You can directly open the pdf of this post here
divergencesYou can directly open the pdf of this post here
You can directly open the pdf of this post here
divergencesYou can directly open the pdf of this post here
When trying to compute variational bounds (as derived in the previous post), a naive attempt to approximate the involved expectations (e.g. using a Taylor expansion) may destroy the bound.
This is where the Higher-order Jensen-Feynman inequality comes in. It allows us to do a higher-order polynomial expansion without destroying the variational bound.