Context: https://arxiv.org/pdf/1312.6114.pdf

So if I start with this equation: $$ \mathcal{L}\left(\boldsymbol{\theta}, \boldsymbol{\phi} ; \mathbf{x}^{(i)}\right) \simeq \frac{1}{2} \sum_{j=1}^{J}\left(1+\log \left(\left(\sigma_{j}^{(i)}\right)^{2}\right)-\left(\mu_{j}^{(i)}\right)^{2}-\left(\sigma_{j}^{(i)}\right)^{2}\right)+\frac{1}{L} \sum_{l=1}^{L} \log p_{\boldsymbol{\theta}}\left(\mathbf{x}^{(i)} \mid \mathbf{z}^{(i, l)}\right) $$ where $\mathbf{z}^{(i, l)}=\boldsymbol{\mu}^{(i)}+\boldsymbol{\sigma}^{(i)} \odot \boldsymbol{\epsilon}^{(l)} \quad$ and $\quad \boldsymbol{\epsilon}^{(l)} \sim \mathcal{N}(0, \mathbf{I})$

So I'm looking at this part of the equation in particular: $$\frac{1}{L}\sum_{l=1}^{L} \log p_{\boldsymbol{\theta}}\left(\mathbf{x}^{(i)} \mid \mathbf{z}^{(i, l)}\right) $$

And I'm looking at it where the decoder is a multivariate Gaussian with a diagonal covariance structure: $$ \begin{aligned} \log p(\mathbf{x} \mid \mathbf{z}) &=\log \mathcal{N}\left(\mathbf{x} ; \boldsymbol{\mu}, \boldsymbol{\sigma}^{2} \mathbf{I}\right) \\ \end{aligned} $$

In this stackexchange discussion, https://ai.stackexchange.com/questions/27341/in-variational-autoencoders-why-do-people-use-mse-for-the-loss, a few answers and comments talk about how manipulating this particular log(p(x|z)) bgets something that resembles the MSE.

So, if you are trying to predict e.g. floating-point numbers (in the case of images, these can be the RGB values in the range $[0,1])$, then you can assume $p_{\boldsymbol{\theta}}(\mathbf{x} \mid \mathbf{z})$ is a Gaussian, then you can equivalently minimise the MSE between the prediction of the decoder and the real image in order to maximise the likelihood. You can easily show this: just replace $p_{\boldsymbol{\theta}}(\mathbf{x} \mid \mathbf{z})$ with the Gaussian $\mathrm{pdf}_{1}$ then maximise that wrt the parameters, and you should end up with something that resembles the MSE.

And similarily in this discussion, Loss function autoencoder vs variational-autoencoder or MSE-loss vs binary-cross-entropy-loss, it is mentioned that

If you assume it follows a normal distribution you will end up with a MSE minimization since $p(x \mid z)$ can be reformulated as $p(x \mid \hat{x}) \sim \mathcal{N}(\hat{x}, \sigma)$

My question is, how do we show that this is true?

This is my attempt:

$$C= \mathbf{\sigma^2 I}$$ is the covariance matrix, and $$\sigma_i^2$$ is the ith diagonal values of this marix;

So then $$N(\textbf{x};\mathbf{\mu},\textbf{C}) =\frac{1}{(2 \pi)^{L/2} \sqrt{det(\textbf{C})}}exp(\frac{-1}{2} (\textbf{x}- \mathbf{\mu})^T C^{-1}(\textbf{x}-\mathbf{\mu}))$$

$$det(\textbf{C}) =\prod{\sigma_i^2}$$

$$ log(N(\textbf{x};\mathbf{\mu},\textbf{C}))=\frac{-L}{2} log(2\pi) + \frac{-1}{2} log(\prod{\sigma_i^2} ) + \sum{ \frac{(x_i-\mu_i)^2}{-2 \sigma_i^2}}$$

$$= \frac{-L}{2} log(2\pi) + \frac{-1}{2} \sum{\sigma_i^2} + \sum{ \frac{(x_i-\mu_i)^2}{-2 \sigma_i^2}} $$

And from this point, I am not sure what to do next.


2 Answers 2


Starting from $$ \frac{-L}{2} log(2\pi) + \frac{-1}{2} \sum{\sigma_i^2} + \sum{ \frac{(x_i-\mu_i)^2}{-2 \sigma_i^2}} $$

$L$, the dimension, is a fixed quantity. $\sigma$ is also a fixed quantity, with $\sigma_i = \sigma_j$ for all $i,j$ (you can choose to treat it as a variable, but this is rarely done, and doesn't lead to MSE). So we can drop the first two terms, since they are constant, and we're left with

$$ -\frac{1}{2\sigma^2}\sum_i{ (x_i-\mu_i)^2} $$

Maximizing this quantity is equivalent to minimizing $\sum_i (x_i-\mu_i)^2$, which is MSE.

  • $\begingroup$ So I know $$\sum{ (x_i-\mu_i)^2}$$ looks similar to MSE,but there is one thing I am not understanding. Because typically if $$y_i$$ is the true label, and $$\hat{y_i}$$ is the estimated label, $$\sum{ (y_i-\hat{y_i})^2}$$ is the MSE , what is the $$y_i $$ and the $$\hat{y_i}$$ in $$\sum{ (x_i-\mu_i)^2}$$ $\endgroup$
    – a12345
    Commented Aug 16, 2021 at 19:24
  • $\begingroup$ @a12345 be careful not to conflate the i in your original attempt, which indexes the dimensions of each data point, with an i which indexes the data points. in this case, $y_i^{(j)}$, the $i$th dimension of the $j$th datapoint, is $x_i^{(j)}$, and $\hat y_i^{(j)}$ is $\mu_i^{(j)}$ $\endgroup$
    – shimao
    Commented Aug 16, 2021 at 19:31
  • $\begingroup$ Ok, thats interesting,but confusing. Because the paper has the following formula: $\mathbf{z}^{(i, l)}=\boldsymbol{\mu}^{(i)}+\boldsymbol{\sigma}^{(i)} \odot \boldsymbol{\epsilon}^{(l)} \quad$ and $\quad \boldsymbol{\epsilon}^{(l)} \sim \mathcal{N}(0, \mathbf{I})$ (using notation from the paper) Then it gets fed to the decoder, which then outputs something. I thought that would be the $\hat{y}_{i}^{(j)}$ (using your notation in the comment) instead of $\mu_{i}^{(j)}$ (using your notation in the comment) $\endgroup$
    – a12345
    Commented Aug 18, 2021 at 4:26

I agree with shimao. $y_i^{(j)}$ is $x_i^{(j)}$, $\hat{y}_i^{(j)}$ is $\mu_i^{(j)}$ for jth datapoint.

But the $\hat{y}_i^{(j)}$(or $\mu_i^{(j)}$) should not be considered model output (estimated label). The model obtains the output by sampling in the distribution $N(x|\hat{\mu}_i^{(j)}, \hat{\sigma}_i^{(j)})$.

In VAE training, we don't need sampling in the decoder,no estimated label, we just maximize the reconstruction loss $p(x|z)$,this is a likelihood, as shimao said, this is equivalent to minimizing $\sum_i x_i^{j} - \mu_i^{j}$, similar in form to MSE.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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