First-order Γ-expansion for entropic optimal transport with non-degenerate costs
Abstract
Entropy-regularized optimal transport (EOT) has become a key tool in optimal transport, providing both theoretical insight and efficient computation via the Sinkhorn algorithm. We study the first-order Γ-expansion of EOT as the regularization parameter ε vanishes, by rewriting EOT as the minimization of a relative entropy with respect to a Gibbs measure gibbs associated with the duality gap energy. Using a mild extension of the Laplace method, we prove the convergence of the Gibbs measures and derive this Γ-expansion for non-degenerate ground costs, under suitable assumptions on the duality gap, the contact set and the marginals. This yields at the same time an entropic selection principle and an expansion of the EOT cost up to o(ε) for this class of ground costs, generalizing existing results.
Related
- 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
- Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
- Sequential Entropic Optimal Transport for Bayesian Inverse Problems via Multilevel Monte Carlo
BibTeX
@misc{nenna2026firstorder,
title = {{First-order Γ-expansion for entropic optimal transport with non-degenerate costs}},
author = {Luca Nenna and Brendan Pass and Paul Pegon and Louis Tocquec},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10257},
eprint = {2610.10257},
archivePrefix = {arXiv},
url = {https://inria.hal.science/hal-05774627v2},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - First-order Γ-expansion for entropic optimal transport with non-degenerate costs
AU - Luca Nenna
AU - Brendan Pass
AU - Paul Pegon
AU - Louis Tocquec
PY - 2026
DA - 2026/10/01
PB - HAL
DO - 10.48550/arxiv.2610.10257
UR - https://inria.hal.science/hal-05774627v2
AB - Entropy-regularized optimal transport (EOT) has become a key tool in optimal transport, providing both theoretical insight and efficient computation via the Sinkhorn algorithm. We study the first-order Γ-expansion of EOT as the regularization parameter ε vanishes, by rewriting EOT as the minimization of a relative entropy with respect to a Gibbs measure gibbs associated with the duality gap energy. Using a mild extension of the Laplace method, we prove the convergence of the Gibbs measures and derive this Γ-expansion for non-degenerate ground costs, under suitable assumptions on the duality gap, the contact set and the marginals. This yields at the same time an entropic selection principle and an expansion of the EOT cost up to o(ε) for this class of ground costs, generalizing existing results.
ER -