I'm trying to understand the equation below from this paper. equation

But there is 2 things I don't quite understand (I'm not a math expert):

  • $E_{z,y}\sim_{P_{data(z, y)}}$, means $E_{z,y}$ follows a data distribution of $_{P_{data(z, y)}}$ ? What does that mean exactly?
  • $||\phi_i(y) - \phi_i(G(z))||$, the double $||$ means: "take the absolute values of $\phi_i(y) - \phi_i(G(z))$" right?

Thanks you for your help.

up vote 1 down vote accepted
  1. $E_{z,y}$ means the expected value of $\|\phi_i(y)-\phi_i(G(z))\|$, where the expectation is taken over both $y$ and $z$. It is $y$ and $z$ that are distributed as $P_{data(y,z)}$.
  2. $\|\phi_i(y)-\phi_i(G(z))\|$ is the $L^2$ norm of $\phi_i(y)-\phi_i(G(z))$. That is the quare root of the sum of squares.

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.