February 2023 A characterization of transportation-information inequalities for Markov processes in terms of dimension-free concentration
Daniel Lacker, Lane Chun Yeung
Author Affiliations +
Ann. Inst. H. Poincaré Probab. Statist. 59(1): 364-377 (February 2023). DOI: 10.1214/22-AIHP1249

Abstract

Inequalities between transportation costs and Fisher information are known to characterize certain concentration properties of Markov processes around their invariant measures. This note provides a new characterization of the quadratic transportation-information inequality W2I in terms of a dimension-free concentration property for i.i.d. (conditionally on the initial positions) copies of the underlying Markov process. This parallels Gozlan’s characterization of the quadratic transportation-entropy inequality W2H. The proof is based on a new Laplace-type principle for the operator norms of Feynman-Kac semigroups, which is of independent interest. Lastly, we illustrate how both our theorem and (a form of) Gozlan’s are instances of a general convex-analytic tensorization principle.

Il est connu que les inégalités entre les coûts de transport et l’information de Fisher caractérisent certaines propriétés de concentration des processus de Markov autour de leurs mesures invariantes. Cette note apporte une nouvelle caractérisation de l’inégalité quadratique transport-information W2I, en termes d’une propriété de concentration indépendante de la dimension pour les copies i.i.d. (conditionnellement aux positions initiales) du processus de Markov sous-jacent. Ceci est comparable à la caractérisation de Gozlan de l’inégalité quadratique transport-entropie W2H. La preuve est basée sur un nouveau principe de type Laplace pour les normes d’opérateurs des semigroupes de Feynman-Kac, qui peut avoir un intérêt indépendant. Enfin, nous expliquons comment notre théorème et (une forme de) celui de Gozlan sont des exemples d’un principe général de tensorisation convexe-analytique.

Funding Statement

D. Lacker was partially supported by the Air Force Office of Scientific Research Grant FA9550-19-1-0291.

Acknowledgements

We thank Ioannis Karatzas for helpful discussions and comments, as well as an anonymous referee for bringing our attention to [25] and posing the question mentioned in Remark 1.10.

Citation

Download Citation

Daniel Lacker. Lane Chun Yeung. "A characterization of transportation-information inequalities for Markov processes in terms of dimension-free concentration." Ann. Inst. H. Poincaré Probab. Statist. 59 (1) 364 - 377, February 2023. https://doi.org/10.1214/22-AIHP1249

Information

Received: 2 April 2021; Revised: 17 December 2021; Accepted: 3 February 2022; Published: February 2023
First available in Project Euclid: 16 January 2023

MathSciNet: MR4533733
zbMATH: 07657656
Digital Object Identifier: 10.1214/22-AIHP1249

Subjects:
Primary: 26D10 , 60E15
Secondary: 60J25

Keywords: Dimension-free concentration , Transportation-information inequalities

Rights: Copyright © 2023 Association des Publications de l’Institut Henri Poincaré

Vol.59 • No. 1 • February 2023
Back to Top