知识卡片
单样本目标不是精确似然
给定x从q抽一个z,log pθ(x|z)是重建期望的一次随机估计;配合解析KL可估计ELBO。它不是精确log pθ(x),也不是未经权重校正的重要性似然估计。ELBO在期望层面为下界,单次随机实现不必逐次低于真实对数似然。
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
The other term, the likelihood term, will be approximated by sampling. For each datapoint x, we will take just a single sample from this expectation, as this is often sufficient in practice. To do so, first we encode x to parameterize qψ(Z | x). Then we sample a z from qψ(Z | x). Finally we decode this z to parameterize pθ(X | z), and we
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第33章《生成建模与表示学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c033.xhtml)
- 结论依据:摘录中关于单样本目标不是精确似然的定义、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:The other term, the likelihood term, will be approximated by sampling. For each datapoint x, we will take just a single sample from this expectation, as this is often sufficient in practice. To do so, first we encode x to parameterize qψ(Z | x). Then we sample a z from qψ(Z | x). Finally we decode this z to parameterize pθ(X | z), and we