Data augmentation for non-Gaussian regression models using variance-mean mixtures

• 成果类型: Article
• 署名作者: Polson, N. G.; Scott, J. G.
• 署名单位: University of Chicago; University of Texas System; University of Texas Austin
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/ass081
• 发表日期: 2013
• 页码: 459471
• 关键词: prior distributions; scale mixtures; selection; estimators; likelihood; Lasso

摘要

We use the theory of normal variance-mean mixtures to derive a data-augmentation scheme for a class of common regularization problems. This generalizes existing theory on normal variance mixtures for priors in regression and classification. It also allows variants of the expectation-maximization algorithm to be brought to bear on a wider range of models than previously appreciated. We demonstrate the method on several examples, focusing on the case of binary logistic regression. We also show that quasi-Newton acceleration can substantially improve the speed of the algorithm without compromising its robustness.