Popular explanations Gibbs sampling
Gibbs Sampling is a certain probability distributions, see what events occurred.
Examples of
A can only E: eat, learn, play,
time T: morning, afternoon, evening,
weather W: sunny, windy, rain.
Now you want a sample, the sample can be: play + + sunny afternoon.
The problem is that we do not know p (E, T, W) , or that do not know the joint distribution joint distribution of three things. Of course, if known, there is no need to use the gibbs sampling. However, we know three things of conditional distribution. In other words, p (E | T, W ), p (T | E, W), p (W | E, T). To do now is through these three conditions known distribution of gibbs sampling method and then obtain the joint distribution.
Specific methods
first initialize a random combination, ie learning + + windy night,
then change them according to a variable conditional probability.
Specifically, suppose we know + windy night, we give E generates a variable, for example, learning - "food. We then follow the conditional probability of change under a variable, according to the learning + wind, the night turned into morning. Similarly, the wind into the wind (of course, can become the same variable). Such learning + + windy night - "eat + + windy morning.
In the same manner to give a sequence, each containing three variables, i.e. a Markov chain. Then skip a certain number of initial cells (such as 100), and a separator unit to take a certain number (for example a spacer 20 to take). Such sample to the unit is approaching the joint distribution.
Two Virginia Booth sampling algorithm
Gibbs conditional probability sampling algorithm in the right we know, for example, you want to sample is two-dimensional Gaussian distribution, then xt is fixed after the one-dimensional Gaussian distribution after two-dimensional Gaussian distribution of fixed xt , and each different coordinate sampling, so this one-dimensional Gaussian probability density function is also not the same.
======================================================================
======================================================================
======================================================================
======================================================================
From
https://blog.csdn.net/wydbyxr/article/details/83212740
https://baike.baidu.com/item/%E5%90%89%E5%B8%83%E6%96%AF%E9%87%87%E6%A0%B7/22660772?fr=aladdin
https://blog.csdn.net/wenyusuran/article/details/97754195