Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the ...
Motivated by the poor performance (linear complexity) of the EM algorithm in clustering large data sets, and inspired by the successful accelerated versions of related algorithms l...
Deacon has recently proposed that complexes of genes can be integrated into functional groups as a result of environmental changes that mask and unmask selection pressures. For exa...
Janet Wiles, James Watson, Bradley Tonkes, Terrenc...
We give an algorithm that learns any monotone Boolean function f : {-1, 1}n {-1, 1} to any constant accuracy, under the uniform distribution, in time polynomial in n and in the de...
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...