Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
Abstract
We study statistical rates in entropic optimal transport in the semi-discrete regime where one measure has finite support and the other is subGaussian. Our main result establishes parametric convergence rates for the empirical dual potentials to their population counterparts, with no dimension dependence in the leading term. Our result relies on tailored strong concavity analysis of the semi-dual objective, coupled with specialized bounds for the semi-discrete potentials. As a consequence, we obtain fast rates for downstream quantities derived from the optimal coupling. Chiefly, the empirical barycentric projection achieves a squared-error rate n−1, matching the fully compact case and improving over the less favorable n−1/2 rate known for fully subGaussian settings. Altogether, these results may indicate a lower complexity adaptation phenomenon whereby the statistical complexity of the barycentric projection is governed by the discrete measure. As an application, we analyze Sinkhorn-EM, an EM-type algorithm in which the E-step is replaced by an entropic optimal transport problem. In a well-specified and balanced two-component Gaussian mixture model, we prove √n-consistency of the empirical iterates to their population counterparts for any fixed number of iterations, matching classical EM rates up to a √(log n) factor. Simulations support the theory.
Related
- First-order Γ-expansion for entropic optimal transport with non-degenerate costs
- On the Linear Convergence of SISTA for Entropic Martingale Optimal Transport
- Low-Budget Active Learning through Entropic Optimal Transport
- Projected McKean--Vlasov Dynamics for Entropic Weak Optimal Transport
- Sequential Entropic Optimal Transport for Bayesian Inverse Problems via Multilevel Monte Carlo
BibTeX
@misc{gonzalez2026statistical,
title = {{Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime}},
author = {Tomas Gonzalez and Gonzalo Mena},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.26647},
eprint = {2609.26647},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.26647},
}
RIS
TY - UNPB
TI - Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
AU - Tomas Gonzalez
AU - Gonzalo Mena
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.26647
UR - https://arxiv.org/abs/2609.26647
AB - We study statistical rates in entropic optimal transport in the semi-discrete regime where one measure has finite support and the other is subGaussian. Our main result establishes parametric convergence rates for the empirical dual potentials to their population counterparts, with no dimension dependence in the leading term. Our result relies on tailored strong concavity analysis of the semi-dual objective, coupled with specialized bounds for the semi-discrete potentials. As a consequence, we obtain fast rates for downstream quantities derived from the optimal coupling. Chiefly, the empirical barycentric projection achieves a squared-error rate n^−1, matching the fully compact case and improving over the less favorable n^−1/2 rate known for fully subGaussian settings. Altogether, these results may indicate a lower complexity adaptation phenomenon whereby the statistical complexity of the barycentric projection is governed by the discrete measure. As an application, we analyze Sinkhorn-EM, an EM-type algorithm in which the E-step is replaced by an entropic optimal transport problem. In a well-specified and balanced two-component Gaussian mixture model, we prove √n-consistency of the empirical iterates to their population counterparts for any fixed number of iterations, matching classical EM rates up to a √(log n) factor. Simulations support the theory.
ER -