The "minimum margin" of an ensemble classifier on a given training set is, roughly speaking, the smallest vote it gives to any correct training label. Recent work has sh...
Boosting is a popular approach for building accurate classifiers. Despite the initial popular belief, boosting algorithms do exhibit overfitting and are sensitive to label noise. ...
Capacity control in perceptron decision trees is typically performed by controlling their size. We prove that other quantities can be as relevant to reduce their flexibility and co...
Kristin P. Bennett, Nello Cristianini, John Shawe-...
Abstract. We present several results related to ranking. We give a general margin-based bound for ranking based on the L∞ covering number of the hypothesis space. Our bound sugge...
This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels induced by the harmonic fun...
Branislav Kveton, Michal Valko, Ali Rahimi, Ling H...