Convergence Rates of the Regularized Optimal Transport : Disentangling Suboptimality and Entropy - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2023

Convergence Rates of the Regularized Optimal Transport : Disentangling Suboptimality and Entropy

Résumé

We study the convergence of the transport plans γε towards γ0 as well as the cost of the entropy-regularized optimal transport (c, γε) towards (c, γ0) as the regularization parameter ε vanishes in the setting of finite entropy marginals. We show that under the assumption of infinitesimally twisted cost and compactly supported marginals the distance W2(γε, γ0) is asymptotically greater than C √ ε and the suboptimality (c, γε) − (c, γ0) is of order ε. In the quadratic cost case the compactness assumption is relaxed into a moment of order 2 + δ assumption. Moreover, in the case of a Lipschitz transport map for the non-regularized problem, the distance W2(γε, γ0) converges to 0 at rate √ ε. Finally, if in addition the marginals have finite Fisher information, we prove (c, γε) − (c, γ0) ∼ dε/2 and we provide a companion expansion of H(γε). These results are achieved by disentangling the role of the cost and the entropy in the regularized problem.
Fichier principal
Vignette du fichier
disentangle.pdf (530.33 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04114127 , version 1 (08-06-2023)
hal-04114127 , version 2 (09-06-2023)

Identifiants

Citer

Hugo Malamut, Maxime Sylvestre. Convergence Rates of the Regularized Optimal Transport : Disentangling Suboptimality and Entropy. 2023. ⟨hal-04114127v2⟩
57 Consultations
80 Téléchargements

Altmetric

Partager

More