知识卡片
领域约束能缩小图搜索空间
可把已知时间顺序、必有或禁止的边、实验设置及潜变量结构作为发现算法约束。它们减少候选空间,但约束错误也会排除真实结构。应区分外部知识、数据证据和算法推断,而非将全部箭头归为数据自动发现。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
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
Because the space of DAGs can be quite large, it is useful to incorporate prior knowledge to constrain the size of that space. This often takes the form of specifying what edges must be present or what must be absent, or of using Bayesian priors on graph structure.
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:摘录中关于领域约束能缩小图搜索空间的定义、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:Because the space of DAGs can be quite large, it is useful to incorporate prior knowledge to constrain the size of that space. This often takes the form of specifying what edges must be present or what must be absent, or of using Bayesian priors on graph structure.