A note on auxiliary particle filters
A note on auxiliary particle filters
复制标题
DOI：
10.1016/j.spl.2008.01.032
复制
发表时间：
2008-09-01
影响因子：
0.8
通讯作者：
Doucet, Arnaud
中科院分区：
文献类型：
--
作者：
Johansen, Adam M.;Doucet, Arnaud
由Pitt和Shephard [Pitt，M.K.，Shephard，N.，1999.通过模拟过滤：辅助粒子滤波器。J. Am.中央集权主义者屁股94，590-599]是顺序重要性采样和恢复（SISR）算法的一种非常流行的替代方案，用于在状态空间模型中执行推理。我们提出了一种新的解释的APF作为SISR算法。这种解释使我们能够提出简单的指导方针，以确保良好的性能的APF和第一次收敛结果，这种算法。此外，我们表明，与流行的信念相反，基于APF的估计量的渐近方差并不总是小于相应的SISR估计量-即使在“完美适应”的情况下。(C)2008 Elsevier B. V.保留所有权利。
The auxiliary particle filter (APF) introduced by Pitt and Shephard [Pitt, M.K., Shephard, N., 1999. Filtering via simulation: Auxiliary particle filters. J. Am. Statist. Ass. 94, 590-599] is a very popular alternative to Sequential Importance Sampling and Resampling (SISR) algorithms to perform inference in state-space models. We propose a novel interpretation of the APF as an SISR algorithm. This interpretation allows us to present simple guidelines to ensure good performance of the APF and the first convergence results for this algorithm. Additionally, we show that, contrary to popular belief, the asymptotic variance of APF-based estimators is not always smaller than those of the corresponding SISR estimators - even in the 'perfect adaptation' scenario. (C) 2008 Elsevier B.V. All rights reserved.