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 1204.4243stat.ML
收藏

EP-GIG先验及其在贝叶斯稀疏学习中的应用

EP-GIG Priors and Applications in Bayesian Sparse Learning

Zhihua Zhang, Shusen Wang, Dehua Liu, Michael I. Jordan

摘要:

在本文中,我们提出了一个新的框架,稀疏诱导先验的建设。特别是,我们定义这样的先验混合指数幂分布与广义逆高斯密度(EP-GIG)。EP-GIG是广义双曲分布的一种变体,其特殊情况包括高斯尺度混合和拉普拉斯尺度混合。此外,拉普拉斯尺度的混合物可以subserve的贝叶斯框架稀疏学习与非凸惩罚。EP-GIG的密度可以明确表达。此外,相应的后验分布也遵循广义逆高斯分布。这些属性使我们的期望最大化算法贝叶斯稀疏学习。我们发现,这些算法承担一个有趣的相似之处,迭代重新加权$\ell_2$或$\ell_1$方法。此外,我们提出了两个扩展的分组变量选择和逻辑斯谛回归。

英文摘要:

In this paper we propose a novel framework for the construction of sparsity-inducing priors. In particular, we define such priors as a mixture of exponential power distributions with a generalized inverse Gaussian density (EP-GIG). EP-GIG is a variant of generalized hyperbolic distributions, and the special cases include Gaussian scale mixtures and Laplace scale mixtures. Furthermore, Laplace scale mixtures can subserve a Bayesian framework for sparse learning with nonconvex penalization. The densities of EP-GIG can be explicitly expressed. Moreover, the corresponding posterior distribution also follows a generalized inverse Gaussian distribution. These properties lead us to EM algorithms for Bayesian sparse learning. We show that these algorithms bear an interesting resemblance to iteratively re-weighted $\ell_2$ or $\ell_1$ methods. In addition, we present two extensions for grouped variable selection and logistic regression.

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。

↑