We analyze the posterior contraction rates of parameters in Bayesian models via the Langevin diffusion process, in particular by controlling moments of the stochastic process and taking limits. Analogous to the non-asymptotic analysis of statistical M-estimators and stochastic optimization algorithms, our contraction rates depend on the structure of the population log-likelihood function, and stochastic perturbation bounds between the population and sample log-likelihood functions. Convergence rates are determined by a non-linear equation that relates the population-level structure to stochastic perturbation terms, along with a term characterizing the diffusive behavior. Based on this technique, we also prove non-asymptotic versions of a Bernstein-von-Mises guarantee for the posterior. We illustrate this general theory by deriving posterior convergence rates for various concrete examples, as well as approximate posterior distributions computed using Langevin sampling procedures.
翻译:我们通过Langevin扩散过程分析巴伊西亚模型中参数的事后收缩率,特别是通过控制随机过程的瞬间和限制来分析。对统计性测算器和随机优化算法的非被动分析,我们的收缩率取决于人口日志相似性功能的结构,以及人口与抽样日志相似性功能之间的随机扰动界限。趋同率是由非线性方程式决定的,该方程式将人口层次结构与随机扰动条件联系起来,同时用词来描述异式行为。基于这一技术,我们还证明了对子宫的Bernstein-von-Mises担保的非被动性版本。我们通过为各种具体实例得出后端趋汇率,以及使用Langevin取样程序计算出近似的后端分布,来说明这一一般性理论。