SMCTC: Sequential Monte Carlo in C++

Journal of Statistical Software

关键词: Monte Carlo;    particle filtering;    sequential Monte Carlo;    simulation;    template class;   

DOI  :  

来源: DOAJ

【 摘 要 】

Sequential Monte Carlo methods are a very general class of Monte Carlo methodsfor sampling from sequences of distributions. Simple examples of these algorithms areused very widely in the tracking and signal processing literature. Recent developmentsillustrate that these techniques have much more general applicability, and can be appliedvery eectively to statistical inference problems. Unfortunately, these methods are oftenperceived as being computationally expensive and dicult to implement. This articleseeks to address both of these problems.A C++ template class library for the ecient and convenient implementation of verygeneral Sequential Monte Carlo algorithms is presented. Two example applications areprovided: a simple particle lter for illustrative purposes and a state-of-the-art algorithmfor rare event estimation.

【 授权许可】

Unknown