Sequential Monte Carlo on large binary sampling spaces

被引：0
作者：
Christian Schäfer
Nicolas Chopin
机构：
[1] Centre de Recherche en Économie et Statistique,CEntre de REcherches en MAthématiques de la DEcision
[2] Université Paris-Dauphine,undefined
[3] Ecole Nationale de la Statistique et de l’Administration,undefined
来源：
Statistics and Computing | 2013年 / 23卷
关键词：
Adaptive Monte Carlo; Multivariate binary data; Sequential Monte Carlo; Linear regression; Variable selection;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A Monte Carlo algorithm is said to be adaptive if it automatically calibrates its current proposal distribution using past simulations. The choice of the parametric family that defines the set of proposal distributions is critical for good performance. In this paper, we present such a parametric family for adaptive sampling on high dimensional binary spaces.
引用
收藏
页码：163 / 184
页数：21
相关论文
共 71 条
[21]  
Cox D.(1996)Families of Lect. Notes Monogr. Ser. 28 120-342
[22]  
Wermuth N.(1996)-variate distributions with given margins and J. Comput. Graph. Stat. 5 1-682
[23]  
Cox D.(1994) ( J. Am. Stat. Assoc. 89 278-1044
[24]  
Wermuth N.(2010)−1)/2 bivariate dependence parameters J. Comput. Graph. Stat. 19 769-490
[25]  
Del Moral P.(2000)Monte Carlo filter and smoother for non-Gaussian nonlinear state space models Stat. Sin. 10 317-139
[26]  
Doucet A.(1996)Sequential imputation and Bayesian missing data problems Biometrika 83 681-464
[27]  
Jasra A.(1998)On the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods J. Am. Stat. Assoc. 93 1032-288
[28]  
Emrich L.(1998)Evolutionary Monte Carlo: Applications to Cp model sampling and change point problem Biometrika 85 487-1808
[29]  
Piedmonte M.(2001)Peskun’s theorem and a modified discrete-state Gibbs sampler Stat. Comput. 11 125-undefined
[30]  
Fearnhead P.(2005)Sequential Monte Carlo methods for dynamic systems Biometrika 92 747-undefined
12345678