Sampling from non-smooth distribution through Langevin diffusion
Résumé
In this paper, we propose algorithms for sampling from the distributions whose density is non-smoothed nor log-concave. Our algorithms are based on the Langevin diffusion on the regularized counterpart of density by the Moreau-Yosida regularization. These results are then applied for computing the exponentially weighted aggregates for high dimensional regression.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...