Optimal exponential bounds on the accuracy of classification

Details Optimal exponential bounds on the accuracy of classification Optimal exponential bounds on the accuracy of classification

2011-11-26

arxiv.org/abs/1111.6160v1

Statistics

Machine Learning

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Optimal exponential bounds on the accuracy of classification does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Optimal exponential bounds on the accuracy of classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal exponential bounds on the accuracy of classification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-483940