知识卡片
变量消除控制中间因子规模
变量消除利用因子分解,对查询不需要的变量逐步求和或积分,再组合剩余因子。消除顺序影响中间因子大小及计算成本;使用图结构不代表算法会自动找到全局最优顺序。
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
- · 概率生成建模入门
原书出处 · 1 处
- · 查看原书依据
Variable elimination uses the graph structure to optimally sum over the variables you wish to eliminate until the resulting table represents the target distribution. In contrast, belief propagation is a message-passing system; the graph is used to form different “cliques” of neighboring variables. For example, if P (Z |Y = 1) is the target distribution, Y=1 is a message iteratively passed back and forth between
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:摘录中关于变量消除控制中间因子规模的定义、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:Variable elimination uses the graph structure to optimally sum over the variables you wish to eliminate until the resulting table represents the target distribution. In contrast, belief propagation is a message-passing system; the graph is used to form different “cliques” of neighboring variables. For example, if P (Z |Y = 1) is the target distribution, Y=1 is a message iteratively passed back and forth between