Classical statistical learning theory studies the generalisation performance of machine learning algorithms rather indirectly. One of the main detours is that algorithms are studi...
We investigate the problem of how to extend constraint query languages with aggregate operators. We deal with standard relational aggregation, and also with aggregates speci c to ...
Intense research on virtual machines has highlighted the need for flexible software architectures that allow quick evaluation of new design and implementation techniques. The inte...
Rademacher and Gaussian complexities are successfully used in learning theory for measuring the capacity of the class of functions to be learned. One of the most important propert...
A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class...