cs.LGJun 3, 2025

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

Authors: Nikita Puchkin, Denis Suchkov, Alexey Naumov, Denis Belomestny

Organizations: HSE University, Russian Federation · Skolkovo Institute of Science and Technology, Russian Federation · Duisburg-Essen University, Germany

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 O~(n−2s/(2s+d))\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 Rd\mathbb R^d whose tails are controlled by Gaussian envelopes.

Figures & tables

Explore similar work

CardsList
  1. Direct Estimation of Schrödinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees

    May 6, 2026Othmane Mazhar, Huyên PhamParameter EstimationSchrödinger Bridges

  2. A Spectral Framework for Closed-Form Relative Density Estimation

    May 11, 2026Francis BachDensity Ratio EstimationSpectral Methods