James Arten's user avatar
James Arten's user avatar
James Arten's user avatar
James Arten
  • Member for 1 year, 4 months
  • Last seen this week
  • United States
3 votes
1 answer
108 views

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

2 votes
1 answer
129 views

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

2 votes
0 answers
120 views

Are spectral approaches to Graph Neural Networks still considered?

2 votes
1 answer
261 views

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

2 votes
1 answer
46 views

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

1 vote
1 answer
369 views

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

1 vote
0 answers
21 views

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

0 votes
0 answers
7 views

Choosing an appropriate loss function for sparse label proportion estimation

0 votes
0 answers
70 views

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

0 votes
0 answers
31 views

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

0 votes
0 answers
17 views

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

0 votes
0 answers
17 views

Parametric vs Non-parametric generative models

0 votes
0 answers
8 views

Derivation of the sparsemax loss function

0 votes
1 answer
56 views

What is intended for 1x1 convolution for input images?

0 votes
0 answers
35 views

Adding an attention mechanism to variational autoencoder

0 votes
1 answer
25 views

Are positional embeddings computed during or before training?

0 votes
0 answers
68 views

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

0 votes
0 answers
20 views

Incorporate specific constraints while training a (Conditional) variational autoencoder