Normalizing constants of log-concave densities

Abstract : We derive explicit bounds for the computation of normalizing constants Z for log-concave densities $\pi= \mathrm{e}^{−U} /Z$ w.r.t. the Lebesgue measure on $\mathbb{R}^d$. Our approach relies on a Gaussian annealing combined with recent and precise bounds on the Unadjusted Langevin Algorithm (Durmus, A. and Moulines, E. (2016). High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm). Polynomial bounds in the dimension $d$ are obtained with an exponent that depends on the assumptions made on $U$. The algorithm also provides a theoretically grounded choice of the annealing sequence of variances. A numerical experiment supports our findings. Results of independent interest on the mean squared error of the empirical average of locally Lipschitz functions are established.
Type de document :
Article dans une revue
Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2018, 12 (1), pp.851-889. 〈10.1214/18-EJS1411〉
Liste complète des métadonnées

Littérature citée [51 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01648666
Contributeur : Nicolas Brosse <>
Soumis le : mardi 6 mars 2018 - 09:16:38
Dernière modification le : jeudi 10 mai 2018 - 02:05:54

Fichier

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Nicolas Brosse, Alain Durmus, Eric Moulines. Normalizing constants of log-concave densities. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2018, 12 (1), pp.851-889. 〈10.1214/18-EJS1411〉. 〈hal-01648666v2〉

Partager

Métriques

Consultations de la notice

108

Téléchargements de fichiers

19