Saved in:
Bibliographic Details
Main Authors: Acciaio, Beatrice, Hou, Songyan, Pammer, Gudmund
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.22421
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912665515851776
author Acciaio, Beatrice
Hou, Songyan
Pammer, Gudmund
author_facet Acciaio, Beatrice
Hou, Songyan
Pammer, Gudmund
contents The adapted Wasserstein ($AW$) distance refines the classical Wasserstein ($W$) distance by incorporating the temporal structure of stochastic processes. This makes the $AW$-distance well-suited as a robust distance for many dynamic stochastic optimization problems where the classical $W$-distance fails. However, estimating the $AW$-distance is a notably challenging task, compared to the classical $W$-distance. In the present work, we build a sharp estimate for the $AW$-distance in terms of the $W$-distance, for smooth measures. This reduces estimating the $AW$-distance to estimating the $W$-distance, where many well-established classical results can be leveraged. As an application, we prove a fast convergence rate of the kernel-based empirical estimator under the $AW$-distance, which approaches the Monte-Carlo rate ($n^{-1/2}$) in the regime of highly regular densities. These results are accomplished by deriving a sharp bi-Lipschitz estimate of the adapted total variation distance by the classical total variation distance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22421
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Estimating causal distances with non-causal ones
Acciaio, Beatrice
Hou, Songyan
Pammer, Gudmund
Probability
The adapted Wasserstein ($AW$) distance refines the classical Wasserstein ($W$) distance by incorporating the temporal structure of stochastic processes. This makes the $AW$-distance well-suited as a robust distance for many dynamic stochastic optimization problems where the classical $W$-distance fails. However, estimating the $AW$-distance is a notably challenging task, compared to the classical $W$-distance. In the present work, we build a sharp estimate for the $AW$-distance in terms of the $W$-distance, for smooth measures. This reduces estimating the $AW$-distance to estimating the $W$-distance, where many well-established classical results can be leveraged. As an application, we prove a fast convergence rate of the kernel-based empirical estimator under the $AW$-distance, which approaches the Monte-Carlo rate ($n^{-1/2}$) in the regime of highly regular densities. These results are accomplished by deriving a sharp bi-Lipschitz estimate of the adapted total variation distance by the classical total variation distance.
title Estimating causal distances with non-causal ones
topic Probability
url https://arxiv.org/abs/2506.22421