daib13 / TwoStageVAE

230 stars 33 forks source link

About finding a sequence of encoders #10

Open gefeiwang opened 4 years ago

gefeiwang commented 4 years ago

Hi, thank you for this interesting work! I was trying to read your proof in appendix E2, and got confused about the design of encoder networks. Ideally, if the decoder network is linear, i.e. f_\mux(z) = Az + b, the true posterior is also gaussian with mean (I\gamma + A^TA)^{-1}A^T(x-b), which is related with \gamma. However, the mean of the variational posterior in this paper is f\mu_z(x) which is independent of \gamma. Is there anything wrong? I was trying to figure this out in the following proof, but couldn't understand why equation (30) holds. Since the variable transformation is z' = (z - z*) / \sqrt(\gamma), then shouldn't z' be somehow related with \gamma? If so, why z' can be canceled out in the second term of the second equality when taking the limit \gamma goes to \intfy?