Exact thresholds for Ising–Gibbs samplers on general graphs

• Autores: Elchanan Mossel, Allan Sly
• Localización: Annals of probability: An official journal of the Institute of Mathematical Statistics, ISSN 0091-1798, Vol. 41, Nº. 1, 2013, págs. 294-328
• Idioma: inglés
• DOI: 10.1214/11-AOP737
• Texto completo no disponible (Saber más ...)
• Resumen

  • We establish tight results for rapid mixing of Gibbs samplers for the Ferromagnetic Ising model on general graphs. We show that if (d−1) tanh β < 1, then there exists a constant C such that the discrete time mixing time of Gibbs samplers for the ferromagnetic Ising model on any graph of n vertices and maximal degree d, where all interactions are bounded by β, and arbitrary external fields are bounded by Cnlogn. Moreover, the spectral gap is uniformly bounded away from 0 for all such graphs, as well as for infinite graphs of maximal degree d.

    We further show that when dtanh β < 1, with high probability over the Erdős–Rényi random graph G(n,d/n), it holds that the mixing time of Gibbs samplers is n1+Θ(1/loglogn).

    Both results are tight, as it is known that the mixing time for random regular and Erdős–Rényi random graphs is, with high probability, exponential in n when (d−1) tanh β> 1, and dtanh β>1, respectively. To our knowledge our results give the first tight sufficient conditions for rapid mixing of spin systems on general graphs. Moreover, our results are the first rigorous results establishing exact thresholds for dynamics on random graphs in terms of spatial thresholds on trees.