While these algorithms havebeen extensively studied, both theoretically and practically, see, e.g., [10], many questions remain open. In particular, most results are based onthecase where theestimatord V isunbiased.

Adversarially robust classification, that has been of much recent interest, is typically formulated as follows.

Cross-EntrWeuse ylog (f (x)) (1 y) log ( f (x)).