2026
Neyman-Pearson Classification under Both Null and Alternative Distributions Shift
ICLR 2026poster
We consider the problem of transfer learning in Neyman–Pearson classification, where the objective is to minimize the error w.r.t. a distribution $\mu_1$, subject to the constraint that the error w.r.t. a distribution $\mu_0$ remains below a prescribed threshold. While transfer learning has been ext…