Optimal exponential bounds on the accuracy of classification

We consider a standard binary classification problem. The performance of any binary classifier based on the training data is characterized by the excess risk. We study Bahadur's type exponential bounds on the minimax accuracy confidence function based on the excess risk. We study how this quantity depends on the complexity of the class of distributions characterized by exponents of entropies of the class of regression functions or of the class of Bayes classifiers corresponding to the distributions from the class. We also study its dependence on margin parameters of the classification problem.