An important aspect of clustering algorithms is whether the partitions constructed on finite samples converge to a useful clustering of the whole data space as the sample size inc...
Ulrike von Luxburg, Olivier Bousquet, Mikhail Belk...
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
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
In this paper, we present an efficient algorithm for performing stepwise selection in the class of decomposable models. We focus on the forward selection procedure, but we also di...
Amol Deshpande, Minos N. Garofalakis, Michael I. J...
The (axis-parallel) stabbing number of a given set of line segments is the maximum number of segments that can be intersected by any one (axis-parallel) line. We investigate probl...