...
- Not to regress the neutrino p_{T} pT directly, as the pT distribution might not be unimodal. Instead, try two different approaches
- Quantile regression with the median
- Auxilary task based on classification of neutrino pT class prediction, i.e. ., predict the bin 0-1 for the ratio of neutrino pT & jet pT. Also, add overflow bin
- loss function based on median rather than mean square error, ie, MAE rather than MSE