Z-loss definition

[Jbiloki]

Hey folks, I was looking into the loss function here and see there is a z loss added to the typical log loss definition.

The only paper I could surface on this was https://arxiv.org/abs/1604.08859 but I don't see the correlation. In the code it is logsumexp of the logits squared.

But in the paper it is calculating mean/variance for the z-loss you can see the author's implementation here I am asking for help either connecting the two or looking for resources on the current implementation if they are infact unrelated.

Thank you.