An Inertial Langevin Algorithm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Falk, Alexander, Habring, Andreas, Griesbacher, Christoph, Pock, Thomas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912634836615168
author Falk, Alexander
Habring, Andreas
Griesbacher, Christoph
Pock, Thomas
author_facet Falk, Alexander
Habring, Andreas
Griesbacher, Christoph
Pock, Thomas
contents We present a novel method for drawing samples from Gibbs distributions with densities of the form $π(x) \propto \exp(-U(x))$. The method accelerates the unadjusted Langevin algorithm by introducing an inertia term similar to Polyak's heavy ball method, together with a corresponding noise rescaling. Interpreting the scheme as a discretization of \emph{kinetic} Langevin dynamics, we prove ergodicity (in continuous and discrete time) for twice continuously differentiable, strongly convex, and $L$-smooth potentials and bound the bias of the discretization to the target in Wasserstein-2 distance. In particular, the presented proofs allow for smaller friction parameters in the kinetic Langevin diffusion compared to existing literature. Moreover, we show the close ties of the proposed method to the over-relaxed Gibbs sampler. The scheme is tested in an extensive set of numerical experiments covering simple toy examples, total variation image denoising, and the complex task of maximum likelihood learning of an energy-based model for molecular structure generation. The experimental results confirm the acceleration provided by the proposed scheme even beyond the strongly convex and $L$-smooth setting.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06723
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Inertial Langevin Algorithm
Falk, Alexander
Habring, Andreas
Griesbacher, Christoph
Pock, Thomas
Numerical Analysis
65C40, 65C05, 68U10, 65C60
G.3; I.4.5
We present a novel method for drawing samples from Gibbs distributions with densities of the form $π(x) \propto \exp(-U(x))$. The method accelerates the unadjusted Langevin algorithm by introducing an inertia term similar to Polyak's heavy ball method, together with a corresponding noise rescaling. Interpreting the scheme as a discretization of \emph{kinetic} Langevin dynamics, we prove ergodicity (in continuous and discrete time) for twice continuously differentiable, strongly convex, and $L$-smooth potentials and bound the bias of the discretization to the target in Wasserstein-2 distance. In particular, the presented proofs allow for smaller friction parameters in the kinetic Langevin diffusion compared to existing literature. Moreover, we show the close ties of the proposed method to the over-relaxed Gibbs sampler. The scheme is tested in an extensive set of numerical experiments covering simple toy examples, total variation image denoising, and the complex task of maximum likelihood learning of an energy-based model for molecular structure generation. The experimental results confirm the acceleration provided by the proposed scheme even beyond the strongly convex and $L$-smooth setting.
title An Inertial Langevin Algorithm
topic Numerical Analysis
65C40, 65C05, 68U10, 65C60
G.3; I.4.5
url https://arxiv.org/abs/2510.06723