Paperlane

no. 16 · Tuesday 17 November 2026

On accuracy of density estimation in generative models based on stochastic optimal control

Nikita Puchkin, Denis Suchkov, Alexey Naumov and Denis Belomestny

math.ST · v2 · 62 pp

Abstract

We study the statistical accuracy of Schrödinger bridge models based on an Ornstein-Uhlenbeck reference process. Given a known, compactly supported initial distribution and independent samples from an unknown target distribution, we estimate a right Schrödinger log-potential by minimizing empirical Kullback-Leibler (KL) risk over a prescribed function class. For bounded sub-Gaussian target densities, potentially with unbounded support, we establish a non-asymptotic high-probability oracle inequality for the KL-divergence between the target and estimated terminal marginals. Under additional two-sided Gaussian bounds and smoothness assumptions on the target log-density, we derive approximation guarantees for sparse ReLU networks and establish a KL convergence rate of $\widetilde{O}(n^{-2s / (2s + d)})$ for exact empirical risk minimization. This matches, up to logarithmic factors, the classical nonparametric KL-risk convergence exponent, while allowing target densities on $\mathbb R^d$ whose tails are controlled by Gaussian envelopes.

comments
62 pages, 2 figures
fields
Statistics Theory
pdf ↗ page arXiv:2506.03043 ↗