Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport

TL;DR

This paper introduces persistence spheres, an explicit, stable, and convex-geometry-based representation of measures for partial optimal transport, improving topological machine learning tasks with a parameter-free, continuous inverse map.

Contribution

It extends and refines persistence spheres to better encode partial transport, providing a stable, explicit, and convex-geometry-based measure representation with proven inverse continuity.

Findings

Competitive performance across various data types.

Often outperforms existing topological summaries.

Stable and explicit measure representation.

Abstract

We improve and extend persistence spheres, introduced in~\cite{pegoraro2025persistence}. Persistence spheres map an integrable measure $\mu$ on the upper half-plane, including persistence diagrams (PDs) as counting measures, to a function $S(\mu)\in C(\mathbb{S}^2)$, and the map is stable with respect to 1-Wasserstein partial transport distance $\mathrm{POT}_1$. Moreover, to the best of our knowledge, persistence spheres are the first explicit representation used in topological machine learning for which continuity of the inverse on the image is established at every compactly supported target. Recent bounded-cardinality bi-Lipschitz embedding results in partial transport spaces, despite being powerful, are not given by the kind of explicit summary map considered here. Our construction is rooted in convex geometry: for positive measures, the defining ReLU integral is the support function of the lift zonoid. Building on~\cite{pegoraro2025persistence}, we refine the definition to better match the $\mathrm{POT}_1$ deletion mechanism, encoding partial transport via a signed diagonal augmentation. In particular, for integrable $\mu$, the uniform norm between $S(0)$ and $S(\mu)$ depends only on the persistence of $\mu$, without any need of ad-hoc re-weightings, reflecting optimal transport to the diagonal at persistence cost. This yields a parameter-free representation at the level of measures (up to numerical discretization), while accommodating future extensions where $\mu$ is a smoothed measure derived from PDs (e.g., persistence intensity functions~\citep{wu2024estimation}). Across clustering, regression, and classification tasks involving functional data, time series, graphs, meshes, and point clouds, the updated persistence spheres are competitive and often improve upon persistence images, persistence landscapes, persistence splines, and sliced Wasserstein kernel baselines.