: As the Web grows in importance in institutional settings, so does the need for training. Universities are looking at the daunting task of putting more information and services on...
In this paper we study a paradigm to generalize online classification algorithms for binary classification problems to multiclass problems. The particular hypotheses we investig...
Kernel methods have been successfully applied to many machine learning problems. Nevertheless, since the performance of kernel methods depends heavily on the type of kernels being...
Tianbao Yang, Mehrdad Mahdavi, Rong Jin, Jinfeng Y...
We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...
Educational on-line resources are expanding in their application beyond delivering courses to providing venues in which members of professional communities of practice meet to exc...