A predicate P : {−1, 1}k → {0, 1} can be associated with a constraint satisfaction problem Max CSP(P). P is called “approximation resistant” if Max CSP(P) cannot be approxi...
A new algorithm for performing classification with imperfectly labeled data is presented. The proposed approach is motivated by the insight that the average prediction of a group ...
Fault tolerant algorithms are often designed under the t-out-of-n assumption, which is based on the assumption that all processes or components fail independently with equal proba...
We consider the problem of learning a hypergraph using edge-detecting queries. In this model, the learner may query whether a set of vertices induces an edge of the hidden hypergr...
AdaCost, a variant of AdaBoost, is a misclassification cost-sensitive boosting method. It uses the cost of misclassifications to update the training distribution on successive boo...
Wei Fan, Salvatore J. Stolfo, Junxin Zhang, Philip...