English

Second Order Ensemble Langevin Method for Sampling and Inverse Problems

Dynamical Systems 2025-06-06 v3 Machine Learning Numerical Analysis Numerical Analysis Methodology

Abstract

We propose a sampling method based on an ensemble approximation of second order Langevin dynamics. The log target density is appended with a quadratic term in an auxiliary momentum variable and damped-driven Hamiltonian dynamics introduced; the resulting stochastic differential equation is invariant to the Gibbs measure, with marginal on the position coordinates given by the target. A preconditioner based on covariance under the law of the dynamics does not change this invariance property, and is introduced to accelerate convergence to the Gibbs measure. The resulting mean-field dynamics may be approximated by an ensemble method; this results in a gradient-free and affine-invariant stochastic dynamical system. Numerical results demonstrate its potential as the basis for a numerical sampler in Bayesian inverse problems.

Keywords

Cite

@article{arxiv.2208.04506,
  title  = {Second Order Ensemble Langevin Method for Sampling and Inverse Problems},
  author = {Ziming Liu and Andrew M. Stuart and Yixuan Wang},
  journal= {arXiv preprint arXiv:2208.04506},
  year   = {2025}
}
R2 v1 2026-06-25T01:35:06.825Z