Robust statistics, hypothesis testing, and confidence intervals for persistent homology on metric measure spaces

2012/06/20 by Blumberg, Andrew J., Gal, Itamar, Mandell, Michael A. +1
#Computational Geometry (cs.CG) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1206.4581

Abstract

We study distributions of persistent homology barcodes associated to taking subsamples of a fixed size from metric measure spaces. We show that such distributions provide robust invariants of metric measure spaces, and illustrate their use in hypothesis testing and providing confidence intervals for topological data analysis.

Related

• A Topological Study of Functional Data and Fréchet Functions of Metric Measure Spaces
• Intrinsic persistent homology via density-based metric learning
• Robust Topological Inference: Distance To a Measure and Kernel Distance
• Adversarially Robust Topological Inference
• Optimal rates of convergence for persistence diagrams in Topological Data Analysis