Recent theoretical results have shown that improved bounds on generalization error of classifiers can be obtained by explicitly taking the observed margin distribution of the trai...
In most of the learning algorithms, examples in the training set are treated equally. Some examples, however, carry more reliable or critical information about the target than the ...
Ling Li, Amrit Pratap, Hsuan-Tien Lin, Yaser S. Ab...
Boosting algorithms build highly accurate prediction mechanisms from a collection of lowaccuracy predictors. To do so, they employ the notion of weak-learnability. The starting po...
Soft constraints are a generalization of classical constraints, where constraints and/or partial assignments are associated to preference or importance levels, and constraints are...
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...