Concentration inequalities for Gibbs sampling under $d_{l_{2}}$-metric
Concentration inequalities for Gibbs sampling under $d_{l_{2}}$-metric
复制标题
DOI：
10.1214/ecp.v19-3502
复制
发表时间：
2014-09
影响因子：
0.5
通讯作者：
Neng-Yi Wang
中科院分区：
文献类型：
--
作者：
Neng-Yi Wang
本文的目的是研究吉布斯抽样，用于计算的平均值的观测值相对于一些功能$f$取决于一个非常小的变量。对于这种类型的可观测量，通过使用$d_{l_{2}}$-度量，可以获得经验平均值的精确集中估计，特别是根据单个可观测量，可以得到$f$的正确集中速度。
The aim of this paper is to investigate the Gibbs sampling that's used for computing the mean of observables with respect to some function $f$ depending on a very small number of variables. For this type of observable, by using the $d_{l_{2}}$-metric one obtains the sharp concentration estimate for the empirical mean, which in particular yields the correct speed in the concentration for $f$ depending on a single observable.