Loss function to optimise signal significance in particle physics
This addresses the need for improved sensitivity in particle physics searches at colliders, though it appears incremental as it builds on existing classification methods.
The authors tackled the problem of optimizing signal significance in particle physics by constructing a surrogate loss function, which resulted in models with higher signal efficiency for similar estimated significance compared to cross-entropy loss.
We construct a surrogate loss to directly optimise the significance metric used in particle physics. We evaluate our loss function for a simple event classification task using a linear model and show that it produces decision boundaries that change according to the cross sections of the processes involved. We find that the models trained with the new loss have higher signal efficiency for similar values of estimated signal significance compared to ones trained with a cross-entropy loss, showing promise to improve sensitivity of particle physics searches at colliders.