Optimal reach estimation and metric learning

DOI10.1214/23-AOS2281MaRDI QIDQ6136583zbMATH OpenFDO

Authors Eddie Aamari, Clément Berenfeld, Clément Levrard

Publication date 31 August 2023

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

Full work available at URL https://arxiv.org/abs/2207.06074, https://projecteuclid.org/journals/annals-of-statistics/volume-51/issue-3/Optimal-reach-estimation-and-metric-learning/10.1214/23-AOS2281.full

zbMATH Keywords

manifold learningminimax riskmetric learninggeometric inferencereach

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Minimax procedures in statistical decision theory (62C20) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Abstract: We study the estimation of the reach, an ubiquitous regularity parameter in manifold estimation and geometric data analysis. Given an i.i.d. sample over an unknown $d$-dimensional $mathcal{C}^k$-smooth submanifold of $mathbb{R}^D$, we provide optimal nonasymptotic bounds for the estimation of its reach. We build upon a formulation of the reach in terms of maximal curvature on one hand, and geodesic metric distortion on the other hand. The derived rates are adaptive, with rates depending on whether the reach of $M$ arises from curvature or from a bottleneck structure. In the process, we derive optimal geodesic metric estimation bounds.

Recommendations

• Estimating the reach of a manifold
• Universally consistent estimation of the reach
• Nonasymptotic rates for manifold, tangent space and curvature estimation
• Density estimation on an unknown submanifold
• Minimax adaptive estimation in manifold inference

Cites work

• scientific article; zbMATH DE number 6378006 (Why is no real title available?)
• scientific article; zbMATH DE number 5286897 (Why is no real title available?)
• scientific article; zbMATH DE number 5506223 (Why is no real title available?)
• scientific article; zbMATH DE number 823375 (Why is no real title available?)
• scientific article; zbMATH DE number 7625193 (Why is no real title available?)
• Approximation of functions over manifolds: a moving least-squares approach
• Convergence rates for persistence diagram estimation in topological data analysis
• Curvature Measures
• Estimating the reach of a manifold
• Estimating the reach of a manifold via its convexity defect function
• Geometric inference for probability measures
• Local differentiability of distance functions
• Local regularization of noisy point clouds: improved global geometric estimates and data analysis
• Manifold estimation and singular deconvolution under Hausdorff loss
• Manifold reconstruction using tangential Delaunay complexes
• Minimax adaptive estimation in manifold inference
• Minimax manifold estimation
• Nonasymptotic rates for manifold, tangent space and curvature estimation
• On Lipschitz embedding of finite metric spaces in Hilbert space
• Optimal reach estimation and metric learning
• Supervised distance metric learning through maximization of the Jeffrey divergence
• The reach, metric distortion, geodesic convexity and the variation of tangent spaces
• The “λ-medial axis”
• Tight minimax rates for manifold estimation under Hausdorff loss
• Unconstrained and curvature-constrained shortest-path distances and their approximation
• Universally consistent estimation of the reach
• Vietoris-Rips complexes also provide topologically correct reconstructions of sampled shapes

Cited in

(2)

• Optimal reach estimation and metric learning
• Computable bounds for the reach and \(r\)-convexity of subsets of \({{\mathbb{R}}}^d\)

This page was built for publication: Optimal reach estimation and metric learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136583)