Abstract-- Identification of output error models from frequency domain data generally results in a non-convex optimization problem. A well-known method to approach the output error...
Abstract. In the late nineties, Erickson proved a remarkable lower bound on the decision tree complexity of one of the central problems of computational geometry: given n numbers, ...
We consider the existence of a linear weak learner for boosting algorithms. A weak learner for binary classification problems is required to achieve a weighted empirical error on t...
Supervised learning uses a training set of labeled examples to compute a classifier which is a mapping from feature vectors to class labels. The success of a learning algorithm i...
We present a formal procedure for structure-preserving model reduction of linear second-order and Hamiltonian control problems that appear in a variety of physical contexts, e.g., ...