TrainingRecurrentNeuralNetworksviaForwardPropagationThroughTimeAnilKag1VenkateshSaligrama1Abstractempiricalriskfunction:Back-Propagationthroughtime(BPTT)hasbeen[W∗,v∗]=argminL(W,v)=1NT(yi,yˆti)w...
ATheoryofLabelPropagationforSubpopulationShiftTianleCai12RuiqiGao12JasonD.Lee1QiLei1Abstracttees.Manyoftheworksarebasedonthecovariateshiftas-sumption(Heckman,1979;Shimodaira,2000),whichstatesOneoft...
StateSpaceExpectationPropagation:EfficientInferenceSchemesforTemporalGaussianProcessesWilliamJ.Wilkinson1PaulE.Chang1MichaelRiisAndersen2ArnoSolin1AbstractFiltering/Forwardpass→←Smoothing/Backwar...
BeyondSignalPropagation:IsFeatureDiversityNecessaryinDeepNeuralNetworkInitialization?YanivBlumenfeld1DarGilboa2DanielSoudry1Abstractadetailedanalysisoftheirdynamicsandgeneralizationproperties.Unlik...
GeneralizedApproximateSurveyPropagationforHigh-DimensionalEstimationLucaSaglietti12YueM.Lu3CarloLucibello41AbstractpredictedthroughadynamicalsysteminvolvingonlyscalarquantitiescalledStateEvolution(...
TensorBeliefPropagationAndrewWrigley1WeeSunLee2NanYe3Abstractsationproblemandconstructsapproximationsbysolvingrelaxationsoftheoptimisationproblem.Anumberofwell-Weproposeanewapproximateinferencealgo...
meProp:SparsifiedBackPropagationforAcceleratedDeepLearningwithReducedOverfittingXuSun12XuanchengRen12ShumingMa12HoufengWang12Abstractsuchthatonlyhighlyrelevantparametersareupdatedandotherparameters...