We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
We study a class of overrelaxed bound optimization algorithms, and their relationship to standard bound optimizers, such as ExpectationMaximization, Iterative Scaling, CCCP and No...
We consider geometric conditions on a labeled data set which guarantee that boosting algorithms work well when linear classifiers are used as weak learners. We start by providing ...
We describe a new family of topic-ranking algorithms for multi-labeled documents. The motivation for the algorithms stems from recent advances in online learning algorithms. The a...
Bounded Model Checking (BMC) is a successful refutation method to detect errors in not only circuits and other binary systems but also in systems with more complex domains like ti...