Unbalanced Kantorovich-Rubinstein distance, plan, and barycenter on finite spaces: A statistical perspective

2022/11/16 by Hundrieser, Shayan, Florian Heinemann, Heinemann, Florian +5 · 1 citation
Mathematics · #05C05 #62D99 #62G09 #62R20 #65C60 #90C08 #Advanced Statistical Methods and Models #FOS: Computer and information sciences #Methodology (stat.ME)

paper · pdf · doi:10.48550/arxiv.2211.08858

openalex publication_date 2022/11/16 · openalex created_date 2023/02/15 · openalex updated_date 2026/07/28

Abstract

We analyze statistical properties of plug-in estimators for unbalanced optimal transport quantities between finitely supported measures in different prototypical sampling models. Specifically, our main results provide non-asymptotic bounds on the expected error of empirical Kantorovich-Rubinstein (KR) distance, plans, and barycenters for mass penalty parameter C>0. The impact of the mass penalty parameter C is studied in detail. Based on this analysis, we mathematically justify randomized computational schemes for KR quantities which can be used for fast approximate computations in combination with any exact solver. Using synthetic and real datasets, we empirically analyze the behavior of the expected errors in simulation studies and illustrate the validity of our theoretical bounds.

Cited by

• Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions

Related

• Kantorovich-Rubinstein distance and barycenter for finitely supported measures: Foundations and Algorithms
• Unbalanced Optimal Transport: Dynamic and Kantorovich Formulation
• Sample complexity of optimal transport barycenters with discrete support
• Estimation of Wasserstein distances in the Spiked Transport Model
• An improved central limit theorem for the empirical sliced Wasserstein distance