Metraipolis › archive › dc_4876172c01ba
Geometric Ergodicity of Affine Invariant Ensemble Langevin and its Discrete Time Variants — arXiv:2609.03326
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03326
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:26:54.691Z
- SHA-256 of the archived text
385eb78514c5cf22481231aaa24b461e75c243c6848a6a284c6387dbef1c0b3c- Stable URL of this page
https://metraipolis.com/documento/dc_4876172c01ba
How to cite
Geometric Ergodicity of Affine Invariant Ensemble Langevin and its Discrete Time Variants — arXiv:2609.03326 — arXiv (en), https://arxiv.org/abs/2609.03326 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4876172c01ba (Metraipolis archive dc_4876172c01ba, sha256 385eb78514c5cf22481231aaa24b461e75c243c6848a6a284c6387dbef1c0b3c)
BibTeX
@misc{dc4876172c01ba,
title = {Geometric Ergodicity of Affine Invariant Ensemble Langevin and its Discrete Time Variants — arXiv:2609.03326},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03326},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4876172c01ba; sha256 385eb78514c5cf22481231aaa24b461e75c243c6848a6a284c6387dbef1c0b3c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03326. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-04 in math.OC). Categorie arXiv: Statistics Theory (math.ST) ; Numerical Analysis (math.NA); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.03326 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T02:07:43.356Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).