We study a class of generalized bundle methods for which the stabilizing term can be any closed convex function satisfying certain properties. This setting covers several algorithm...
We consider the problem of providing opportunistic spectrum access to secondary users in wireless cellular networks. From the standpoint of spectrum license holders, achieving ben...
Ashraf Al Daoud, Murat Alanyali, David Starobinski
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...
An important theoretical tool in machine learning is the bias/variance decomposition of the generalization error. It was introduced for the mean square error in [3]. The bias/vari...