Questions tagged [latent-variable]
The latent-variable tag has no usage guidance.
19
questions
0
votes
0
answers
7
views
I have n-dimensional latent representational data, with a y logit label: How do I find peaks in the data using the label?
I essentially need a "find peaks" algorithm for when the input data is n-dimensional.
Specifically, in the latent space of my neural network I have have collected all the training data ...
- 101
1
vote
0
answers
57
views
Pointers to (deep) latent variable models that admit analytical approximations
I am aware that there is a plethora of deep generative models out there (e.g. variational autoencoders (VAE), GANs) that can model high-dimensional data as the images of latent variables under a non-...
- 111
2
votes
1
answer
75
views
how the GAN architecture maintain similar images close in the latent space?
I am learning about generative models, and I don't quite understand how the GAN architecture can maintain similar generated images close in the latent space. For example, an autoencoder and a ...
- 453
2
votes
1
answer
53
views
Clarification on the training objective of denoising diffusion models
I'm reading the Denoising Diffusion Probabilistic Models paper (Ho et al. 2020). And I am puzzled about the training objective. I understood (I think) the trick regarding the reparametrization of the ...
- 21
1
vote
1
answer
176
views
Can you extrapolate outside the latent distribution for GANs?
I was wondering what happens when you extrapolate out of the latent space distribution (noise vector) for a Generative adversarial network (GAN). Can anybody explain this?
- 35
4
votes
2
answers
2k
views
How to generate new data given a trained VAE - sample from the learned latent space or from multivariate Gaussian?
To generate synthetic dataset using a trained VAE, there is confusion between two approaches:
Use learned latent space: z = mu + (eps * log_var) to generate (...
- 225
2
votes
1
answer
1k
views
Could it make any sense to choose a larger dimension for the latent space of the VAE with respect to the original input?
Could it make any sense to choose a larger dimension for the latent space of the VAE with respect to the original input?
For example, we may want to learn how to reconstruct a relatively low-...
- 307
1
vote
0
answers
837
views
What is the most suitable measure of the distance between two VAE's latent spaces?
The problem I'm trying to solve is as follows.
I have two separate domains, where inputs do not have the same dimensions. However, I want to create a common feature space between both domains using ...
1
vote
2
answers
1k
views
Is it possible to have a variable-length latent vector in an autoencoder?
I'm trying to have a simple autoencoder but with variable latent length (the network can produce variable latent lengths with respect to the complexity of the input), but I've not seen any related ...
- 420
1
vote
1
answer
122
views
What is meant by degrees of freedom of latent variables?
...Designing such a likelihood function is typically challenging; however, we observe that features like spectrogram are effective when latent variables have limited degrees of freedom. This motivates ...
- 1,131
2
votes
0
answers
34
views
Why do hypercube latent spaces perform poorer than Gaussian latent spaces in generative neural networks?
I have a quick question regarding the use of different latent spaces to represent a distribution. Why is it that a Gaussian is usually used to represent the latent space of the generative model ...
- 121
2
votes
0
answers
32
views
Does bottleneck size matter in Disentangled Variational Autoencoders?
I suppose that picking an appropriate size for the bottleneck in Autoencoders is neither a trivial nor an intuitive task. After watching this video about VAEs, I've been wondering: Do disentangled ...
- 21
2
votes
1
answer
390
views
In this VAE formula, why do $p$ and $q$ have the same parameters?
In $$\log p_{\theta}(x^1,...,x^N)=D_{KL}(q_{\theta}(z|x^i)||p_{\phi}(z|x^i))+\mathbb{L}(\phi,\theta;x^i),$$ why does $p(x^1,...,x^N)$ and $q(z|x^i)$ have the same parameter $\theta?$
Given that $p$ is ...
- 737
6
votes
1
answer
1k
views
Why is the evidence equal to the KL divergence plus the loss?
Why is the equation $$\log p_{\theta}(x^1,...,x^N)=D_{KL}(q_{\theta}(z|x^i)||p_{\phi}(z|x^i))+\mathbb{L}(\phi,\theta;x^i)$$ true, where $x^i$ are data points and $z$ are latent variables?
I was ...
- 737
4
votes
1
answer
151
views
What are some new deep learning models for learning latent representation of data?
I know that autoencoders are one type of deep neural networks that can learn the latent representation of data. I guess there should be several other models like autoencoders.
What are some new deep ...
- 143
3
votes
2
answers
205
views
Do we also need to model a probability distribution for the decoder of a VAE?
I'm working on understanding VAEs, mostly through video lectures of Stanford cs231n, in particular lecture 13 tackles on this topic and I think I have a good theoretical grasp.
However, when looking ...
- 365
38
votes
5
answers
18k
views
What is the difference between latent and embedding spaces?
In general, the word "latent" means "hidden" and "to embed" means "to incorporate". In machine learning, the expressions "hidden (or latent) space" ...
- 39.6k
1
vote
0
answers
232
views
How can VAE have near perfect reconstruction but still output junk when using random noise input
I am creating a VAE for time series data using CNNs. The data has 4800 timesteps and 4 features. It is standardized and normalized. The network I am using is implemented in Keras as follows. I have ...
- 11
1
vote
0
answers
65
views
What kind of distributions can be used to model discrete latent variables?
If we take the vanilla variational auto-encoder (VAE), we $p(z)$ is a Gaussian distribution with zero mean and unit variance and we approximate $p(z|x) \approx q(z|x)$ to be a Gaussian distribution as ...
- 173