PAGE:ASimpleandOptimalProbabilisticGradientEstimatorforNonconvexOptimizationZhizeLi1HongyanBao1XiangliangZhang1PeterRichta´rik1Abstract(Jain&Kar,2017).Drivenbytheappliedsuccessofdeepneuralnetworks...
OptimalEstimatorforUnlabeledLinearRegressionHangZhang,PingLiCognitiveComputingLabBaiduResearch10900NE8thST.Bellevue,WA98004,USA{zhanghanghitomi,pingli98}@gmail.comAbstractthematrixofmeasurements.Wh...
BoXHED:BoostedeXactHazardEstimatorwithDynamiccovariatesXiaochenWang1ArashPakbin2BobakJ.Mortazavi2HongyuZhao1DonaldK.K.Lee3Abstractdying,butalsowhenthatmighthappen,inordertoprovidetimelycriticalcare...
AdaptiveEstimatorSelectionforOff-PolicyEvaluationYiSu1PavithraSrinath2AkshayKrishnamurthy2Abstracthighqualityestimationashasbeendemonstratedinrecentempiricalstudies(Voloshinetal.,2019).However,data...
ARSM:Augment-REINFORCE-Swap-MergeEstimatorforGradientBackpropagationThroughCategoricalVariablesMingzhangYin1YuguangYue1MingyuanZhou2Abstractzk∈{1,2,...,C}asaunivariateC-waycategoricalvari-able,and...
DiCE:TheInfinitelyDifferentiableMonteCarloEstimatorJakobFoerster1GregoryFarquhar1MaruanAl-Shedivat2TimRockta¨schel1EricP.Xing2ShimonWhiteson1AbstractEstimatingthefirstordergradientsiscomputational...