We consider the problem of structured classification, where the task is to predict a label y from an input x, and y has meaningful internal structure. Our framework includes super...
Peter L. Bartlett, Michael Collins, Benjamin Taska...
Congestion control algorithms, such as TCP or the closelyrelated additive increase-multiplicative decrease algorithms, are extremely difficult to simulate on a large scale. The re...
Abstract. The availability of reliable models of computer virus propagation would prove useful in a number of ways, in order both to predict future threats, and to develop new cont...
Clarkson's algorithm is a two-staged randomized algorithm for solving linear programs, but it can also be applied to the more general LP-type problems which comprise a number...
In this work, we present a general method for approximating nonlinear transformations of Gaussian mixture random variables. It is based on transforming the individual Gaussians wi...