Tight Bounds for Schrödinger Potential Estimation in Unpaired Data Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Puchkin, Nikita, Suchkov, Denis, Naumov, Alexey, Belomestny, Denis
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911533174358016
author Puchkin, Nikita
Suchkov, Denis
Naumov, Alexey
Belomestny, Denis
author_facet Puchkin, Nikita
Suchkov, Denis
Naumov, Alexey
Belomestny, Denis
contents Modern methods of generative modelling and unpaired data translation based on Schrödinger bridges and stochastic optimal control theory aim to transform an initial density to a target one in an optimal way. In the present paper, we assume that we only have access to i.i.d. samples from the initial and final distributions. This makes our setup suitable for both generative modelling and unpaired data translation. Relying on the stochastic optimal control approach, we choose an Ornstein-Uhlenbeck process as the reference one and estimate the corresponding Schrödinger potential. Introducing a risk function as the Kullback-Leibler divergence between couplings, we derive tight bounds on the generalization ability of an empirical risk minimizer over a class of Schrödinger potentials, including Gaussian mixtures. Thanks to the mixing properties of the Ornstein-Uhlenbeck process, we almost achieve fast rates of convergence, up to some logarithmic factors, in favourable scenarios. We also illustrate the performance of the suggested approach with numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Tight Bounds for Schrödinger Potential Estimation in Unpaired Data Translation
Puchkin, Nikita
Suchkov, Denis
Naumov, Alexey
Belomestny, Denis
Machine Learning
Statistics Theory
Modern methods of generative modelling and unpaired data translation based on Schrödinger bridges and stochastic optimal control theory aim to transform an initial density to a target one in an optimal way. In the present paper, we assume that we only have access to i.i.d. samples from the initial and final distributions. This makes our setup suitable for both generative modelling and unpaired data translation. Relying on the stochastic optimal control approach, we choose an Ornstein-Uhlenbeck process as the reference one and estimate the corresponding Schrödinger potential. Introducing a risk function as the Kullback-Leibler divergence between couplings, we derive tight bounds on the generalization ability of an empirical risk minimizer over a class of Schrödinger potentials, including Gaussian mixtures. Thanks to the mixing properties of the Ornstein-Uhlenbeck process, we almost achieve fast rates of convergence, up to some logarithmic factors, in favourable scenarios. We also illustrate the performance of the suggested approach with numerical experiments.
title Tight Bounds for Schrödinger Potential Estimation in Unpaired Data Translation
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2508.07392