Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport

Résumé

We derive nearly tight and non-asymptotic convergence bounds for solutions of entropic semi-discrete optimal transport. These bounds quantify the stability of the dual solutions of the regularized problem (sometimes called Sinkhorn potentials) w.r.t. the regularization parameter, for which we ensure a better than Lipschitz dependence. Such facts may be a first step towards a mathematical justification of annealing or $\varepsilon$-scaling heuristics for the numerical resolution of regularized semi-discrete optimal transport. Our results also entail a non-asymptotic and tight expansion of the difference between the entropic and the unregularized costs.
Fichier principal
Vignette du fichier
main.pdf (608.76 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03396206 , version 1 (22-10-2021)
hal-03396206 , version 2 (29-11-2021)

Identifiants

  • HAL Id : hal-03396206 , version 2

Citer

Alex Delalande. Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport. AISTATS 2022 - 25th International Conference on Artificial Intelligence and Statistics, Mar 2022, Valencia / Virtual, Spain. pp.1619-1642. ⟨hal-03396206v2⟩
91 Consultations
51 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More