Questions tagged [wasserstein-metric]
For questions about the Wasserstein metric/distance (or Kantorovich–Rubinstein metric), which is a metric (distance function) defined between probability distributions.
5
questions
6
votes
2answers
161 views
Why is KL divergence used so often in Machine Learning?
The KL Divergence is quite easy to compute in closed form for simple distributions -such as Gaussians- but has some not-very-nice properties. For example, it is not symmetrical (thus it is not a ...
2
votes
1answer
93 views
Are there some notions of distance between two policies?
I want to determine some distance between two policies $\pi_1 (a \mid s)$ and $\pi_2 (a \mid s)$, i.e. something like $\vert \vert \pi_1 (a \mid s) - \pi_2(a \mid s) \vert \vert$, where $\pi_i (a\mid ...
1
vote
0answers
25 views
WGAN-GP Loss formalization
I have to write the formalization of the loss function of my network, built following the WGAN-GP model. The discriminator takes 3 consecutive images as input (such as 3 consecutive frames of a video) ...
0
votes
0answers
26 views
Wasserstein GAN with gradient penality - Loss values
I have trained a WAN with gradient penalty and the loss values seem to me much higher than the examples I have seen on the net. The generator receives 2 images as input and must generate a ...
3
votes
1answer
73 views
What is the reason for mode collapse in GAN as opposed to WGAN?
In this article I am reading:
$D_{KL}$ gives us inifity when two distributions are disjoint. The value of $D_{JS}$ has sudden jump, not differentiable at $\theta=0$. Only Wasserstein metric provides ...
