PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification

Details PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification

2012-02-28

arxiv.org/abs/1202.6228v2

Statistics

Machine Learning

Scientific paper

In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical use of the confusion matrix of a classifier as an error measure; this puts our contribution in the line of work aiming at dealing with performance measure that are richer than mere scalar criterion such as the misclassification rate. Thanks to very recent and beautiful results on matrix concentration inequalities, we derive two bounds showing that the true confusion risk of the Gibbs classifier is upper-bounded by its empirical risk plus a term depending on the number of training examples in each class. To the best of our knowledge, this is the first PAC-Bayes bounds based on confusion matrices.

Affiliated with

Also associated with

No associations

Rating

PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class 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 PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-610099