Manifold estimation and singular deconvolution under Hausdorff loss

DOI10.1214/12-AOS994zbMath1274.62237arXiv1109.4540OpenAlexW3105264615WikidataQ126021012 ScholiaQ126021012MaRDI QIDQ447839

Marco Perone-Pacifico, Isabella Verdinelli, Christopher R. Genovese, Larry Alan Wasserman

Publication date: 29 August 2012

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

Full work available at URL: https://arxiv.org/abs/1109.4540

zbMATH Keywords

minimaxdeconvolutionmanifold learning

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Asymptotic properties of nonparametric inference (62G20) Nonparametric estimation (62G05)

Related Items

Reconstruction of a Riemannian Manifold from Noisy Intrinsic Distances, Obtaining minimax lower bounds: a review, Theoretical analysis of nonparametric filament estimation, Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning, Rates of convergence for robust geometric inference, Stability and minimax optimality of tangential Delaunay complexes for manifold reconstruction, Overview of object oriented data analysis, Different perspectives on object oriented data analysis, Data analysis from empirical moments and the Christoffel function, A geometrically motivated parametric model in manifold estimation, Posterior contraction and credible sets for filaments of regression functions, Minimax rates of convergence for Wasserstein deconvolution with supersmooth errors in any dimension, Asymptotic theory for density ridges, Adversarial manifold estimation, Optimal reach estimation and metric learning, Deep nonparametric estimation of intrinsic data structures by chart autoencoders: generalization error and robustness, Reconstruction of manifold embeddings into Euclidean spaces via intrinsic distances, Minimax rate of distribution estimation on unknown submanifolds under adversarial losses, Statistical embedding: beyond principal components, Deconvolution of spherical data corrupted with unknown noise, Manifold energy two-sample test, A \(k\)-points-based distance for robust geometric inference, Reconstruction and interpolation of manifolds. I: The geometric Whitney problem, Nonparametric ridge estimation, Methods for estimation of convex sets, On boundary detection, Nonasymptotic rates for manifold, tangent space and curvature estimation, Tight minimax rates for manifold estimation under Hausdorff loss, Remember the curse of dimensionality: the case of goodness-of-fit testing in arbitrary dimension, Unnamed Item, Statistical Analysis and Parameter Selection for Mapper, Testing the manifold hypothesis, Estimation of convex supports from noisy measurements, Minimax adaptive estimation in manifold inference, Normal-Bundle Bootstrap

Cites Work

• Unnamed Item
• Unnamed Item
• On the optimal rates of convergence for nonparametric deconvolution problems
• Random projections of smooth manifolds
• Laws of large numbers for classes of functions
• Rates of convergence of some estimators in a class of deconvolution problems
• Nonparametric regression with errors in variables
• Empirical geometry of multivariate data: a deconvolution approach.
• Deconvolution for the Wasserstein metric and geometric inference
• Finding the homology of submanifolds with high confidence from random samples
• Estimating the support of multivariate densities under measurement error
• A Topological View of Unsupervised Learning from Noisy Data
• Curvature Measures
• Curve and Surface Reconstruction
• Minimax Manifold Estimation
• Advanced Lectures on Machine Learning
• Connect the dots: how many random points can a regular curve pass through?