Questions tagged [variational-inference]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
0answers
6 views

How does the VAE learn p(x,z)?

I found the following paragraph from An Introduction to Variational Autoencoders sounds relevant, but I am not fully understanding it. A VAE learns stochastic mappings between an observed $\mathbf{x}$...
0
votes
0answers
13 views

Tensorflow Probability Implementation of Automatic Differentiation Variational Inference with Mixtures

In this paper, the authors suggest using the following loss instead of the traditional ELBO in order to train what basically is a Variational Autoencoder with a Gaussian Mixture Model instead of a ...
0
votes
0answers
8 views

Question from Original GAN Paper: Variational Inference to Train Undirected Models

I was advised to split this post into separate questions. I am wondering why in the original GAN paper, it is claimed that variational inference is used in deep undirected models for inference. I was ...
0
votes
0answers
16 views

How accurate is this table from the original GAN paper summarizing difficulties and properties for deep generative models?

In the original GAN paper, they talk about how inference and training might be done in other deep generative models. In no particular order I was confused by: what is meant by "Learned ...
3
votes
1answer
77 views

What does the approximate posterior on latent variables, $q_\phi(z|x)$, tend to when optimising VAE's

The ELBO objective is described as follows $$ ELBO(\phi,\theta) = E_{q_\phi(z|x)}[log p_\theta (x|z)] - KL[q_\phi (z|x)||p(z)] $$ This form of ELBO includes a regularisation term in the form of the ...
2
votes
1answer
107 views

What is the intuition behind variational inference for Bayesian neural networks?

I'm trying to understand the concept of Variational Inference for BNNs. My source is this work. The aim is to minimize the divergence between the approx. distribution and the true posterior $$\text{KL}...