Slicing Unbalanced Optimal Transport

TL;DR

This paper introduces a novel framework combining sliced and unbalanced optimal transport to efficiently compare positive measures, with new algorithms and empirical validation on synthetic and real datasets.

Contribution

It develops a general, GPU-friendly framework for sliced unbalanced OT, including two variants, and analyzes their properties and applications.

Findings

Efficient GPU-compatible algorithms for sliced unbalanced OT.

The proposed methods are computationally efficient and applicable to real-world data.

Empirical results demonstrate relevance and robustness in geophysical and synthetic datasets.

Abstract

Optimal transport (OT) is a powerful framework to compare probability measures, a fundamental task in many statistical and machine learning problems. Substantial advances have been made in designing OT variants which are either computationally and statistically more efficient or robust. Among them, sliced OT distances have been extensively used to mitigate optimal transport's cubic algorithmic complexity and curse of dimensionality. In parallel, unbalanced OT was designed to allow comparisons of more general positive measures, while being more robust to outliers. In this paper, we bridge the gap between those two concepts and develop a general framework for efficiently comparing positive measures. We notably formulate two different versions of sliced unbalanced OT, and study the associated topology and statistical properties. We then develop a GPU-friendly Frank-Wolfe like algorithm to compute the corresponding loss functions, and show that the resulting methodology is modular as it encompasses and extends prior related work. We finally conduct an empirical analysis of our loss functions and methodology on both synthetic and real datasets, to illustrate their computational efficiency, relevance and applicability to real-world scenarios including geophysical data.