Metraipolis › archive › dc_0f4f510ccdca

Rényi mixing bounds for kinetic samplers via $L^2$ hypocoercivity — arXiv:2611.03921

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03921
License (as archived)
CC0-1.0
Archived
2026-11-04T21:56:14.916Z
SHA-256 of the archived text
63f20186c37e4a18e64c1e92ab8307e4c473e5e9b86ff6bd651a03ddf8520eaa
Stable URL of this page
https://metraipolis.com/documento/dc_0f4f510ccdca

How to cite

Rényi mixing bounds for kinetic samplers via $L^2$ hypocoercivity — arXiv:2611.03921 — arXiv (en), https://arxiv.org/abs/2611.03921 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f4f510ccdca (Metraipolis archive dc_0f4f510ccdca, sha256 63f20186c37e4a18e64c1e92ab8307e4c473e5e9b86ff6bd651a03ddf8520eaa)
BibTeX
@misc{dc0f4f510ccdca,
  title = {Rényi mixing bounds for kinetic samplers via $L^2$ hypocoercivity — arXiv:2611.03921},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03921},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f4f510ccdca; sha256 63f20186c37e4a18e64c1e92ab8307e4c473e5e9b86ff6bd651a03ddf8520eaa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03921. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study convergence in Rényi divergence of order two for underdamped Langevin dynamics, the bouncy particle sampler, and the Zigzag sampler, for a target $e^{-U}$ on $\mathbb R^d$ that satisfies a logarithmic Sobolev inequality, with $\nabla^2U$ bounded below by a possibly negative constant and, for the Zigzag sampler, also bounded above. For initial laws whose Rényi divergence from equilibrium is at most $R$, we show that it decays exponentially, at a rate that depends on $R$. With the friction or refreshment rate chosen according to $R$, the time needed to reach a fixed accuracy in total variation or in Rényi divergence is of order $\sqrt{R\log R}$ at fixed dimension and target parameters, improving the linear dependence obtained by directly converting exponential $L^2$ decay. The key idea is to use the logarithmic Sobolev inequality for the position target in place of the usual spatial spectral-gap estimate in the $L^2$ hypocoercivity argument. For the bouncy particle and Zigzag samplers, this order is sharp for the Rényi divergence on a one-dimensional Gaussian target, uniformly in the refreshment rate. For the Zigzag sampler in dimension at least two, Gaussian examples show that the mixing-time bound is sharp up to logarithmic factors in the worst case over strongly convex targets, in both the initial divergence and the upper Hessian bound; in particular, strong convexity alone does not give a uniform mixing bound.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.PR, nuovi lavori del giorno).
Categorie arXiv: Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2611.03921 — 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 2026-11-04T21:41:04.527Z dalla pagina https://arxiv.org/list/math.PR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).