Random-scan Gibbs samplers possess a natural hierarchical structure. The structure connects Gibbs samplers targeting higher dimensional distributions to those targeting lower dimensional ones. This leads to a quasi-telescoping property of their spectral gaps. Based on this property, we derive three new bounds on the spectral gaps and convergence rates of Gibbs samplers on general domains. The three bounds relate a chain's spectral gap to, respectively, the correlation structure of the target distribution, a class of random walk chains, and a collection of influence matrices. Notably, one of our results generalizes the technique of spectral independence, which has received considerable attention for its success on finite domains, to general state spaces. We illustrate our methods through a sampler targeting the uniform distribution on a corner of an $n$-cube.
翻译:随机扫描 Gibbs 采样器拥有自然的等级结构。 结构将Gibbs 采样器连接到高维分布和低维分布。 这导致其光谱差距的准星级属性。 基于此属性, 我们从Gibs 采样器在一般域的光谱差距和趋同率中得出三个新的界限。 三个界限将链条的光谱差距分别与目标分布的关联结构、 随机行走链的分类和影响力矩阵的集合联系起来。 值得注意的是, 我们的成果之一是将光谱独立技术( 光谱独立技术在有限域的成功获得了相当大的关注) 概括到一般的状态空间。 我们通过一个取样器来说明我们的方法, 其目标在以美元立方角为角的统一分布。