We consider semi-supervised classification when part of the available data is unlabeled. These unlabeled data can be useful for the classification problem when we make an assumpti...
The problem of optimal sequential decision for individual sequences, relative to a class of competing o -line reference strategies, is studied for general loss functions with memo...
Neri Merhav, Erik Ordentlich, Gadiel Seroussi, Mar...
This paper considers the regularized learning algorithm associated with the leastsquare loss and reproducing kernel Hilbert spaces. The target is the error analysis for the regres...
We consider the problem of accurately measuring the credit risk of a portfolio consisting of loans, bonds and other financial assets. One particular performance measure of interes...
Generalization bounds depending on the margin of a classifier are a relatively recent development. They provide an explanation of the performance of state-of-the-art learning syste...