Sharp Convergence Rates of Empirical Unbalanced Optimal Transport for Spatio-Temporal Point Processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Struleva, Marina, Hundrieser, Shayan, Schuhmacher, Dominic, Munk, Axel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914022477004800
author Struleva, Marina
Hundrieser, Shayan
Schuhmacher, Dominic
Munk, Axel
author_facet Struleva, Marina
Hundrieser, Shayan
Schuhmacher, Dominic
Munk, Axel
contents We statistically analyze empirical plug-in estimators for unbalanced optimal transport (UOT) formalisms, focusing on the Kantorovich-Rubinstein distance, between general intensity measures based on observations from spatio-temporal point processes. Specifically, we model the observations by two weakly time-stationary point processes with spatial intensity measures $μ$ and $ν$ over the expanding window $(0,t]$ as $t$ increases to infinity, and establish sharp convergence rates of the empirical UOT in terms of the intrinsic dimensions of the measures. We assume a sub-quadratic temporal growth condition of the variance of the process, which allows for a wide range of temporal dependencies. As the growth approaches quadratic, the convergence rate becomes slower. This variance assumption is related to the time-reduced factorial covariance measure, and we exemplify its validity for various point processes, including the Poisson cluster, Hawkes, Neyman-Scott, and log-Gaussian Cox processes. Complementary to our upper bounds, we also derive matching lower bounds for various spatio-temporal point processes of interest and establish near minimax rate optimality of the empirical Kantorovich-Rubinstein distance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sharp Convergence Rates of Empirical Unbalanced Optimal Transport for Spatio-Temporal Point Processes
Struleva, Marina
Hundrieser, Shayan
Schuhmacher, Dominic
Munk, Axel
Statistics Theory
Machine Learning
primary 62G05, 62G07, 62R20, secondary: 60D05, 60G60
We statistically analyze empirical plug-in estimators for unbalanced optimal transport (UOT) formalisms, focusing on the Kantorovich-Rubinstein distance, between general intensity measures based on observations from spatio-temporal point processes. Specifically, we model the observations by two weakly time-stationary point processes with spatial intensity measures $μ$ and $ν$ over the expanding window $(0,t]$ as $t$ increases to infinity, and establish sharp convergence rates of the empirical UOT in terms of the intrinsic dimensions of the measures. We assume a sub-quadratic temporal growth condition of the variance of the process, which allows for a wide range of temporal dependencies. As the growth approaches quadratic, the convergence rate becomes slower. This variance assumption is related to the time-reduced factorial covariance measure, and we exemplify its validity for various point processes, including the Poisson cluster, Hawkes, Neyman-Scott, and log-Gaussian Cox processes. Complementary to our upper bounds, we also derive matching lower bounds for various spatio-temporal point processes of interest and establish near minimax rate optimality of the empirical Kantorovich-Rubinstein distance.
title Sharp Convergence Rates of Empirical Unbalanced Optimal Transport for Spatio-Temporal Point Processes
topic Statistics Theory
Machine Learning
primary 62G05, 62G07, 62R20, secondary: 60D05, 60G60
url https://arxiv.org/abs/2509.04225