Learning on Persistence Diagrams as Radon Measures

Autor:	Elchesen, Alex, Hartsock, Iryna, Perea, Jose A., Rask, Tatum
Rok vydání:	2022
Předmět:	Computer Science - Computational Geometry Computer Science - Machine Learning Mathematics - Algebraic Topology 55N31
Druh dokumentu:	Working Paper
Popis:	Persistence diagrams are common descriptors of the topological structure of data appearing in various classification and regression tasks. They can be generalized to Radon measures supported on the birth-death plane and endowed with an optimal transport distance. Examples of such measures are expectations of probability distributions on the space of persistence diagrams. In this paper, we develop methods for approximating continuous functions on the space of Radon measures supported on the birth-death plane, as well as their utilization in supervised learning tasks. Indeed, we show that any continuous function defined on a compact subset of the space of such measures (e.g., a classifier or regressor) can be approximated arbitrarily well by polynomial combinations of features computed using a continuous compactly supported function on the birth-death plane (a template). We provide insights into the structure of relatively compact subsets of the space of Radon measures, and test our approximation methodology on various data sets and supervised learning tasks. Comment: 16 pages, 4 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.08295 Zobrazit plný text záznamu View this record from Arxiv