Tag Info

What is being optimized with WGAN loss? Is the generator maximizing or minimizing the critic value?

I think I understand what's happening with the loss functions now. Notation: D = discriminator/critic G = generator D(x) - Critic score on real data D(G(z)) - Critic score on fake data ∇_D - Critic ...

Visualizing the loss landscape in deep NN to compare optimization methods

How about: speed of convergence stability/variance w.r.t to the initial random seed (or other sources of variance like learning rate) presence/number of saddle points in your loss landscape
1 vote
Accepted

What does IOU3 mean in this context?

Since we would like to distinguish among IoU values close to 1.0, we use IOU3 as the ground truth score for the SRN. It seems to be just IoU to the power of 3. They use the cube function because they ...
• 136
1 vote

What does IOU3 mean in this context?

From context, I would say: Yes, it's IoU to the power of 3, since they want to have larger differences between values close to 1. Obviously, the difference between ...
• 175

What is the domain of the discriminator of a GAN?

Let me try to explain this way, comment if you think it's incorrect. Assume a simple linear function, $y=f(x)=ax+b$ where $a \in \mathbb{R}^*$ and $b\in \mathbb{R}$, each value of $y$ is unique, which ...
• 817

What is the domain of the discriminator of a GAN?

Formally, for an input $x$, $D(x)$ gives you the probability of $x$ being real. In this sense $D:\mathcal{X}\rightarrow [0,1]$, where $\mathcal{X}$ is the input space. That said, the output of the ...
Accepted

PPO: policy loss becomes nan

You might want to try substituting the exponentiation with a piecewise-defined function that uses a numerical approximation that is more numerically stable for low values of the exponent, such as ...
• 66