Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift
It is shown that under symmetric corruption the label-dependent part of a criterion linear in the label indicator is multiplied by one common factor whenever its coefficient sums are candidate-invariant, a class holding teacher contrasts and accuracy but not cross-entropy.
Alejandro Rodríguez Domínguez, Muhammad Shahzad, Xia Hong
· 0 citations