Preprint

Inserted: 10 jul 2025
Last Updated: 3 oct 2025

Pages: 27
Year: 2025
Notes:

10 figures

Abstract:

Unbalanced optimal transport (UOT) is a natural extension of optimal transport (OT) allowing comparison between measures of different masses. It arises naturally in machine learning by offering a robustness against outliers. The aim of this work is to provide convergence rates of the regularized transport cost and plans towards their original solution when both measures are weighted sums of Dirac masses.

Keywords: optimal transport, entropic regularization, convex analysis, asymptotic analysis

Download:

• article - convergence rate regularized unbalanced OT