论文标题
关于决策的原因
On The Reasons Behind Decisions
论文作者
论文摘要
最近的工作表明，一些常见的机器学习分类器可以编译为具有相同输入输出行为的布尔电路。我们提出了一种理论，以揭示布尔分类器做出的决定背后的原因，并研究其一些理论和实际含义。除分类器和决策偏见外，我们定义了诸如决策背后的足够，必要和完整的理由之类的概念。我们展示了这些概念如何用于评估反事实陈述，例如“决定即使……因为...”。我们提出了计算这些概念的有效算法，这些算法基于可拖动布尔电路的新进展，并使用案例研究对其进行了说明。
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.
