...
首页> 外文期刊>Psychometrika >An Efficient MCMC Algorithm to Sample Binary Matrices with Fixed Marginals
【24h】

An Efficient MCMC Algorithm to Sample Binary Matrices with Fixed Marginals

机译:固定边际的二进制矩阵的有效MCMC算法

获取原文
获取原文并翻译 | 示例
           

摘要

Uniform sampling of binary matrices with fixed margins is known as a difficult problem. Two classes of algorithms to sample from a distribution not too different from the uniform are studied in the literature: importance sampling and Markov chain Monte Carlo (MCMC). Existing MCMC algorithms converge slowly, require a long burn-in period and yield highly dependent samples. Chen et al. developed an importance sampling algorithm that is highly efficient for relatively small tables. For larger but still moderate sized tables (300×30) Chen et al.’s algorithm is less efficient. This article develops a new MCMC algorithm that converges much faster than the existing ones and that is more efficient than Chen’s algorithm for large problems. Its stationary distribution is uniform. The algorithm is extended to the case of square matrices with fixed diagonal for applications in social network theory.
机译:具有固定余量的二进制矩阵的均匀采样被称为一个难题。在文献中研究了两类从分布与均匀性差别不大的样本中进行采样的算法:重要性采样和马尔可夫链蒙特卡洛(MCMC)。现有的MCMC算法收敛速度很慢,需要很长的老化时间,并产生高度依赖的样本。 Chen等。开发了一种重要采样算法,该算法对于相对较小的表非常高效。对于较大但尺寸适中的桌子(300×30),Chen等人的算法效率较低。本文开发了一种新的MCMC算法,该算法收敛速度比现有算法快得多,并且在解决大问题时比Chen算法更有效。它的静态分布是均匀的。该算法扩展到对角线固定的正方形矩阵的情况,以用于社交网络理论。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号