Learning on Persistence Diagrams as Radon Measures

TL;DR

This paper introduces a method to approximate continuous functions on Radon measures derived from persistence diagrams, enabling improved supervised learning by leveraging polynomial feature combinations.

Contribution

It develops a novel approximation framework for functions on Radon measures of persistence diagrams, enhancing topological data analysis in supervised learning.

Findings

Effective approximation of continuous functions on Radon measures.

Successful application to various supervised learning tasks.

Insights into the structure of measure spaces supporting the methods.

Abstract

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.