Optimal reach estimation and metric learning

DOI10.1214/23-AOS2281arXiv2207.06074MaRDI QIDQ6136583FDOQ6136583

Clément Levrard, Clément Berenfeld, Eddie Aamari

Publication date: 31 August 2023

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

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.

Full work available at URL: https://arxiv.org/abs/2207.06074

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)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Convergence rates for persistence diagram estimation in topological data analysis
• Curvature Measures
• Geometric inference for probability measures
• The reach, metric distortion, geodesic convexity and the variation of tangent spaces
• Vietoris-Rips complexes also provide topologically correct reconstructions of sampled shapes
• Local differentiability of distance functions
• Manifold estimation and singular deconvolution under Hausdorff loss
• On Lipschitz embedding of finite metric spaces in Hilbert space
• Minimax Manifold Estimation
• The “λ-medial axis”
• Tight minimax rates for manifold estimation under Hausdorff loss
• Nonasymptotic rates for manifold, tangent space and curvature estimation
• Manifold reconstruction using tangential Delaunay complexes
• Estimating the reach of a manifold
• Approximation of functions over manifolds: a moving least-squares approach
• Unconstrained and curvature-constrained shortest-path distances and their approximation
• Minimax adaptive estimation in manifold inference
• Supervised distance metric learning through maximization of the Jeffrey divergence
• Estimating the reach of a manifold via its convexity defect function
• Universally consistent estimation of the reach
• Optimal reach estimation and metric learning

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)