FiedlerRegularization:LearningNeuralNetworkswithGraphSparsityEdricTam1DavidDunson1Abstractthusbeendeveloped.Thesetechniquesoftenregularizethenetworksfromaglobal/uniformperspective,e.g.weightde-Wein...
TraditionalandHeavyTailedSelfRegularizationinNeuralNetworkModelsCharlesH.Martin1MichaelW.Mahoney2Abstracttheorydidnotapplytothesesystems(Vapniketal.,1994).Itwasoriginallyassumedthatlocalminimainthe...
RegularizationinDirectableEnvironmentswithApplicationtoTetrisJanMalteLichtenberg1O¨zgu¨rS¸ims¸ek1AbstractonRegularization.Specifically,weproposeamodelthatintroducesabiastowardgivingallfeaturese...
OnDropoutandNuclearNormRegularizationPooryaMianjy1RamanArora1Abstractislinear,therepresentationinfactoredformmakestheop-timizationlandscapenon-convexandhence,challengingWegiveaformalandcompletechar...
Learning-to-LearnStochasticGradientDescentwithBiasedRegularizationGiuliaDenevi12CarloCiliberto34RiccardoGrazzi14MassimilianoPontil14Abstracttasksfromaprescribedfamily.Tohighlightthedifferencebetwee...
EfficientFull-MatrixAdaptiveRegularizationNamanAgarwal1BrianBullins12XinyiChen1EladHazan12KaranSingh12CyrilZhang12YiZhang12AbstractThisbringsustoadaptiveRegularization:themostsophis-ticated,hardtoi...
DiscriminativeRegularizationforLatentVariableModelswithApplicationstoElectrocardiographyAndrewC.Miller1ZiadObermeyer2JohnP.Cunningham3SendhilMullainathan4Abstracttion(e.g.atrialfibrillationorafib,a...
ControlRegularizationforReducedVarianceReinforcementLearningRichardCheng1AbhinavVerma2Ga´borOrosz3SwaratChaudhuri2YisongYue1JoelW.Burdick1Abstractrithmsfocusonmaximizingthelong-termrewardthroughtr...
ALarge-ScaleStudyonRegularizationandNormalizationinGANsKarolKurach1MarioLucic1XiaohuaZhai1MarcinMichalski1SylvainGelly1Abstractfromthetruedistributionorweresynthesizedbythegenera-tor.Thesolutiontot...
StochasticPCAwith2and1RegularizationPooryaMianjy1RamanArora1Abstractsubspacethatmaximizesthevarianceindataprojectedontothesubspace,i.e.E[Ux2],amongallk-dimensionalsub-Werevisitconvexrelaxationbased...
Noisin:UnbiasedRegularizationforRecurrentNeuralNetworksAdjiB.Dieng1RajeshRanganath2JaanAltosaar3DavidM.Blei1Abstractvationconditionalonitsstate.ThekeyelementofanRNNisitstransitionfunction.Thetransi...
LearningCompactNeuralNetworkswithRegularizationSametOymak1Abstractertiesofcomplexneuralnetworkmodels.Significantques-tionsofinterestincludeefficienttrainingofsuchmodelsProperRegularizationiscritica...
ImplicitRegularizationinNonconvexStatisticalEstimation:GradientDescentConvergesLinearlyforPhaseRetrievalandMatrixCompletionCongMa1KaizhengWang1YuejieChi2YuxinChen3Abstract1.IntroductionRecentyearsh...
DropoutTraining,Data-dependentRegularization,andGeneralizationBoundsWenlongMou1YuchenZhou2JunGao3LiweiWang34AbstractexperimentalstudieshaveshowntheRegularizationeffectincurredbydropout,asthegapbetw...
Sub-sampledCubicRegularizationforNon-convexOptimizationJonasMoritzKohler1AurelienLucchi1Abstractlearningwhennisverylarge.Itsconvergenceproper-tiesarewellunderstoodforconvexfunctions,whichariseWecon...