Improved generic acceptance function for Multi-point Metropolis algorithm

摘要：

　　The key of designing MCMC algorithm is the choice of acceptance function.In this work,Selection criteria of acceptance function is given,and an improved Multi-point Metropolis algorithm with generic acceptance function is proposed,which is called GAF-MPM.Then GAF-MPM is showed to satisfy Detailed Balance Condition to ensure its convergence,the strict proof is given in this work.Further,several different acceptance functions are given,and we discuss the effect on the convergence speed,acceptance rate of the samples and the correlation due to the choice of different acceptance functions.Finally,its correctness and effectiveness is proven through numerical experiments.

关键词： MCMC Metropolis Hastings Multi-point Detailed Balance Condition

作者: Yinghua Zhang Wensheng Zhang

作者单位: State key Laboratory of Management and Control of Complex Systems Institute of Automation,Chinese Academy of Science,BeiJing,China

会议类型: 国际会议

会议名称: the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT-2012)(2012年电机工程与信息技术国际会议)

会议地点: 沈阳

会议语种:英文

页码: 16-21

在线出版日期: 2012-09-26（万方平台首次上网日期，不代表论文的发表时间）