Graph convex hull bounds as generalized Jensen inequalities

Author:

Klebanov Ilja1ORCID

Affiliation:

1. Mathematical Institute Freie Universität Berlin Berlin Germany

Abstract

AbstractJensen's inequality is ubiquitous in measure and probability theory, statistics, machine learning, information theory and many other areas of mathematics and data science. It states that, for any convex function defined on a convex domain and any random variable taking values in , . In this paper, sharp upper and lower bounds on , termed ‘graph convex hull bounds’, are derived for arbitrary functions on arbitrary domains , thereby extensively generalizing Jensen's inequality. The derivation of these bounds necessitates the investigation of the convex hull of the graph of , which can be challenging for complex functions. On the other hand, once these inequalities are established, they hold, just like Jensen's inequality, for any ‐valued random variable . Therefore, these bounds are of particular interest in cases where is relatively simple and is complicated or unknown. Both finite‐ and infinite‐dimensional domains and codomains of are covered as well as analogous bounds for conditional expectations and Markov operators.

Funder

Deutsche Forschungsgemeinschaft

Publisher

Wiley

Reference20 articles.

1. Analysis and Geometry of Markov Diffusion Operators

2. Convex Analysis and Nonlinear Optimization

3. Further reverse results for Jensen's discrete inequality and applications in information theory;Budimir I.;JIPAM. J. Inequal. Pure Appl. Math.,2001

4. Vector Measures

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