The focus is on black-box optimization of a function f : RN R given as a black box, i. e. an oracle for f-evaluations. This is commonly called direct search, and in fact, most meth...
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
Bartlett et al (2006) recently proved that a ground condition for convex surrogates, classification calibration, ties up the minimization of the surrogates and classification risk...
Clustering is often formulated as the maximum likelihood estimation of a mixture model that explains the data. The EM algorithm widely used to solve the resulting optimization pro...
Abstract--Kernel-based algorithms such as support vector machines have achieved considerable success in various problems in batch setting, where all of the training data is availab...
Jyrki Kivinen, Alex J. Smola, Robert C. Williamson