Preprint 66/2017

Tropical Sufficient Statistics for Persistent Homology

Anthea Monod, Sara Kališnik Verovšek, Juan Ángel Patiño-Galindo, and Lorin Crawford

Contact the author: Please use for correspondence this email.
Submission date: 04. Oct. 2017
Pages: 24
published in: SIAM journal on applied algebra and geometry, 3 (2019) 2, p. 337-371 
DOI number (of the published article): 10.1137/17M1148037
Download full preprint: PDF (525 kB)

In this paper, we show that an embedding in Euclidean space based on tropical algebraic geometry generates stable sufficient statistics for barcodes. Conventionally, barcodes are multiscale summaries of topological characteristics that capture the "shape" of data; however, in practice, they have complex structures which make them difficult to use in statistical settings. The sufficiency result presented in this work allows for classical probability distributions to be assumed on the tropicalized representation of barcodes. This makes a variety of parametric statistical inference methods amenable to barcodes, all while maintaining their initial interpretations. More specifically, we show that exponential family distributions may be assumed, and that likelihood functions for persistent homology may be constructed. We conceptually demonstrate sufficiency and illustrate its utility in persistent homology dimensions 0 and 1 with concrete parametric applications to HIV and avian influenza data.

18.12.2019, 02:40