Rates of convergence for robust geometric inference
From MaRDI portal
Abstract: Distances to compact sets are widely used in the field of Topological Data Analysis for inferring geometric and topological features from point clouds. In this context, the distance to a probability measure (DTM) has been introduced by Chazal et al. (2011) as a robust alternative to the distance a compact set. In practice, the DTM can be estimated by its empirical counterpart, that is the distance to the empirical measure (DTEM). In this paper we give a tight control of the deviation of the DTEM. Our analysis relies on a local analysis of empirical processes. In particular, we show that the rates of convergence of the DTEM directly depends on the regularity at zero of a particular quantile fonction which contains some local information about the geometry of the support. This quantile function is the relevant quantity to describe precisely how difficult is a geometric inference problem. Several numerical experiments illustrate the convergence of the DTEM and also confirm that our bounds are tight.
Recommendations
Cites work
- A weighted \(k\)-nearest neighbor density estimate for geometric inference
- Adaptive Hausdorff estimation of density level sets
- Adaptive multiscale detection of filamentary structures in a background of uniform random points
- Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator
- Asymptotics for L₂ functionals of the empirical quantile process, with applications to tests of fit based on weighted Wasserstein distances
- Central limit theorems for the Wasserstein distance between the empirical and the true distributions
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- Confidence sets for persistence diagrams
- Constructive quantization: approximation by empirical measures
- Convergence rates for persistence diagram estimation in topological data analysis
- Deconvolution for the Wasserstein metric and geometric inference
- Detection of Abnormal Behavior Via Nonparametric Estimation of the Support
- Efficient and robust persistent homology for measures
- Empirical Processes with Applications to Statistics
- Finding the homology of submanifolds with high confidence from random samples
- Geometric inference for probability measures
- Geometric inference on kernel density estimates
- scientific article; zbMATH DE number 1064667 (Why is no real title available?)
- Inequalities for E k(X, Y) when the marginals are fixed
- Manifold estimation and singular deconvolution under Hausdorff loss
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Normal cone approximation and offset shape isotopy
- On boundary estimation
- On the path density of a gradient field
- On the rate of convergence in Wasserstein distance of the empirical measure
- Optimal Transport
- Persistence-based clustering in Riemannian manifolds
- Principal Curves
- Smooth discrimination analysis
- Smooth manifold reconstruction from noisy and non-uniform approximation with guarantees
- Stochastic convergence of persistence landscapes and silhouettes
- The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality
- Topological analysis of scalar fields with outliers
- Topology and data
- Witnessed k-distance
Cited in
(12)- Analyzing the squared distance-to-measure gradient flow system with k-order Voronoi diagrams
- Intrinsic dimension of geometric data sets
- Reweighting samples under covariate shift using a Wasserstein distance criterion
- A \(k\)-points-based distance for robust geometric inference
- Rate of convergence for geometric inference based on the empirical Christoffel function
- Statistical analysis and parameter selection for Mapper
- Robust topological inference: distance to a measure and kernel distance
- Topological data analysis and its usefulness for precision medicine studies
- Unsupervised space-time clustering using persistent homology
- On standardness: estimation of the standardness constant and decidability aspects
- Convergence of message-passing graph neural networks with generic aggregation on large random graphs
- Detecting and modeling critical dependence structures between random inputs of computer models
This page was built for publication: Rates of convergence for robust geometric inference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309578)
