arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2002.09284cs.AIcs.LG
收藏

关于决策背后的原因

On The Reasons Behind Decisions

University of California, Los Angeles(加州大学洛杉矶分校)

Adnan Darwiche, Auguste Hirth

摘要:

最近的工作表明,一些常见的机器学习分类器可以编译成具有相同输入输出行为的布尔电路。我们提出了一个理论,揭示了布尔分类器的决策背后的原因,并研究了它的一些理论和实践意义。我们定义的概念,如决策背后的充分,必要和完整的原因,除了分类和决策偏差。我们展示了如何使用这些概念来评估反事实陈述,如“即使......因为... .“我们提出了有效的算法来计算这些概念,这是基于新的进展,易处理的布尔电路,并说明他们使用的案例研究。

英文摘要:

Recent work has shown that some common machine learning classifiers can be compiled into Boolean circuits that have the same input-output behavior. We present a theory for unveiling the reasons behind the decisions made by Boolean classifiers and study some of its theoretical and practical implications. We define notions such as sufficient, necessary and complete reasons behind decisions, in addition to classifier and decision bias. We show how these notions can be used to evaluate counterfactual statements such as "a decision will stick even if ... because ... ." We present efficient algorithms for computing these notions, which are based on new advances on tractable Boolean circuits, and illustrate them using a case study.

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。

↑