摘要

In the problem of classification (or pattern recognition), given a set of n samples, we attempt to construct a classifier g(n) with a small misclassification error. It is important to study the convergence rates of the misclassification error as n tends to infinity. It is known that such a rate can't exist for the set of all distributions. In this paper we obtain the optimal convergence rates for a class of distributions D(lambda,omega) in multicategory classification and nonstandard binary classification.

全文