Entangled Monte Carlo
Entangled Monte Carlo
复制标题
纠缠蒙特卡罗
DOI：
10.14288/1.0074196
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Alexandre Bouchard
中科院分区：
文献类型：
--
作者：
Seong;Liangliang Wang;Alexandre Bouchard
我们提出了一种新的方法，可扩展的并行SMC算法，纠缠蒙特卡罗模拟（EMC）。EMC避免了粒子在节点之间的传输，而是从粒子谱系重建它们。特别是，我们表明，我们可以减少每台机器的粒子权重的通信，同时有效地保持隐式的全局一致性的并行模拟。我们解释的方法，以有效地保持一个家谱的粒子，任何粒子可以重建。我们证明使用贝叶斯系统发育的例子，从并行化使用EMC的计算增益显着超过粒子重建的成本。计时实验表明，粒子的重建确实比粒子的传输更有效。
We propose a novel method for scalable parallelization of SMC algorithms, Entangled Monte Carlo simulation (EMC). EMC avoids the transmission of particles between nodes, and instead reconstructs them from the particle genealogy. In particular, we show that we can reduce the communication to the particle weights for each machine while efficiently maintaining implicit global coherence of the parallel simulation. We explain methods to efficiently maintain a genealogy of particles from which any particle can be reconstructed. We demonstrate using examples from Bayesian phylogenetic that the computational gain from parallelization using EMC significantly outweighs the cost of particle reconstruction. The timing experiments show that reconstruction of particles is indeed much more efficient as compared to transmission of particles.