Comment on Sequential Monte Carlo for Bayesian Computation (P. Del Moral, A. Doucet, A. Jas
- 1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。
a r X i v :m a t h /0606557v 1 [m
a t h .S T ] 22 J u n 2006Comment on ”Sequential Monte Carlo for Bayesian Computation”(P.Del Moral,A.Doucet,A.Jasra,Eighth Valencia International Meeting on Bayesian Statistics )David R.Bickel (Johnston,Iowa,USA)June 21,2006The authors added promising innovations in sequential Monte Carlo method-ology to the arsenal of the Bayesian community.Most notably,their backward-kernel framework obviates the evaluation of the importance density function,enabling greater flexibility in the choice of algorithms.They also set their work on posterior inference in a more general context by citing results of the obser-vation that particle filters approximate the path integrals studied in theoretical physics (Del Moral 2004).My first question concerns another recent advance in SMC,the use of the mixture transition kernel αn,m κm (x n −1,x n ),where