Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal Distributions
Résumé
Poincaré inequalities are ubiquitous in probability and analysis and have various applications in statistics (concentration of measure, rate of convergence of Markov chains). The Poincaré constant, for which the inequality is tight, is related to the typical convergence rate of diffusions to their equilibrium measure. In this paper, we show both theoretically and experimentally that, given sufficiently many samples of a measure, we can estimate its Poincaré constant. As a by-product of the estimation of the Poincaré constant, we derive an algorithm that captures a low dimensional representation of the data by finding directions which are difficult to sample. These directions are of crucial importance for sampling or in fields like molecular dynamics, where they are called reaction coordinates. Their knowledge can leverage, with a simple conditioning step, computational bottlenecks by using importance sampling techniques.
Fichier principal
Poincare_estimation.pdf (725.19 Ko)
Télécharger le fichier
comparison.pdf (17.64 Ko)
Télécharger le fichier
kappas.pdf (14.96 Ko)
Télécharger le fichier
lipschitz.png (345.39 Ko)
Télécharger le fichier
mixture.pdf (12.48 Ko)
Télécharger le fichier
mixture_optim.pdf (12.56 Ko)
Télécharger le fichier
mixture_samples.pdf (13.08 Ko)
Télécharger le fichier
mixture_whiten_samples.pdf (12.46 Ko)
Télécharger le fichier
nus.pdf (5.87 Ko)
Télécharger le fichier
poinca_gaussian_1.pdf (14.42 Ko)
Télécharger le fichier
poinca_gaussian_2.pdf (6.48 Ko)
Télécharger le fichier
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|