Questions tagged [latent-variable]
The latent-variable tag has no usage guidance.
26 questions
0
votes
0
answers
15
views
Which generative model architecture (and loss function) should I use to train on a dataset of 3D arrays of embedded tokens?
I've curated a dataset of player-made Minecraft builds. Each unique Minecraft block is tokenized and treated as a unique "word" like in NLP. I've trained a Skip-Gram model on the dataset (...
- 1
0
votes
0
answers
22
views
VAE to compare two datasets
I have two cell-by-gene matrices, each representing gene counts for cells in sample 1 and sample 2. I'm interested in identifying common gene expression patterns across both samples. These patterns ...
- 111
2
votes
0
answers
83
views
VAE suffers from posterior collapse under all hyper parameters [closed]
I am trying to find a low-dimensional latent space representation for a bunch of simulated data. No matter what VAE architecture I try and no matter how I tweak it, the output of the VAE is always the ...
- 131
2
votes
2
answers
288
views
What is the meaning of log p(x) in VAE math and why is it constant
I was reading the article on medium, where the author cites this equation for Variational Inference:
\begin{align*}
\text{KL}(q(z|x^{(i)})||p(z|x^{(i)})) &= \int_z q(z|x^{(i)})\text{log}\frac{q(z|...
- 103
1
vote
0
answers
21
views
Is it reasonable to ask for the same time-regularity of the high and low dimensional signals?
Consider we are dealing with sequential data sampled from a continuous time signal $x(t)\in \mathbb{R}^n$, so that the dataset will look like $\{x_0,x_1,…,x_n\}$, with $x_i= x(t_i)$.
Assume that we ...
- 11
0
votes
0
answers
24
views
How to apply Latent Diffusion for 3D Binary Voxel Data?
Suppose we have a voxel of shape (60, 36, 60) with values 0 or 1 (1-occupied, 0-empty). What is the possible architecture of latent diffusion?
1
vote
0
answers
123
views
Are diffusion models still beneficial in highly compressed latent spaces?
Consider for example the MNIST dataset. When we apply diffusion to the pixel space, the image slowly becomes more and more noisy until white noise has been reached (like below). In the last step (t=...
- 1,217
1
vote
1
answer
99
views
Variational Lower Bound in VAE for Gaussian latent prior
From Bishop's recent book on Deep Learning, it says the ELBO for Gaussian latent prior can be approximated by
$\frac{1}{L}\sum_{l=1}^L \ln p(x_n|z_n^l,w) + KL(q(z_n|x_n,\phi)||p(z_n))$
where $n$ are ...
- 133
1
vote
0
answers
93
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
185
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 ...
- 660
3
votes
1
answer
133
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 ...
- 31
1
vote
1
answer
227
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
5
votes
2
answers
4k
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 (...
- 235
2
votes
1
answer
2k
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
1k
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
131
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 ...
- 1,171
2
votes
0
answers
36
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
35
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
452
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 ...
- 805
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 ...
- 805
4
votes
1
answer
156
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
238
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
39
votes
5
answers
22k
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" ...
- 41.4k
2
votes
0
answers
246
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 ...
- 21
1
vote
0
answers
75
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