flowseq
flowseq copied to clipboard
Can someone explain why restricting the posterior `z` as diagonal Gaussian?
Maybe I do not understand this paper throughly, but can someone explain this?
The posterior z
is modelled as diagonal Gaussian. And in the Zero initialization
part, ensures that the posterior distribution as a simple normal distribution
.
If it is a simple distribution, why a complex prior flow is needed to learn its distribution?
This is the initialization to ensure the posterior distribution as a normal. During training, the posterior distribution will become more and more complex when we update the parameters.