# Multivariate Gaussian Variational Autoencoder (the decoder part)

**URL:** <https://discuss.pytorch.org/t/multivariate-gaussian-variational-autoencoder-the-decoder-part/58235>\
**Category:** vision\
**Created:** [October 15, 2019, 2:59am UTC](https://discuss.pytorch.org/t/multivariate-gaussian-variational-autoencoder-the-decoder-part/58235 "2019-10-15T02:59:26Z")\
**Posts on this page:** 2\
**Page:** 2

<div class="post-metadata">

**Author:** ![e-pet](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/e-pet/32/64346_2.png) [@e-pet](https://discuss.pytorch.org/u/e-pet)\
**Post date:** [October 3, 2023, 10:33am UTC](https://discuss.pytorch.org/t/multivariate-gaussian-variational-autoencoder-the-decoder-part/58235/21 "2023-10-03T10:33:57Z")

</div>

Possibly related, since OP is (was) trying to simultaneously learn mean and variance:

- [machine learning - Is the optimization of the Gaussian VAE well-posed? - Cross Validated](https://stats.stackexchange.com/questions/373858/is-the-optimization-of-the-gaussian-vae-well-posed)
- “Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance.” [[2010.09042] Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression](https://arxiv.org/abs/2010.09042)

---

<div class="post-metadata">

**Author:** ![muammar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/muammar/32/76367_2.png) [@muammar](https://discuss.pytorch.org/u/muammar)\
**Post date:** [March 27, 2025, 12:58pm UTC](https://discuss.pytorch.org/t/multivariate-gaussian-variational-autoencoder-the-decoder-part/58235/22 "2025-03-27T12:58:25Z")

</div>

I just saw this. Thanks for sharing.

[Previous page](https://discuss.pytorch.org/t/multivariate-gaussian-variational-autoencoder-the-decoder-part/58235.md?page=1)