Conditional particle filters (CPFs) with backward/ancestor sampling are powerful methods for sampling from the posterior distribution of the latent states of a dynamic model such as a hidden Markov model. However, the performance of these methods deteriorates with models involving weakly informative observations and/or slowly mixing dynamics. Both of these complications arise when sampling finely time-discretised continuous-time path integral models, but can occur with hidden Markov models too. Multinomial resampling, which is commonly employed with CPFs, resamples excessively for weakly informative observations and thereby introduces extra variance. Furthermore, slowly mixing dynamics render the backward/ancestor sampling steps ineffective, leading to degeneracy issues. We detail two conditional resampling strategies suitable for the weakly informative regime: the so-called `killing' resampling and the systematic resampling with mean partial order. To avoid the degeneracy issues, we introduce a generalisation of the CPF with backward sampling that involves auxiliary `bridging' CPF steps that are parameterised by a blocking sequence. We present practical tuning strategies for choosing an appropriate blocking. Our experiments demonstrate that the CPF with a suitable resampling and the developed `bridge backward sampling' can lead to substantial efficiency gains in the weakly informative and slow mixing regime.
翻译:条件粒子滤波器 (CPF)可以通过向后或祖先采样从动态模型(如隐 Markov 模型)的潜在状态后验分布中进行采样。然而,这些方法的性能随着涉及弱信息观测和/或缓慢混合动力学的模型而恶化。这两种复杂性都会在对时间细分的连续时路径积分模型进行采样时出现,但也可能出现在隐马尔可夫模型中。常用于 CPF 中的多项重采样对于弱信息观测过于频繁地进行重采样,从而引入额外的方差。此外,缓慢混合的动力学使得向后/祖先采样步骤失效,导致退化问题。我们介绍两种适用于弱信息方案的条件重采样策略:所谓的 `killing' 重采样和具有平均偏序的系统重采样。为了避免退化问题,我们引入了一个 CPF 的一般化形式,其中包括辅助的 `桥式' CPF 步骤,其由一个阻塞序列参数化。我们提出了实际的调整策略,以选择适当的阻塞。我们的实验表明,具有合适重采样和开发的 `桥向后采样'的 CPF 可以在弱信息和缓慢混合的情况下导致显着的效率提升。