Persistence barcodes versus Kolmogorov signatures: detecting modes of one-dimensional signals

DOI10.1007/S10208-015-9281-9MaRDI QIDQ525596zbMATH OpenOpenAlexFDO

Authors Ulrich Bauer, Axel Munk, Hannes Sieling, M. Wardetzky

Publication date 5 May 2017

Published in Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1404.1214

zbMATH Keywords

persistent homologycritical pointspartial sum processtaut stringsmode huntingbarcodesexponential deviation boundKolmogorov signatures

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Estimation in multivariate analysis (62H12) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Critical points and critical submanifolds in differential topology (57R70) Abstract critical point theory (Morse theory, Lyusternik-Shnirel'man theory, etc.) in infinite-dimensional spaces (58E05)

Abstract: We investigate the problem of estimating the number of modes (i.e., local maxima) - a well known question in statistical inference - and we show how to do so without presmoothing the data. To this end, we modify the ideas of persistence barcodes by first relating persistence values in dimension one to distances (with respect to the supremum norm) to the sets of functions with a given number of modes, and subsequently working with norms different from the supremum norm. As a particular case we investigate the Kolmogorov norm. We argue that this modification has certain statistical advantages. We offer confidence bands for the attendant Kolmogorov signatures, thereby allowing for the selection of relevant signatures with a statistically controllable error. As a result of independent interest, we show that taut strings minimize the number of critical points for a very general class of functions. We illustrate our results by several numerical examples.

Recommendations

• Confidence sets for persistence diagrams
• Counting bumps
• Statistical topology via Morse theory, persistence and nonparametric estimation
• Topological consistency via kernel estimation
• Statistical topological data analysis using persistence landscapes

Cites work

• scientific article; zbMATH DE number 1354815 (Why is no real title available?)
• scientific article; zbMATH DE number 739533 (Why is no real title available?)
• scientific article; zbMATH DE number 847282 (Why is no real title available?)
• A statistical approach to persistent homology
• Asymptotic Statistics
• Asymptotic theory of weakly dependent stochastic processes
• Computational topology. An introduction
• Confidence sets for persistence diagrams
• Densities, spectral densities and modality.
• Density Estimation and Bump-Hunting by the Penalized Likelihood Method Exemplified by Scattering and Meteorite Data
• Detection with the scan and the average likelihood ratio
• Empirical Processes with Applications to Statistics
• Generalizations of the Taut String Method
• Geometric inference for probability measures
• Higher criticism for detecting sparse heterogeneous mixtures.
• Improving homology estimates with random walks
• Local extremes, runs, strings and multiresolution. (With discussion)
• Locally adaptive regression splines
• Nonparametric goodness-of-fit testing under Gaussian models
• One-sided inference about functionals of a density
• Optimal topological simplification of discrete functions on surfaces
• Stability of persistence diagrams
• Statistical topology via Morse theory, persistence and nonparametric estimation
• The dip test of unimodality
• The equivalence of the taut string algorithm and BV-regularization
• Topological persistence and simplification

Cited in

(3)

• Amplitudes in persistence theory
• Boundedness and unboundedness in total variation regularization
• Topological data analysis for true step detection in periodic piecewise constant signals

Describes a project that uses

Uses Software

• KernSmooth
• ftnonpar

This page was built for publication: Persistence barcodes versus Kolmogorov signatures: detecting modes of one-dimensional signals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q525596)