James Arten's user avatar
James Arten's user avatar
James Arten's user avatar
James Arten
  • Member for 1 year, 6 months
  • Last seen this week
  • United States
0 votes
1 answer
51 views

How to encode time embeddings in a diffusion model for 1D vectors?

5 votes
2 answers
222 views

What is the exact role of model $p_\theta$ in diffusion models for the reverse process?

0 votes
0 answers
10 views

Choosing an appropriate loss function for sparse label proportion estimation

1 vote
0 answers
70 views

Out of distribution detection (OOD) in the context of regression problems

0 votes
0 answers
18 views

Derivation of the sparsemax loss function

2 votes
1 answer
654 views

Could it make any sense to choose a larger dimension for the latent space of the VAE with respect to the original input?

0 votes
0 answers
29 views

Parametric vs Non-parametric generative models

2 votes
1 answer
196 views

Why do we use a linear interpolation of fake and real data to penalize the gradient of discriminator in WGAN-GP

0 votes
0 answers
37 views

How to generate data lying in the union of different hyperplanes using a VAE

2 votes
1 answer
394 views

What is multi-head attention doing mathematically, and how is it different from self-attention?

0 votes
0 answers
86 views

Interpretation of the loss function of Wasserstein GAN: the lower the better?

0 votes
1 answer
82 views

What is intended for 1x1 convolution for input images?

0 votes
0 answers
77 views

In CVAE's objective function, why do both terms condition on $\textbf{c}$?

0 votes
0 answers
57 views

Adding an attention mechanism to variational autoencoder

2 votes
1 answer
47 views

Is there a way to inject linear constrains during GAN training?

0 votes
1 answer
30 views

Are positional embeddings computed during or before training?

0 votes
0 answers
29 views

Incorporate specific constraints while training a (Conditional) variational autoencoder

2 votes
0 answers
137 views

Are spectral approaches to Graph Neural Networks still considered?