How to deal with the negative loss?

[Mrils]

Hi!
When I try to increase the uncertainty part (described as the log section in your paper) in the network, the loss changed to negative.
Is this normal？ How did you solve it?

[minygd]

I think it's fine, as log(x) can always have a negative value when x < 1.

[Mrils]

So what is the direction of network optimization?
Minimize the absolute value of network loss?

[Matteo Poggi]

Hi @Mrils
that's correct. The optimization process pushes the denominator in Eq. 12,13 to be high, thus avoiding both the second term and the total loss to reach -infinite.

[Mrils]

So will the loss stabilize around a negative value after some epochs?

[Matteo Poggi]

Correct. In our experiments, this occurred quite early

[Mrils]

Got it! Thank you

[jilner]

Dear Mrils, I have trouble writing the loss function when reproduction the training, could you share me the loss function codes and I would be very grateful to you!