arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.07971stat.MEstat.AP
收藏

使用确定性近似加速SMC用于后验采样

Using deterministic approximations to accelerate SMC for posterior sampling

Sophie Donnet, Stéphane Robin

摘要:

序贯蒙特卡罗已成为复杂模型贝叶斯推断的标准工具。这种方法在计算上要求很高,特别是当从先验分布初始化时。另一方面,后验分布的确定性近似通常是可用的,而没有理论上的可靠性。我们提出了一个桥式抽样方案,从这样一个确定性的近似的后验分布,并针对真正的。由此产生的缩短桥采样器(SBS)依赖于一系列的分布,确定在一个自适应的方式。我们说明的鲁棒性和效率的方法在一个大型的模拟研究。当应用于网络数据集,SBS推断导致不同的统计结论,从一个标准的变分贝叶斯近似提供。

英文摘要:

Sequential Monte Carlo has become a standard tool for Bayesian Inference of complex models. This approach can be computationally demanding, especially when initialized from the prior distribution. On the other hand, deter-ministic approximations of the posterior distribution are often available with no theoretical guaranties. We propose a bridge sampling scheme starting from such a deterministic approximation of the posterior distribution and targeting the true one. The resulting Shortened Bridge Sampler (SBS) relies on a sequence of distributions that is determined in an adaptive way. We illustrate the robustness and the efficiency of the methodology on a large simulation study. When applied to network datasets, SBS inference leads to different statistical conclusions from the one supplied by the standard variational Bayes approximation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑