Gaussoids are two-antecedental approximations of Gaussian conditional independence structures

Author:

Boege TobiasORCID

Abstract

AbstractThe gaussoid axioms are conditional independence inference rules which characterize regular Gaussian CI structures over a three-element ground set. It is known that no finite set of inference rules completely describes regular Gaussian CI as the ground set grows. In this article we show that the gaussoid axioms logically imply every inference rule of at most two antecedents which is valid for regular Gaussians over any ground set. The proof is accomplished by exhibiting for each inclusion-minimal gaussoid extension of at most two CI statements a regular Gaussian realization. Moreover we prove that all those gaussoids have rational positive-definite realizations inside every ε-ball around the identity matrix. For the proof we introduce the concept of algebraic Gaussians over arbitrary fields and of positive Gaussians over ordered fields and obtain the same two-antecedental completeness of the gaussoid axioms for algebraic and positive Gaussians over all fields of characteristic zero as a byproduct.

Funder

Max Planck Institute for Mathematics in the Sciences

Publisher

Springer Science and Business Media LLC

Subject

Applied Mathematics,Artificial Intelligence

Reference39 articles.

1. Abo Khamis, M., Kolaitis, P.G., Ngo, H.Q., Suciu, D.: Decision problems in information theory. arXiv:2004.08783 (2020)

2. Boege, T.: Incidencegeometryintheprojectiveplaneviaalmost-principalminorsofsymmetricmatrices. arXiv:2103.02589 (2021)

3. Boege, T., D’Alì, A., Kahle, T., Sturmfels, B.: Thegeometryofgaussoids. Found.Comput.Math. 19(4), 775–812 (2019). https://doi.org/10.1007/s10208-018-9396-x

4. Boege, T., Kahle, T.: Constructionmethodsforgaussoids. Kybernetika 56(6), 1045–1062 (2020). https://doi.org/10.14736/kyb-2020-6-1045

5. Bouckaert, R., Hemmecke, R., Lindner, S., Studený, M.: Efficientalgorithmsforconditionalindependenceinference. J.Mach.Learn.Res. 11, 3453–3479 (2010)

Cited by 5 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