Subgradient Langevin Methods for Sampling from Non-smooth Potentials

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Habring, Andreas, Holler, Martin, Pock, Thomas
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929357691289600
author Habring, Andreas
Holler, Martin
Pock, Thomas
author_facet Habring, Andreas
Holler, Martin
Pock, Thomas
contents This paper is concerned with sampling from probability distributions $π$ on $\mathbb{R}^d$ admitting a density of the form $π(x) \propto e^{-U(x)}$, where $U(x)=F(x)+G(Kx)$ with $K$ being a linear operator and $G$ being non-differentiable. Two different methods are proposed, both employing a subgradient step with respect to $G\circ K$, but, depending on the regularity of $F$, either an explicit or an implicit gradient step with respect to $F$ can be implemented. For both methods, non-asymptotic convergence proofs are provided, with improved convergence results for more regular $F$. Further, numerical experiments are conducted for simple 2D examples, illustrating the convergence rates, and for examples of Bayesian imaging, showing the practical feasibility of the proposed methods for high dimensional data.
format Preprint
id arxiv_https___arxiv_org_abs_2308_01417
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Subgradient Langevin Methods for Sampling from Non-smooth Potentials
Habring, Andreas
Holler, Martin
Pock, Thomas
Optimization and Control
Computation
65C40, 65C05, 68U10, 65C60
G.3; G.1.6
This paper is concerned with sampling from probability distributions $π$ on $\mathbb{R}^d$ admitting a density of the form $π(x) \propto e^{-U(x)}$, where $U(x)=F(x)+G(Kx)$ with $K$ being a linear operator and $G$ being non-differentiable. Two different methods are proposed, both employing a subgradient step with respect to $G\circ K$, but, depending on the regularity of $F$, either an explicit or an implicit gradient step with respect to $F$ can be implemented. For both methods, non-asymptotic convergence proofs are provided, with improved convergence results for more regular $F$. Further, numerical experiments are conducted for simple 2D examples, illustrating the convergence rates, and for examples of Bayesian imaging, showing the practical feasibility of the proposed methods for high dimensional data.
title Subgradient Langevin Methods for Sampling from Non-smooth Potentials
topic Optimization and Control
Computation
65C40, 65C05, 68U10, 65C60
G.3; G.1.6
url https://arxiv.org/abs/2308.01417