知识卡片
马尔可夫链采样保留拒绝状态
MCMC构造以目标分布为平稳分布的转移过程,样本之间通常相关,需要关注混合及收敛。接受拒绝型算法在拒绝时保留原状态,重复状态也是链的一部分;不能只保留接受值。并非所有MCMC都必须显式接受拒绝,例如Gibbs采样。
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
Markov chain Monte Carlo Markov chain Monte Carlo (MCMC) is an inference algorithm popular amongst computational Bayesians. These are accept/reject algorithms where each newly generated outcome depends on the previous (non-rejected) generated outcome. This produces a chain of outcomes, and the distribution of outcomes in the chain eventually converges to the target distribution. Hamiltonian Monte Carlo (HMC) is a popular version that doesn’t require users
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:摘录中关于马尔可夫链采样保留拒绝状态的定义、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:Markov chain Monte Carlo Markov chain Monte Carlo (MCMC) is an inference algorithm popular amongst computational Bayesians. These are accept/reject algorithms where each newly generated outcome depends on the previous (non-rejected) generated outcome. This produces a chain of outcomes, and the distribution of outcomes in the chain eventually converges to the target distribution. Hamiltonian Monte Carlo (HMC) is a popular version that doesn’t require users