A dimension-free reverse logarithmic Sobolev inequality for low-complexity functions in Gaussian space
Preprint
Abstract
We discuss new proofs, and new forms, of a reverse logarithmic Sobolev inequality, with respect to the standard Gaussian measure, for low complexity functions, measured in terms of Gaussian-width. In particular, we provide a dimension-free improvement for a related result given in [Eldan '18].Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Multi-variate correlation and mixtures of product measuresKybernetika, 2020
- The structure of low-complexity Gibbs measures on product spacesThe Annals of Probability, 2019
- Gaussian-width gradient complexity, reverse log-Sobolev inequalities and nonlinear large deviationsGeometric and Functional Analysis, 2018
- Regularization under diffusion and anticoncentration of the information contentDuke Mathematical Journal, 2018
- Analysis and Geometry of Markov Diffusion Operators2014
- Representation formula for the entropy and functional inequalitiesAnnales de l'Institut Henri Poincaré, Probabilités et Statistiques, 2013