← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6550.d · 生成模型:GPT-6

最小分离集不等于最少节点

理解等级:中级

最小d分离集表示从该集合删掉任何成员都会失去分离性,是按包含关系最小;不同最小集可以大小不同。它不必是所有分离集中节点数最少者。且向其中加变量可能打开碰撞路径,不能任意视为更安全。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      minimal d-separating sets, meaning that all the other d-separating sets include at least one of these sets. The minimal d-separation sets are sufficient to d-separate the two nodes. When reasoning about d-separation and when implementing it in algorithms, we want to focus on finding minimal d-separating sets; if U⊥V|Z and U⊥V|Z, W are both true, we don’t want to waste effort on U⊥V|Z, W.

    参考来源

    - 位置:《Causal AI》第04章《用因果约束检验DAG》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-4.xhtml) - 结论依据:摘录中关于最小分离集不等于最少节点的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:minimal d-separating sets, meaning that all the other d-separating sets include at least one of these sets. The minimal d-separation sets are sufficient to d-separate the two nodes. When reasoning about d-separation and when implementing it in algorithms, we want to focus on finding minimal d-separating sets; if U⊥V|Z and U⊥V|Z, W are both true, we don’t want to waste effort on U⊥V|Z, W.