论文标题
通过软干预措施的因果抽象
Causal Abstraction with Soft Interventions
论文作者
论文摘要
因果抽象提供了一个理论，描述了几种因果模型如何以不同级别的细节来表示相同的系统。现有的理论建议将抽象模型的分析限制为“硬”干预措施，将因果变量固定为恒定值。在这项工作中，我们将因果抽象扩展到“软”干预措施，这些干预措施将可能的非构态函数分配给变量，而无需添加新的因果关系。具体来说，（i）我们将$τ$ -Abstraction从Beckers和Halpern（2019）（2019）概括为软干预措施，（ii）我们提出了对软抽象的进一步定义，以确保在软干预之间进行独特的映射$ω$，并且（iii）我们证明，我们对软抽象的建设性定义可以保证干预映射$ $ω$具有特定的表格，并具有特定的表格。
Causal abstraction provides a theory describing how several causal models can represent the same system at different levels of detail. Existing theoretical proposals limit the analysis of abstract models to "hard" interventions fixing causal variables to be constant values. In this work, we extend causal abstraction to "soft" interventions, which assign possibly non-constant functions to variables without adding new causal connections. Specifically, (i) we generalize $τ$-abstraction from Beckers and Halpern (2019) to soft interventions, (ii) we propose a further definition of soft abstraction to ensure a unique map $ω$ between soft interventions, and (iii) we prove that our constructive definition of soft abstraction guarantees the intervention map $ω$ has a specific and necessary explicit form.
