importance sampling methods are broadly used to approximate posterior
distributions or some of their moments. In its standard approach, samples are
drawn from a single proposal distribution and weighted properly. However, since
the performance depends on the mismatch between the target
本文提出一种自适应算法，通过迭代地更新混合重要性采样密度的权重和组分参数，以优化重要性采样性能，该方法适用于广泛类别的重要性采样密度，包括特别是多元学生 t 分布的混合物，实验表明，该算法在人工和实际例子上的表现都很好，并且特别突出了一个新颖的 Rao-Blackwellisation 装置的好处，该装置可以轻松地纳入更新方案中。