Linked Questions

8
votes
1answer
2k views

How do Variational Auto Encoders backprop past the sampling step [duplicate]

From my understanding of VAE's, there's a step during training in the middle where, after the encoder produces a mean and standard deviation, random samples are drawn from the given learned ...
25
votes
1answer
5k views

What are variational autoencoders and to what learning tasks are they used?

As per this and this answer, autoencoders seem to be a technique that uses neural networks for dimension reduction. I would like to additionally know what is a variational autoencoder (its main ...
2
votes
3answers
564 views

Why is reparameterization trick necessary for variational autoencoders?

I know it is said that we do the reparameterization trick so we can do back-propagation and back-propagation cant be applied on random sampling! However, I don't precisely understand the last part. ...
5
votes
1answer
652 views

Why is random sampling a non-differentiable operation?

This answer states that we cannot back-propagate through a random node. So, in the case of VAEs, you have the reparametrisation trick, which shifts the source of randomness to another variable ...
3
votes
1answer
1k views

Basics of Reparametrization trick in Machine Learning

I am trying to understand the reparameterization trick (RPT) used in the calculation of stochastic backpropagation. There are already some excellent answers here and here. Under usual notation, we ...
0
votes
1answer
144 views

Reparameterization trick for exponential distribution

Is there way to generate Exponential(lambda) distributed samples via a reparameterization trick? As in: Reparameterization trick for gamma distribution And also: How does the reparameterization ...
0
votes
1answer
135 views

Meaning of “backpropagate through Gaussian distributions”?

I just started reading about GAN theory properly for the first time and I have a question about a comment in the original GAN paper. On page two there's a paragraph that states the following: ... ...
2
votes
1answer
97 views

Reparametrization trick

I am thinking about the reparameterization trick in a variational autoencoder. I know that it can be used with normal distribution. Can the reparameterization trick be applied to other distributions ...
1
vote
1answer
43 views

Adding a vector of values to encoder output in autoencoder (keras)

I am experimenting with autoencoders for a very specific application, but cannot unfortunately go into the specific details of what I am doing yet (fingers crossed I can do so after I make some ...
1
vote
1answer
53 views

A technical question about the reparametrisation trick

I was reading this post which enlightened me about the technicalities of the reparametrisation trick, but I only get the intuition of this equivalent transform and I'm not sure why it is true: $$𝐸_𝑞[...