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 2202.11629cs.AIstat.ML
收藏

可解影响图中信息值的一个完全判据

A Complete Criterion for Value of Information in Soluble Influence Diagrams

University of Oxford(牛津大学);DeepMind

Chris van Merwijk, Ryan Carey, Tom Everitt

摘要:

影响图最近被用来分析AI系统的安全性和公平性。这种分析的一个关键组成部分是信息价值(VoI)的图形标准。本文建立了第一个完整的图形标准的VoI的影响图与多个决策。在此过程中,我们建立了两个重要的技术证明多决策影响图的属性:ID同态是影响图的结构保持变换,而系统树是捕获信息和控制如何在影响图中流动的路径的集合。

英文摘要:

Influence diagrams have recently been used to analyse the safety and fairness properties of AI systems. A key building block for this analysis is a graphical criterion for value of information (VoI). This paper establishes the first complete graphical criterion for VoI in influence diagrams with multiple decisions. Along the way, we establish two important techniques for proving properties of multi-decision influence diagrams: ID homomorphisms are structure-preserving transformations of influence diagrams, while a Tree of Systems is collection of paths that captures how information and control can flow in an influence diagram.

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。

↑