Geometric Ergodicity of Affine Invariant Ensemble Langevin and its Discrete Time Variants
Abstract
Affine-invariant ensemble samplers are widely used in Bayesian applications. However, their quantitative convergence theory, in particular geometric ergodicity, remains a basic open question. We study the affine invariant ensemble Langevin dynamics, an interacting particle system that uses the empirical covariance of the whole ensemble as a preconditioner. While effective in practice, theoretical understanding of this method is not available beyond plain qualitative convergence in total variation, with a central difficulty being that the empirical covariance can become degenerate. For potentials with bounded Hessian that are strongly convex outside a ball, we prove geometric ergodicity using a novel Lyapunov function that combines the inverse covariance with a coercive exponential energy. We then show that directly applying the Euler--Maruyama scheme can diverge with positive probability, even for a one-dimensional Gaussian target. This motivates a covariance-trace regularization in continuous time. We prove geometric ergodicity of the regularized diffusion and, for sufficiently small step size, of its unadjusted Euler--Maruyama discretization. We also show that the invariant distributions of the discretization converge weakly to the product target distribution as the step size tends to zero. Lastly, we provide an explicit discretization that is both affine-invariant and geometrically ergodic, based on an adaptive step size clamping.
Related
- Tempered Langevin diffusions with polynomial-tailed targets: explosions, moment thresholds and ergodicity
- Exponential Ergodicity and Invariant Distribution of a Degenerate Reflected SDE with Stable Noise
- Space of Geometric Gibbs Measures: Uniqueness, Ergodicity, and Teichmüller Complex Manifold Structure
- PICKLES: Covariance-Preconditioned Kinetic Langevin Ensemble Sampler
- Geometric ergodicity of the block Gibbs sampler for Bayesian linear mixed models with scale mixtures of normal random effects
BibTeX
@misc{tan2026geometric,
title = {{Geometric Ergodicity of Affine Invariant Ensemble Langevin and its Discrete Time Variants}},
author = {Hong Ye Tan and Yifan Chen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.03326},
eprint = {2609.03326},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.03326},
}
RIS
TY - UNPB
TI - Geometric Ergodicity of Affine Invariant Ensemble Langevin and its Discrete Time Variants
AU - Hong Ye Tan
AU - Yifan Chen
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2609.03326
UR - https://arxiv.org/abs/2609.03326
AB - Affine-invariant ensemble samplers are widely used in Bayesian applications. However, their quantitative convergence theory, in particular geometric ergodicity, remains a basic open question. We study the affine invariant ensemble Langevin dynamics, an interacting particle system that uses the empirical covariance of the whole ensemble as a preconditioner. While effective in practice, theoretical understanding of this method is not available beyond plain qualitative convergence in total variation, with a central difficulty being that the empirical covariance can become degenerate. For potentials with bounded Hessian that are strongly convex outside a ball, we prove geometric ergodicity using a novel Lyapunov function that combines the inverse covariance with a coercive exponential energy. We then show that directly applying the Euler--Maruyama scheme can diverge with positive probability, even for a one-dimensional Gaussian target. This motivates a covariance-trace regularization in continuous time. We prove geometric ergodicity of the regularized diffusion and, for sufficiently small step size, of its unadjusted Euler--Maruyama discretization. We also show that the invariant distributions of the discretization converge weakly to the product target distribution as the step size tends to zero. Lastly, we provide an explicit discretization that is both affine-invariant and geometrically ergodic, based on an adaptive step size clamping.
ER -