence for geometric inference based on the empirical Christoffel function

DOI10.1051/PS/2022003MaRDI QIDQ3389501zbMATH OpenOpenAlexFDO

Authors V. M. Trang, François Bachoc, Edouard Pauwels

Publication date 23 March 2022

Published in ESAIM: Probability and Statistics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1910.14458

zbMATH Keywords

support estimationconvergence rateconcentrationChristoffel functionfinite sample

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Orthogonal functions and polynomials, general theory of nontrigonometric harmonic analysis (42C05)

Abstract: We consider the problem of estimating the support of a measure from a finite, independent, sample. The estimators which are considered are constructed based on the empirical Christoffel function. Such estimators have been proposed for the problem of set estimation with heuristic justifications. We carry out a detailed finite sample analysis, that allows us to select the threshold and degree parameters as a function of the sample size. We provide a convergence rate analysis of the resulting support estimation procedure. Our analysis establishes that we may obtain finite sample bounds which are comparable to existing rates for different set estimation procedures. Our results rely on concentration inequalities for the empirical Christoffel function and on estimates of the supremum of the Christoffel-Darboux kernel on sets with smooth boundaries, that can be considered of independent interest.

Recommendations

• The empirical Christoffel function with applications in data analysis
• Optimal rates of convergence for convex set estimation from support functions
• Exact rates in density support estimation
• A plug-in approach to support estimation
• Rates of convergence for robust geometric inference

Cites work

• scientific article; zbMATH DE number 1188845 (Why is no real title available?)
• scientific article; zbMATH DE number 192895 (Why is no real title available?)
• scientific article; zbMATH DE number 3579836 (Why is no real title available?)
• scientific article; zbMATH DE number 1271910 (Why is no real title available?)
• scientific article; zbMATH DE number 770285 (Why is no real title available?)
• scientific article; zbMATH DE number 3211300 (Why is no real title available?)
• scientific article; zbMATH DE number 5055767 (Why is no real title available?)
• A Limit Theorem for Solutions of Inequalities
• A plug-in approach to support estimation
• Adaptation to lowest density regions with application to support recovery
• Adaptive Hausdorff estimation of density level sets
• Asymptotical minimax recovery of sets with smooth boundaries
• Asymptotics for Christoffel functions for general measures on the real line
• Asymptotics of the Christoffel functions on a simplex in \(\mathbb{R}^d\)
• Christoffel functions and universality in the bulk for multivariate orthogonal polynomials
• Christoffel functions and universality on the boundary of the ball
• Data analysis from empirical moments and the Christoffel function
• Detection of Abnormal Behavior Via Nonparametric Estimation of the Support
• Exact rates in density support estimation
• Fekete points and convergence towards equilibrium measures on complex manifolds
• Granulometric smoothing
• Local convex hull support and boundary estimation
• Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
• On Poincaré cone property
• On boundary estimation
• On nonparametric estimation of density level sets
• On statistical properties of sets fulfilling rolling-type conditions
• On the shape of a set of points in the plane
• Optimal rates for plug-in estimators of density level sets
• Orthogonal polynomials of several variables
• PLUG-IN ESTIMATION OF GENERAL LEVEL SETS
• Real analysis
• Semi-algebraic approximation using Christoffel-Darboux kernel
• Set estimation under convexity type assumptions
• Summability of Fourier orthogonal series for Jacobi weight on a ball in ℝ^{𝕕}
• The empirical Christoffel function with applications in data analysis
• Theory of Reproducing Kernels
• �ber die konvexe H�lle von n zuf�llig gew�hlten Punkten

Cited in

(2)

• The empirical Christoffel function with applications in data analysis
• Moment-SoS methods for optimal transport problems

Describes a project that uses

Uses Software

• UCI

This page was built for publication: Rate of convergence for geometric inference based on the empirical Christoffel function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3389501)