FastMaximizationofNon-Submodular,MonotonicFunctionsontheIntegerLatticeAlanKuhnle1J.DavidSmith1VictoriaG.Crawford1MyT.Thai1AbstractKempe,2011;Horel&Singer,2016).Inthiswork,weTheoptimizationofsubmodu...
BoundsontheApproximationPowerofFeedforwardNeuralNetworksMohammadMehrabi1AslanTchamkerten2MansoorI.Yousefi2AbstractDeterminingthecapacityofaneuralnetworkswithapiece-wiselinearactivationfunctiontypic...
Beyond1/2-ApproximationforSubmodularMaximizationonMassiveDataStreamsAshkanNorouzi-Fard1JakubTarnawski1SlobodanMitrovic´1AmirZandieh1AidasadatMousavifar1OlaSvensson1Abstractstreams,sensordata,socia...
AdversarialAttackonGraphStructuredDataHanjunDai1HuiLi2TianTian3XinHuang2LinWang2JunZhu3LeSong12Abstractyieldgoodpredictions,butcouldalsoputthemodelinarisk.Acriminalcouldtrytodisguisehimselfbyconnec...
ADistributionalPerspectiveonReinforcementLearningMarcG.Bellemare1WillDabney1Re´miMunos1Abstractmentlearning.Specifically,themainobjectofourstudyistherandomreturnZwhoseexpectationisthevalueQ.ThisIn...
TensorBalancingonStatisticalManifoldMahitoSugiyama12HiroyukiNakahara3KojiTsuda456AbstractGiventensorAStatisticalmanifold(duallyatRiemannianmanifold)Wesolvetensorbalancing,rescalinganNthor-dernonneg...
Semi-SupervisedClassificationBasedonClassificationfromPositiveandUnlabeledDataTomoyaSakai12MarthinusChristoffelduPlessisGangNiu1MasashiSugiyama21Abstractularizerfortrainingaclassifierandbiasesthecl...
Re-revisitingLearningonHypergraphs:ConfidenceIntervalandSubgradientMethodChenziZhang1ShuguangHu1ZhihaoGavinTang1T-H.HubertChan12AbstractInthispaper,weconsidersemi-supervisedlearningonanedge-weighte...
ontheIterationComplexityofSupportRecoveryviaHardThresholdingPursuitJieShen1PingLi1Abstract2010;Blumensath&Davies,2009;Bouchotetal.,2016).RecoveringthesupportofasparsesignalfromComparedtoparameteres...
onTheProjectionOperatortoAThree-viewCardinalityConstrainedSetHaichuanYang1ShupengGui1ChuyangKe1DanielStefankovic1RyoheiFujimaki2JiLiu1Abstractwherewistheoptimizationvariable,gisanindexsubsetThecard...
ontheSamplingProblemforKernelQuadratureFranc¸ois-XavierBriol12ChrisJ.Oates34JonCockayne1WilsonYeChen5MarkGirolami24AbstractCarlo(MC)methodscanbeusedtoestimatethenumericalvalueofEqn.1.Aclassicalres...
onorthogonalityandlearningrecurrentnetworkswithlongtermdependenciesEugeneVorontsov12ChihebTrabelsi12SamuelKadoury13ChrisPal12Abstractstabilizethenormofpropagatingsignalsdirectlybypenal-izingdiffere...
onRelaxingDeterminisminArithmeticCircuitsArthurChoi1AdnanDarwiche1AbstractAnexaminationoftheliteraturesurroundingarithmeticcir-cuitsandtheirvariantssuggeststhattheimplicationsofThepastdecadehasseen...
onContext-DependentClusteringofBanditsClaudioGentile1ShuaiLi2PurushottamKar3AlexandrosKaratzoglou4GiovanniZappella5EvansEtrue1Abstractmovierecommendationsystem,wherethecatalogisrela-tivelystaticand...
onMixedMembershipsandSymmetricNonnegativeMatrixFactorizationsXueyuMao1PurnamritaSarkar2DeepayanChakrabarti3Abstractinstance,individualsinasocialnetworkmayhavemul-tipleinterests,andhencearebestdescr...
onKernelizedMulti-armedBanditsSayakRayChowdhury1AdityaGopalan1Abstractanceexplorationandexploitation,asavailableknowledgemustbetransferredefficientlyfromafinitesetofobser-Weconsiderthestochasticban...
onCalibrationofModernNeuralNetworksChuanGuo1GeoffPleiss1YuSun1KilianQ.Weinberger1AbstractLeNet(1998)ResNet(2016)1.0CIFAR-100CIFAR-100Confidencecalibration–theproblemofpredict-ingprobabilityestimat...
onApproximationGuaranteesforGreedyLowRankOptimizationRajivKhanna1EthanR.Elenberg1AlexandrosG.Dimakis1JoydeepGhosh1SahandNegahban2AbstractUnfortunately,theaboveoptimizationcanbecomputation-allytaxin...
DictionaryLearningBasedonSparseDistributionTomographyPedramPad1FarnoodSalehi2ElisaCelis2PatrickThiran2MichaelUnser1Abstracttheentriesofxarestatisticallyindependent,whichresultsinaclassofmethodsrefe...