Calculus of Variations and Geometric Measure Theory

G. Carlier - P. Pegon - L. Tamanini

Convergence rate of general entropic optimal transport costs

created by pegon on 07 Jun 2022
modified on 09 Apr 2024


Published Paper

Inserted: 7 jun 2022
Last Updated: 9 apr 2024

Journal: Calculus of Variations and Partial Differential Equations
Volume: 62
Year: 2023
Doi: 10.1007/s00526-023-02455-0

ArXiv: 2206.03347 PDF
Links: HAL repository


We investigate the convergence rate of the optimal entropic cost $v_\varepsilon$ to the optimal transport cost as the noise parameter $\varepsilon \downarrow 0$. We show that for a large class of cost functions $c$ on $\mathbb{R}^d\times \mathbb{R}^d$ (for which optimal plans are not necessarily unique or induced by a transport map) and compactly supported and $L^{\infty}$ marginals, one has $v_\varepsilon-v_0= \frac{d}{2} \varepsilon \log(1/\varepsilon)+ O(\varepsilon)$. Upper bounds are obtained by a block approximation strategy and an integral variant of Alexandrov's theorem. Under an infinitesimal twist condition on $c$, i.e.\ invertibility of $\nabla_{xy}^2 c(x,y)$, we get the lower bound by establishing a quadratic detachment of the duality gap in $d$ dimensions thanks to Minty's trick.

Keywords: Optimal transport, Entropic regularization, Schrödinger problem, convex analysis, entropic dimension