I'm trying to reconstruct variational autoencoder situation with a more "imaginable" example, known all properties. I was playing around, and can't find a way how can for example the sum of two normal distributions ($P(Z|X_1)$, $P(Z|X_2)$) with different means, and standard deviations multiplied with $P(X)$ can form $P(Z)$ - a normal distributon.

Just for example we're checking a group's IQ, and region. The group consists of 10000 participants.

$X$ states regions.

  • $X_1$, region one has a probability of 0.2, so 2000 participants
  • $X_2$, region two has a probability of 0.8, so 8000 participants

$Z$ states the IQ. It is a normal distribution with mean 100, and standard deviation 10.

Out of both regions, participants IQ is:

    IQ       P(Z[IQ]) quantity
    60-70:   0.0020 - 20
    70-80:   0.0210 - 210
    80-90:   0.1360 - 1360
    90-100:  0.3410 - 3410
    100-110: 0.3410 - 3410
    110-120: 0.1360 - 1360
    120-130: 0.0210 - 210
    130-140: 0.0020 - 20

The only way I got the same results back if $P(Z|X_i) = P(Z)$:

  X[1]: 4,  42,  272,  682,  682,  272,  42,  4
  X[2]: 16, 168, 1088, 2728, 2728, 1088, 168, 16

I was trying out different setups for $P(Z|X_i)$ not be equal to $P(Z)$, with different means, or standard deviations, but by simply looking at the graphs, it is clear that the shape of them regardless of $P(X)$ won't form a normal distribution. According to my tries, I can't see a way to form a gaussian from two gaussians that aren't equal. However, in VAEs we're trying to accomplish that, so there must be something I'm getting wrong.


A mixture of Gaussians$$p_1\mathcal N(\mu_1,\sigma^2_1)+(1-p_1)\mathcal N(\mu_2,\sigma^2_2)$$is only a Gaussian when $$\mu_1=\mu_2\,\quad \sigma_1=\sigma_2$$ or when $$p_1\in\{0,1\}$$


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.