An Asymptotically Optimal Algorithm For Classification of Data Vectors with Independent Non-Identically Distributed Elements

In this paper, we propose a classifier for classification of data vectors with mutually independent but not identically distributed elements. For the proposed classifier, we prove that the error probability goes to zero as the length of the data vectors goes to infinity, even when there is only one training data vector per label available. Finally, we present numerical examples where we show that the performance of the proposed classifier outperforms conventional classification algorithms when the number of training data is small.