Convergence of Empirical Optimal Transport in Unbounded Settings

arXiv2306.11499MaRDI QIDQ6510657FDOQ6510657

Authors: Thomas Staudt, Shayan Hundrieser 

Abstract: In compact settings, the convergence rate of the empirical optimal transport cost to its population value is well understood for a wide class of spaces and cost functions. In unbounded settings, however, hitherto available results require strong assumptions on the ground costs and the concentration of the involved measures. In this work, we pursue a decomposition-based approach to generalize the convergence rates found in compact spaces to unbounded settings under generic moment assumptions that are sharp up to an arbitrarily small $epsilon>0$. Hallmark properties of empirical optimal transport on compact spaces, like the recently established adaptation to lower complexity, are shown to carry over to the unbounded case.

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Asymptotic properties of nonparametric inference (62G20) Statistical aspects of big data and data science (62R07) Optimal transportation (49Q22) Robustness and adaptive procedures (parametric inference) (62F35)

This page was built for publication: Convergence of Empirical Optimal Transport in Unbounded Settings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6510657)