Support nn.GaussianNLLLoss

Hi,

I would like to apply the Cockpit library to my problem, which is using the Gaussian log-likelihood for training. If I only want to look at first-order information, this loss function should already work with Backpack. However, I would be very interested in also seeing the second-order informations, for which explicit support in Backpack is needed.

What would it take to integrate this loss? I might be able to contribute as well if it is not too complicated.

The documentation is here: https://pytorch.org/docs/stable/generated/torch.nn.GaussianNLLLoss.html

Thanks!

Start with the linked PyTorch GaussianNLLLoss documentation and determine which second-order quantities Backpack must support for this loss. Review the project's existing loss-support conventions, then add coverage for GaussianNLLLoss and verify the relevant second-order outputs against the documented behavior.

Written by the indexing model from the issue text.