Many network applications that need to distribute content and data to a large number of clients use a hybrid scheme in which one (or more) multicast channel is used in parallel to...
Bayesian Kullback Ying—Yang dependence reduction system and theory is presented. Via stochastic approximation, implementable algorithms and criteria are given for parameter lear...
We derive PAC-Bayesian generalization bounds for supervised and unsupervised learning models based on clustering, such as co-clustering, matrix tri-factorization, graphical models...
Testability is one of the most important factors that are considered during design cycle along with reliability, speed, power consumption, cost and other factors important for a c...
To achieve correct execution of peer-to-peer applications on non-reliable resources, we present a portable and distributed algorithm that provides fault tolerance and result checki...