Optimal rates of convergence to Bayes risk in nonparametric discrimination (Q760130)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Optimal rates of convergence to Bayes risk in nonparametric discrimination |
scientific article |
Statements
Optimal rates of convergence to Bayes risk in nonparametric discrimination (English)
0 references
1983
0 references
Consider the multiclassification (discrimination) problem with known prior probabilities and a multi-dimensional vector of observations. Assume the underlying densities corresponding to the various classes are unknown but a training sample of size N is available from each class. Rates of convergence to Bayes risk are investigated under smoothness conditions on the underlying densities of the type often seen in nonparametric density estimation. These rates can be drastically affected by a small change in the prior probabilities, so the error criterion used here is Bayes risk averaged (uniformly) over all prior probabilities. Then it is shown that a certain rate, \(N^{-r}\), is optimal in the sense that no rule can do better (uniformly over the class of smooth densities) and a rule is exhibited which does that well. The optimal value of r depends on the smoothness of the distribution and the dimensionality of the observations in the same way as for nonparametric density estimation with integrated square error loss.
0 references
optimal rates
0 references
multiclassification
0 references
discrimination
0 references
known prior probabilities
0 references
training sample
0 references
Rates of convergence to Bayes risk
0 references
smooth densities
0 references