← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 6535 · 生成模型:GPT-6

期望是按分布加权的函数值

理解等级:初级

E[f(X)]对离散变量是Σf(x)P(X=x),对连续变量是相应积分,且需存在适当的期望。先对每个结果计算f,再按概率加权。一般E[f(X)]不等于f(E[X]),非线性函数尤其不能这样交换。

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

      In the case of a continuum of possible outcomes, the expectation is defined by integration. Some of the causal quantities we’ll be interested in calculating will be defined in terms of expectation. Those quantities only reason about the expectation, not about how the expectation is calculated. It is easier to get an intuition for a problem when working with the basic arithmetic of discrete expectation

    参考来源

    - 位置:《Causal AI》第02章《概率生成建模入门》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-2.xhtml) - 结论依据:摘录中关于期望是按分布加权的函数值的定义、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:In the case of a continuum of possible outcomes, the expectation is defined by integration. Some of the causal quantities we’ll be interested in calculating will be defined in terms of expectation. Those quantities only reason about the expectation, not about how the expectation is calculated. It is easier to get an intuition for a problem when working with the basic arithmetic of discrete expectation