Loss¶
Todo
Fill overview page
|
An Unbinned Negative Log Likelihood with an additional poisson term for the number of events in the dataset. |
|
Unbinned Negative Log Likelihood. |
|
A “simultaneous fit” can be performed by giving one or more model, data, fit_range to the loss. |
|
Loss from a (function returning a) Tensor. |
EXPERIMENTAL! Enable a loss penalty if the loss is NaN, which can push back the minimizer. |