New algorithm of exact sampling with directional threshold  

作　　者：Linfeng Shen Yan Lin 

机构地区：[1]School of Automation, Beihang University, Beijing 100191, R R. China

出　　处：《Journal of Systems Engineering and Electronics》2010年第2期281-286,共6页系统工程与电子技术（英文版）

摘　　要：Although it is known that exact sampling algorithm is easy to construct and less sensitive to noise, the samples distri- bution of the algorithm deviates from the target states distribution due to the local dependent coupling problem. A new algorithm, named exact sampling with directional threshold （ES-DT） is intro- duced. The main advantage of the new algorithm, in comparison with the traditional exact sampling algorithm, is that it can control the sampling with a rejection strategy in Markov chain during the path growth, and closely approach the ideal distribution based on maintaining the target density. Simulation experiments show the effectiveness of the proposed algorithm.Although it is known that exact sampling algorithm is easy to construct and less sensitive to noise, the samples distri- bution of the algorithm deviates from the target states distribution due to the local dependent coupling problem. A new algorithm, named exact sampling with directional threshold （ES-DT） is intro- duced. The main advantage of the new algorithm, in comparison with the traditional exact sampling algorithm, is that it can control the sampling with a rejection strategy in Markov chain during the path growth, and closely approach the ideal distribution based on maintaining the target density. Simulation experiments show the effectiveness of the proposed algorithm.

关 键 词：Markov chain Monte Carlo exact sampling perfect sampling rejection control. 

分 类 号：O212.2[理学—概率论与数理统计] TP271.8[理学—数学]