Maximum a posteriori estimation in graphical models using local linear approximation

Author:

Sagar Ksheera1,Datta Jyotishka2,Banerjee Sayantan3ORCID,Bhadra Anindya1

Affiliation:

1. Department of Statistics Purdue University West Lafayette Indiana USA

2. Department of Statistics Virginia Tech Blacksburg Virginia USA

3. Operations Management and Quantitative Techniques Area Indian Institute of Management Indore Indore Madhya Pradesh India

Abstract

AbstractSparse structure learning in high‐dimensional Gaussian graphical models is an important problem in multivariate statistical inference, since the sparsity pattern naturally encodes the conditional independence relationship among variables. However, maximum a posteriori (MAP) estimation is challenging under hierarchical prior models, and traditional numerical optimization routines or expectation–maximization algorithms are difficult to implement. To this end, our contribution is a novel local linear approximation scheme that circumvents this issue using a very simple computational algorithm. Most importantly, the condition under which our algorithm is guaranteed to converge to the MAP estimate is explicitly stated and is shown to cover a broad class of completely monotone priors, including the graphical horseshoe. Further, the resulting MAP estimate is shown to be sparse and consistent in the ‐norm. Numerical results validate the speed, scalability and statistical performance of the proposed method.

Publisher

Wiley

Reference50 articles.

1. Generalized double Pareto shrinkage;Armagan A.;Statistica Sinica,2013

2. Banerjee S. Castillo I. &Ghosal S.(2021).Bayesian inference in high‐dimensional models. arXiv preprint arXiv:2101.04491.

3. Bayesian structure learning in graphical models

4. On the Statistical Analysis of Dirty Pictures

5. The Horseshoe-Like Regularization for Feature Subset Selection

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3