A hybrid sampler for Poisson-Kingman mixture models
A hybrid sampler for Poisson-Kingman mixture models
复制标题
泊松-金曼混合模型的混合采样器
DOI：
10.1007/978-3-319-23461-8_36
复制
发表时间：
2015
影响因子：
3
通讯作者：
Y. Teh
中科院分区：
文献类型：
--
作者：
M. Lomeli;S. Favaro;Y. Teh
本文介绍了一种新的马尔可夫链蒙特卡罗方案，用于贝叶斯非参数混合模型中的后验采样，其先验属于一般泊松-金曼类。我们提出了一种新颖的紧凑方式来表示模型的无限维分量，这样在显式表示该无限分量的同时，它比以前的 MCMC 方案具有更少的内存和存储需求。我们描述了比较模拟结果，证明了所提出的 MCMC 算法相对于现有边际和条件 MCMC 采样器的有效性。
This paper concerns the introduction of a new Markov Chain Monte Carlo scheme for posterior sampling in Bayesian nonparametric mixture models with priors that belong to the general Poisson-Kingman class. We present a novel compact way of representing the infinite dimensional component of the model such that while explicitly representing this infinite component it has less memory and storage requirements than previous MCMC schemes. We describe comparative simulation results demonstrating the efficacy of the proposed MCMC algorithm against existing marginal and conditional MCMC samplers.