1
$\begingroup$

I am reading this paper on variational inference and this website.

One thing I am confused about is how they get to decompose ELBO, where $ELBO(q) = E_q[log~p(z,x)] - E_q[log~q(z)]$, when focusing on one latent variable's variational distribution $q_j$ like this:

$$ ELBO(q_j) = E_j[E_{-j}[log~p(z_j, z_{-j}, x)]] - E_j[log~q_j(z_j)] + C $$

They say that they use iterated expectation but I had a hard time decomposing $ELBO(q_j)$ using that ($E[X] = E[E[X|Y]]$).

Can anyone elaborate on this? Thanks!

UPDATE: $q(z)=\prod_{i} q(z_i)$ is an assumption so I understand the decomposition of the 2nd term.

$\endgroup$
1
$\begingroup$

Your update has stated that you are using the mean-field variational family, or in other words that $q(z)=\prod_{i} q(z_i)$ which means that $$ \log q(z) = \sum_i \log q(z_i) \tag{*}. $$

So \begin{align*} \text{ELBO}(q) &= E_q[\log p(z,x)] - E_q[\log q(z)] \\ &= E_q[\log p(z_j, z_{-j},x)] - E_q[\log q(z_j, z_{-j})] \\ &= E_q[\log p(z_j, z_{-j},x)] - E_q[\log q(z_j) + \sum_{i\neq j}\log q(z_i)] \tag{*}\\ &= E_q[E\left(\log p(z_j, z_{-j},x) \mid z_{j} \right)] - E_q[\log q(z_j)] - E\left[\sum_{i\neq j}\log q(z_i)\right].\\ \end{align*} This is equivalent to equation (19) in your first linked document.

$\endgroup$
4
  • $\begingroup$ Thanks for the reply! The last equality confuses me a bit: you said that the outer expectation is taken w.r.t. $z$ or $z_{j}$. But according to the law iterated expectation, the outer expectation should be taken w.r.t. $Y$, which is $z_{-j}$ here. Shouldn't the first term be $E_q [E_q[log~p(z_j, z_{-j}, x) \vert z_{j}]]$? $\endgroup$
    – Zhiya
    Feb 12 '18 at 17:24
  • $\begingroup$ I am still confused. Why the equation above has the same term on both the RHS and LHS? $\endgroup$
    – Zhiya
    Feb 12 '18 at 17:40
  • $\begingroup$ Thanks for the clarification but I could not get your idea. I figured out one understanding below. Let me know if you think that's appropriate or not if you have time. Thanks again! $\endgroup$
    – Zhiya
    Feb 12 '18 at 18:00
  • $\begingroup$ @Zhiya looks good! $\endgroup$
    – Taylor
    Feb 12 '18 at 21:10
0
$\begingroup$

I read those two materials again and think that the decomposition may be done via the following rearrangement:

\begin{align} ELBO & = E_q[log~p(x,z)] - E_q[log~q(z)] \\ & = E_q[log~p(x, z_j, z_{-j})] - \sum_{q_l}E_{q_l}[q_l(z_l)] \\ & [\text{Here we use the fact that } q(z) \text{ can be factorized}]\\ & = E_j\Big[E_{-j}\big[ log~p(x, z_j, z_{-j}) \vert z_{j} \big] \Big] - E_{q_j}[q_j] + const \\ \end{align}

Now, according to the definition of expectation, we have: \begin{align} E_{-j}\big[ log~p(x, z_j, z_{-j}) \vert z_{j} \big] &= \int_{-j} log~p(x, z_j, z_{-j})~q(z_{-j}|z_j) dq_{-j} \\ & = \int_{-j} log~p(x, z_j, z_{-j})~q(z_{-j}) dq_{-j} \\ & = E_{-j}\big[ log~p(x, z_j, z_{-j}) \big] \end{align} [We assume independence between latent variables' variational distributions $q(z)$]

Therefore we have:

$$ELBO = E_{-j}\big[ log~p(x, z_j, z_{-j}) \big] - E_{q_j}[q_j] + const $$

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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