Bootstrapping persistent Betti numbers and other stabilizing statistics

DOI10.1214/23-AOS2277MaRDI QIDQ6183746zbMATH OpenOpenAlexFDO

Authors Benjamin Roycraft, Johannes T. N. Krebs, Wolfgang Polonik

Publication date 4 January 2024

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

Full work available at URL https://arxiv.org/abs/2005.01417, https://projecteuclid.org/journals/annals-of-statistics/volume-51/issue-4/Bootstrapping-persistent-Betti-numbers-and-other-stabilizing-statistics/10.1214/23-AOS2277.full

zbMATH Keywords

Betti numbersbootstrapEuler characteristicpersistent homologyrandom geometric complexesstabilizing statisticsstochastic geometrytopological data analysis

Mathematics Subject Classification ID

Persistent homology and applications, topological data analysis (55N31) Bootstrap, jackknife and other resampling methods (62F40) Nonparametric estimation (62G05) Multivariate distribution of statistics (62H10) Topological data analysis (62R40)

Abstract: The present contribution investigates multivariate bootstrap procedures for general stabilizing statistics, with specific application to topological data analysis. Existing limit theorems for topological statistics prove difficult to use in practice for the construction of confidence intervals, motivating the use of the bootstrap in this capacity. However, the standard nonparametric bootstrap does not directly provide for asymptotically valid confidence intervals in some situations. A smoothed bootstrap procedure, instead, is shown to give consistent estimation in these settings. The present work relates to other general results in the area of stabilizing statistics, including central limit theorems for functionals of Poisson and Binomial processes in the critical regime. Specific statistics considered include the persistent Betti numbers of v{C}ech and Vietoris-Rips complexes over point sets in $mathbb{R}^d$, along with Euler characteristics, and the total edge length of the $k$-nearest neighbor graph. Special emphasis is made throughout to weakening the necessary conditions needed to establish bootstrap consistency. In particular, the assumption of a continuous underlying density is not required. A simulation study is provided to assess the performance of the smoothed bootstrap for finite sample sizes, and the method is further applied to the cosmic web dataset from the Sloan Digital Sky Survey (SDSS). Source code is available at github.com/btroycraft/stabilizing_statistics_bootstrap.

Recommendations

• On approximation theorems for the Euler characteristic with applications to the bootstrap
• Statistical topology via Morse theory, persistence and nonparametric estimation
• Stochastic convergence of persistence landscapes and silhouettes
• Stochastic convergence of persistence landscapes and silhouettes
• Topological consistency via kernel estimation

Cites work

• A statistical approach to persistent homology
• Analysis of Kolmogorov flow and Rayleigh-Bénard convection using persistent homology
• Applications of computational homology to the analysis of treatment response in breast cancer patients
• Central limit theorems for some graphs in computational geometry.
• Computing persistent homology
• Confidence sets for persistence diagrams
• Coverage in sensor networks via persistent homology
• Geometric and topological inference
• scientific article; zbMATH DE number 4001209 (Why is no real title available?)
• Limit theorems for Betti numbers of extreme sample clouds with application to persistence barcodes
• Limit theorems for persistence diagrams
• Limit theorems for point processes under geometric constraints (and topological crackle)
• Modeling and replicating statistical topology and evidence for CMB nonhomogeneity
• Normal approximation for stabilizing functionals
• Normal approximation on Poisson spaces: Mehler's formula, second order Poincaré inequalities and stabilization
• On approximation theorems for the Euler characteristic with applications to the bootstrap
• On central limit theorems in stochastic geometry for add-one cost stabilizing functionals
• On the topology of random complexes built over stationary point processes
• Persistence curves: a canonical framework for summarizing persistence diagrams
• Persistent homology transform for modeling shapes and surfaces
• Predicting clinical outcomes in glioblastoma: an application of topological and functional data analysis
• Quantifying force networks in particulate systems
• Quantitative two-scale stabilization on the Poisson space
• Random geometric complexes in the thermodynamic regime
• Statistical topological data analysis using persistence landscapes
• Stochastic convergence of persistence landscapes and silhouettes
• Subsampling
• Testing goodness of fit for point processes via topological data analysis
• The density of expected persistence diagrams and its kernel based estimation
• The topology of probability distributions on manifolds
• Topological persistence and simplification
• Weak laws of large numbers in geometric probability

Cited in

(4)

• Stampedes I: fishnet OPE and octagon bootstrap with nonzero bridges
• Randomness of Shapes and Statistical Inference on Shapes via the Smooth Euler Characteristic Transform
• A geometric condition for uniqueness of Fréchet means of persistence diagrams
• On the limits of topological data analysis for statistical inference

This page was built for publication: Bootstrapping persistent Betti numbers and other stabilizing statistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6183746)