We study two design criteria for classification: the Neyman--Pearson criterion and a min--max criterion. For each we prove a lemma bounding estimation error in terms of error deviance. We then show how these lemmas can be used to determine probabilistic guarantees on estimation error.
A. Cannon, J. Howse, D. Hush, and C. Scovel, Learning with the Neyman-Pearson and min-max criteria. Los Alamos National Laboratory Technical Report LA-UR-02-2951, 2002. [ Abstract | PostScript (208 KB) | PDF (196 KB) ]
