当前位置: X-MOL 学术J. Comput. Graph. Stat. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
High-dimensional Copula Variational Approximation through Transformation
Journal of Computational and Graphical Statistics ( IF 1.4 ) Pub Date : 2020-04-20 , DOI: 10.1080/10618600.2020.1740097
Michael Stanley Smith 1 , Rubén Loaiza-Maya 2 , David J. Nott 3
Affiliation  

ABSTRACT Variational methods are attractive for computing Bayesian inference when exact inference is impractical. They approximate a target distribution—either the posterior or an augmented posterior—using a simpler distribution that is selected to balance accuracy with computational feasibility. Here, we approximate an element-wise parametric transformation of the target distribution as multivariate Gaussian or skew-normal. Approximations of this kind are implicit copula models for the original parameters, with a Gaussian or skew-normal copula function and flexible parametric margins. A key observation is that their adoption can improve the accuracy of variational inference in high dimensions at limited or no additional computational cost. We consider the Yeo–Johnson and inverse G&H transformations, along with sparse factor structures for the scale matrix of the Gaussian or skew-normal. We also show how to implement efficient reparameterization gradient methods for these copula-based approximations. The efficacy of the approach is illustrated by computing posterior inference for three different models using six real datasets. In each case, we show that our proposed copula model distributions are more accurate variational approximations than Gaussian or skew-normal distributions, but at only a minor or no increase in computational cost. Supplementary materials comprising an online appendix, MATLAB code to implement the method, and the datasets employed, are available online.

中文翻译:

通过变换的高维 Copula 变分逼近

摘要 当精确推理不切实际时,变分方法对于计算贝叶斯推理很有吸引力。他们使用更简单的分布来近似目标分布——后验分布或增强后验分布——使用更简单的分布来平衡准确性和计算可行性。在这里,我们将目标分布的元素参数变换近似为多元高斯或偏斜正态。这种近似是原始参数的隐式 copula 模型,具有高斯或偏斜正态 copula 函数和灵活的参数边界。一个关键的观察结果是,它们的采用可以在有限或没有额外计算成本的情况下提高高维变分推理的准确性。我们考虑 Yeo-Johnson 和逆 G&H 变换,以及高斯或偏斜正态的尺度矩阵的稀疏因子结构。我们还展示了如何为这些基于 copula 的近似值实现有效的重新参数化梯度方法。该方法的有效性通过使用六个真实数据集计算三个不同模型的后验推理来说明。在每种情况下,我们都表明我们提出的 copula 模型分布是比高斯分布或偏态正态分布更准确的变分近似,但计算成本只增加很小或没有增加。包括在线附录、实现该方法的 MATLAB 代码和使用的数据集在内的补充材料可在线获取。该方法的有效性通过使用六个真实数据集计算三个不同模型的后验推理来说明。在每种情况下,我们都表明我们提出的 copula 模型分布是比高斯分布或偏态正态分布更准确的变分近似,但计算成本只增加很小或没有增加。包括在线附录、实现该方法的 MATLAB 代码和使用的数据集在内的补充材料可在线获取。该方法的有效性通过使用六个真实数据集计算三个不同模型的后验推理来说明。在每种情况下,我们都表明我们提出的 copula 模型分布是比高斯分布或偏态正态分布更准确的变分近似,但计算成本只增加很小或没有增加。包括在线附录、实现该方法的 MATLAB 代码和使用的数据集在内的补充材料可在线获取。
更新日期:2020-04-20
down
wechat
bug