On accuracy of density estimation in generative models based on stochastic optimal control
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 for exact empirical risk minimization. This matches, up to logarithmic factors, the classical nonparametric KL-risk convergence exponent, while allowing target densities on whose tails are controlled by Gaussian envelopes.
Figures & tables
| Setup | Sliced Wasserstein | Energy distance | |
|---|---|---|---|
| Standard | |||
| Irregular | |||
| Anisotropic |
Density Estimation
Density estimation learns probability distributions from data to measure likelihood, detect anomalies, quantify uncertainty, and generate samples.
See all 69 papers