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

DOI10.1051/PS/2022003zbMATH Open1490.62095arXiv1910.14458OpenAlexW2982287550MaRDI QIDQ3389501FDOQ3389501

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

Publication date: 23 March 2022

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

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.

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

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

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)

Cites Work

• A plug-in approach to support estimation
• Asymptotical minimax recovery of sets with smooth boundaries
• On statistical properties of sets fulfilling rolling-type conditions
• A Limit Theorem for Solutions of Inequalities
• Detection of Abnormal Behavior Via Nonparametric Estimation of the Support
• On boundary estimation
• Theory of Reproducing Kernels
• On nonparametric estimation of density level sets
• PLUG-IN ESTIMATION OF GENERAL LEVEL SETS
• Title not available (Why is that?)
• Optimal rates for plug-in estimators of density level sets
• Granulometric smoothing
• Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
• Orthogonal polynomials of several variables
• On Poincaré cone property
• Local convex hull support and boundary estimation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Set estimation under convexity type assumptions
• Summability of Fourier orthogonal series for Jacobi weight on a ball in ℝ^{𝕕}
• Fekete points and convergence towards equilibrium measures on complex manifolds
• Real analysis
• Christoffel functions and universality on the boundary of the ball
• Christoffel functions and universality in the bulk for multivariate orthogonal polynomials
• Adaptive Hausdorff estimation of density level sets
• Asymptotics for Christoffel functions for general measures on the real line
• �ber die konvexe H�lle von n zuf�llig gew�hlten Punkten
• Title not available (Why is that?)
• Title not available (Why is that?)
• Exact rates in density support estimation
• Asymptotics of the Christoffel functions on a simplex in \(\mathbb{R}^d\)
• Title not available (Why is that?)
• On the shape of a set of points in the plane
• Data analysis from empirical moments and the Christoffel function
• Adaptation to lowest density regions with application to support recovery
• The empirical Christoffel function with applications in data analysis
• Semi-algebraic approximation using Christoffel-Darboux kernel

Cited In (2)

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

Uses Software

• UCI-ml

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)