Heat flow, log-concavity, and Lipschitz transport maps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brigati, Giovanni, Pedrotti, Francesco
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909192130920448
author Brigati, Giovanni
Pedrotti, Francesco
author_facet Brigati, Giovanni
Pedrotti, Francesco
contents In this paper we derive estimates for the Hessian of the logarithm (log-Hessian) for solutions to the heat equation. For initial data in the form of log-Lipschitz perturbation of strongly log-concave measures, the log-Hessian admits an explicit, uniform (in space) lower bound. This yields a new estimate for the Lipschitz constant of a transport map pushing forward the standard Gaussian to a measure in this class. Further connections are discussed with score-based diffusion models and improved Gaussian logarithmic Sobolev inequalities. Finally, we show that assuming only fast decay of the tails of the initial datum does not suffice to guarantee uniform log-Hessian upper bounds.
format Preprint
id arxiv_https___arxiv_org_abs_2404_15205
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Heat flow, log-concavity, and Lipschitz transport maps
Brigati, Giovanni
Pedrotti, Francesco
Analysis of PDEs
Probability
26D10
In this paper we derive estimates for the Hessian of the logarithm (log-Hessian) for solutions to the heat equation. For initial data in the form of log-Lipschitz perturbation of strongly log-concave measures, the log-Hessian admits an explicit, uniform (in space) lower bound. This yields a new estimate for the Lipschitz constant of a transport map pushing forward the standard Gaussian to a measure in this class. Further connections are discussed with score-based diffusion models and improved Gaussian logarithmic Sobolev inequalities. Finally, we show that assuming only fast decay of the tails of the initial datum does not suffice to guarantee uniform log-Hessian upper bounds.
title Heat flow, log-concavity, and Lipschitz transport maps
topic Analysis of PDEs
Probability
26D10
url https://arxiv.org/abs/2404.15205