Concentration of Exponential Tilts Implies Curvature

arXiv:2610.34570 · math.PR · Submitted 2026-10-25 · Read on arXiv

math.PR

Submitted: 2026-10-25

Updated: 2026-10-25

Comments: 17 pages

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: We show, under a smoothness assumption, that probability measures whose exponential tilts have a uniformly bounded variance are given by a strongly convex potential…

Abstract

We show, under a smoothness assumption, that probability measures whose exponential tilts have a uniformly bounded variance are given by a strongly convex potential, up to a bounded perturbation, yielding a partial converse to the Bakry-Émery theorem combined with Holley-Stroock's perturbation principle. A stronger version enforcing uniform convexity of the potential is obtained by considering the low-temperature regime.

Related papers