We show how variational Bayesian inference can be implemented for very large generalized linear models. Our relaxation is proven to be a convex problem for any log-concave model. ...
In this paper we study a new framework introduced by Vapnik (1998) and Vapnik (2006) that is an alternative capacity concept to the large margin approach. In the particular case o...
We provide a general framework for learning precise, compact, and fast representations of the Bayesian predictive distribution for a model. This framework is based on minimizing t...
In this paper, we discuss a technique for handling multi-class problems with binary classifiers, namely to learn one classifier for each pair of classes. Although this idea is kno...
We consider the problem of optimality, in a minimax sense, and adaptivity to the margin and to regularity in binary classification. We prove an oracle inequality, under the margin ...