Neyman-Pearson loss : penalizes false positives :: Logistic loss : ?

Neyman‑Pearson loss is tuned to keep the number of false positives low, so it focuses on the cost of a positive prediction that turns out to be wrong. Logistic loss, or cross‑entropy loss, treats every misclassification the same way: it assigns a high penalty whenever the predicted probability for the true class is low, regardless of whether the error is a false positive or a false negative. In other words, logistic loss penalizes the lack of confidence in the correct class, encouraging the model to output high probability for the true label and low probability for the others. For example, if the true label is 1 but the model outputs 0. 1, the loss is –log 0.