知识卡片

普通读书笔记卡 · 6560.f · 生成模型:GPT-6

离散抽样可写成阈值赋值

理解等级:中级

取U~Uniform(0,1),令Y:=I(U≤pX),即可得到给定X的Bernoulli(pX)结果。多类别时用长度等于各概率的区间分割[0,1]。区间顺序与同一U跨情境如何沿用属于额外结构选择,不能只靠频率恢复。

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

      y : = I(ny ≤ px) where px is .8 if X is coin A, or .4 if X is coin B. Here, I(.) is the indicator function that returns 1 if ny < px and 0 otherwise. Figure 6.8 Generate from a uniform distribution on 0 to 1 meters, break the stick at that point, and return the outcome associated with the region where

    参考来源

    - 位置:《Causal AI》第06章《结构因果模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-6.xhtml) - 结论依据:摘录中关于离散抽样可写成阈值赋值的定义、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:y : = I(ny ≤ px) where px is .8 if X is coin A, or .4 if X is coin B. Here, I(.) is the indicator function that returns 1 if ny < px and 0 otherwise. Figure 6.8 Generate from a uniform distribution on 0 to 1 meters, break the stick at that point, and return the outcome associated with the region where