Confusion about Lambda

[ForgottenOneNyx]

Hello, Firstly thank you for the awesome work!
I had a question in the Pytorch_Wasserstein.ipynb:

In the WassersteinLossVanilla, why is it
self.K = torch.exp(-self.cost/self.lam) ?
Shouldn't it be
self.K = torch.exp(-self.cost*self.lam)?

In mocha also it is the above https://github.com/pluskid/Mocha.jl/blob/5e15b882d7dd615b0c5159bb6fde2cc040b2d8ee/src/layers/wasserstein-loss.jl#L33

Have you changed it because "Note that we use a different convention for $\lambda$ (i.e. we use $\lambda$ as the weight for the regularisation, later versions of the above use $\lambda^-1$ as the weight)." ?

Also what is the reason for the above?

[t-vi]

Hi,
They're mostly equivalent, to me the more natural view seemed to be lambda as the same unit as cost.
In the meantime I revised the notebook to feature a kernel and added a writeup of my maths.

Best regards

Thomas