A new characterization of quadratic transportation-information inequalities
Yuan Liu

TL;DR
This paper introduces a new characterization of quadratic transportation-information inequalities, establishing their equivalence with Lyapunov conditions, their stability under perturbations, and their connection to Talagrand's inequality.
Contribution
It provides a novel equivalence between $ ext{W}_2I$ and Lyapunov conditions, and demonstrates the stability of $ ext{W}_2I$ under bounded perturbations, expanding the theoretical understanding of these inequalities.
Findings
Proves the equivalence of $ ext{W}_2I$ and Lyapunov conditions.
Shows stability of $ ext{W}_2I$ under bounded perturbations.
Derives $ ext{W}_2H$ from a restricted $ ext{W}_2I$.
Abstract
It is known that a quadratic transportation-information inequality interpolates between the Talagrand's inequality and the log-Sobolev inequality (LSI for short). The aim of the present paper is threefold: (1) To prove the equivalence of and the Lyapunov condition, which gives a new characterization inspired by Cattiaux-Guillin-Wu [8]. (2) To prove the stability of under bounded perturbations, which gives a transference principle in the sense of Holley-Stroock. (3) To prove through a restricted , which gives a counterpart of the restricted LSI presented by Gozlan-Roberto-Samson [15].
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNonlinear Partial Differential Equations · Geometric Analysis and Curvature Flows · Markov Chains and Monte Carlo Methods
