SUNRISE:ASimpleUnifiedFrameworkforEnsembleLearninginDeepReinforcementLearningKiminLee1MichaelLaskin1AravindSrinivas1PieterAbbeel1Abstractefficientmodel-freeRLalgorithmsthroughimprovementsinoff-poli...
EnsembleBootstrappingforQ-LearningOrenPeer1ChenTessler1NadavMerlis1RonMeir1Abstractfocusesonlearningthevalue-function.Thevaluerepresentstheexpected,discounted,reward-to-gothattheagentwillQ-learning...
TheTreeEnsembleLayer:DifferentiabilitymeetsConditionalComputationHusseinHazimeh1NataliaPonomareva2PetrosMol2ZhenyuTan3RahulMazumder1Abstract(Hastieetal.,2009;Chen&Guestrin,2016).Anothernatu-ralprop...
Onp-normRobustnessofEnsembleDecisionStumpsandTreesYihanWang1HuanZhang2HonggeChen3DuaneBoning3Cho-JuiHsieh2Abstractetal.,2017;Ilyasetal.,2018;Brendeletal.,2018;Chengetal.,2019a;2020),variousalgorith...
OnaProjectiveEnsembleApproachtoTwoSampleTestforEqualityofDistributionsZhimeiLi1YaowuZhang1Abstracttestingfortheequalityoftwodistributions,i.e.,Inthiswork,weproposearobusttestforthemul-H0:F=GversusH...
Mix-n-Match:EnsembleandCompositionalMethodsforUncertaintyCalibrationinDeepLearningJizeZhang1BhavyaKailkhura1T.Yong-JinHan1AbstractFigure1.(Top):(left)TemperatureScaling(TS)(Guoetal.,2017)isdata-ef...
Acceleratingthediffusion-basedEnsemblesamplingbynon-reversibledynamicsFutoshiFutami12IsseiSato12MasashiSugiyama21AbstractMurphy,2012).Formanypracticalmodels,wecannotob-tainananalyticalexpressionoft...
Multivariate-InformationAdversarialEnsembleforScalableJointDistributionMatchingZiliangChen1ZhanfuYang2XiaoxiWang1XiaodanLiang1XiaopengYan1GuanbinLi1LiangLin1Abstract(∀j∈[m],j=i)tosatisfytheequati...
ImprovingAdversarialRobustnessviaPromotingEnsembleDiversityTianyuPang1KunXu1ChaoDu1NingChen1JunZhu1Abstract2017b;Athalyeetal.,2018),whereimageswithhumanimperceptibleperturbations(i.e.,adversarialex...
BatchBayesianOptimizationviaMulti-objectiveAcquisitionEnsembleforAutomatedAnalogCircuitDesignWenlongLyu1FanYang1ChanghaoYan1DianZhou12XuanZeng1AbstractofICmanufacturetechnologyforecastedbyMoore’sl...