Dual-PathDistillation:AUnifiedFrameworktoImproveBlack-BoxAttacksYonggangZhang1YaLi2TongliangLiu3XinmeiTian1Abstract(Athalyeetal.,2018),evaluatemodelrobustness(Carlini&Wagner,2017;Moosavi-Dezfooliet...
CanIncreasingInputDimensionalityImproveDeepReinforcementLearning?KeiOta1TomoakiOiki1DeveshK.Jha2ToshisadaMariyama1DanielNikovski2Abstract1.IntroductionDeepreinforcementlearning(RL)algorithmsDeeprei...
UsingPre-TrainingCanImproveModelRobustnessandUncertaintyDanHendrycks1KiminLee2MantasMazeika3AbstractSurprisingly,pre-trainingprovidesnoperformancebene-fitonvarioustasksandarchitecturesovertrainingf...
RadialGAN:LeveragingmultipledatasetstoImprovetarget-specificpredictivemodelsusingGenerativeAdversarialNetworksJinsungYoon1JamesJordon2MihaelavanderSchaar123Abstractinhospitalsperformwelloneachhospi...
LeveragingUnionofSubspaceStructuretoImproveConstrainedClusteringJohnLipor1LauraBalzano1Abstractvectorsandestimatetheunderlyingsubspaces,achievingex-cellentperformanceonavarietyofrealdatasets.Howeve...