On quantitative Laplace-type convergence results for some exponential probability measures, with two applications - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

On quantitative Laplace-type convergence results for some exponential probability measures, with two applications

Résumé

Laplace-type results characterize the limit of sequence of measures $(\pi_\varepsilon)_{\varepsilon >0}$ with density w.r.t the Lebesgue measure $(\mathrm{d} \pi_\varepsilon / \mathrm{d} \mathrm{Leb})(x) \propto \exp[-U(x)/\varepsilon]$ when the temperature $\varepsilon>0$ converges to $0$. If a limiting distribution $\pi_0$ exists, it concentrates on the minimizers of the potential $U$. Classical results require the invertibility of the Hessian of $U$ in order to establish such asymptotics. In this work, we study the particular case of norm-like potentials $U$ and establish quantitative bounds between $\pi_\varepsilon$ and $\pi_0$ w.r.t. the Wasserstein distance of order $1$ under an invertibility condition of a generalized Jacobian. One key element of our proof is the use of geometric measure theory tools such as the coarea formula. We apply our results to the study of maximum entropy models (microcanonical/macrocanonical distributions) and to the convergence of the iterates of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm at low temperatures for non-convex minimization.

Dates et versions

hal-03945493 , version 1 (18-01-2023)

Identifiants

Citer

Valentin de Bortoli, Agnès Desolneux. On quantitative Laplace-type convergence results for some exponential probability measures, with two applications. 2023. ⟨hal-03945493⟩
21 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More