Theoretical analysis of nonparametric filament estimation

DOI10.1214/15-AOS1405MaRDI QIDQ292890zbMATH OpenOpenAlexFDO

Authors Wanli Qiao, Wolfgang Polonik

Publication date 9 June 2016

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1510.07105, https://projecteuclid.org/euclid.aos/1460381693

zbMATH Keywords

extreme value distributionintegral curveskernel density estimationnonparametric curve estimation

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Abstract: This paper provides a rigorous study of the nonparametric estimation of filaments or ridge lines of a probability density $f$. Points on the filament are considered as local extrema of the density when traversing the support of $f$ along the integral curve driven by the vector field of second eigenvectors of the Hessian of $f$. We `parametrize' points on the filaments by such integral curves, and thus both the estimation of integral curves and of filaments will be considered via a plug-in method using kernel density estimation. We establish rates of convergence and asymptotic distribution results for the estimation of both the integral curves and the filaments. The main theoretical result establishes the asymptotic distribution of the uniform deviation of the estimated filament from its theoretical counterpart. This result utilizes the extreme value behavior of non-stationary Gaussian processes indexed by manifolds $M_h,hin(0,1]$ as $ho0$.

Recommendations

• The geometry of nonparametric filament estimation
• Posterior contraction and credible sets for filaments of regression functions
• On the path density of a gradient field
• Asymptotic confidence regions for density ridges
• Asymptotic theory for density ridges

Cites work

• Adaptive multiscale detection of filamentary structures in a background of uniform random points
• Asymptotic theory for density ridges
• Extrema of rescaled locally stationary Gaussian fields on manifolds
• scientific article; zbMATH DE number 1055632 (Why is no real title available?)
• scientific article; zbMATH DE number 1894348 (Why is no real title available?)
• Integral curves of noisy vector fields and statistical problems in diffusion tensor imaging: nonparametric kernel estimation and hypotheses testing
• Locally defined principal curves and surfaces
• Manifold estimation and singular deconvolution under Hausdorff loss
• Nonparametric ridge estimation
• On some global measures of the deviations of density function estimates
• On the maximal deviation of k-dimensional density estimates
• On the path density of a gradient field
• Principal Curves
• Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
• Ridges in image and data analysis
• The estimation of the gradient of a density function, with applications in pattern recognition
• The geometry of nonparametric filament estimation
• Theoretical analysis of nonparametric filament estimation
• Uniform in bandwidth consistency of kernel-type function estimators
• Weak convergence and empirical processes. With applications to statistics

Cited in

(15)

• On the path density of a gradient field
• Posterior contraction rates of density derivative estimation
• Asymptotic confidence regions for density ridges
• Space partitioning and regression maxima seeking via a mean-shift-inspired algorithm
• Posterior contraction and credible sets for filaments of regression functions
• Asymptotic confidence sets for the jump curve in bivariate regression problems
• Univariate log-concave density estimation with symmetry or modal constraints
• Theoretical analysis of nonparametric filament estimation
• Limit laws on extremes of nonhomogeneous Gaussian random fields
• The geometry of nonparametric filament estimation
• Confidence regions for filamentary structures
• Clustering by Hill-climbing: consistency results
• Toroidal PCA via density ridges
• On nonparametric ridge estimation for multivariate long-memory processes
• Asymptotic theory for density ridges

This page was built for publication: Theoretical analysis of nonparametric filament estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q292890)