PointwiseBinaryClassificationwithPairwiseConfidenceComparisonsLeiFeng1SenlinShu2NanLu34BoHan54MiaoXu64GangNiu4BoAn7MasashiSugiyama43Abstractweaklysupervisedlearningproblems(Zhou,2018)havebeenextens...
Off-PolicyConfidenceSequencesNikosKarampatziakis1PaulMineiro2AadityaRamdas3Abstractthattheprobabilitythattheyeverexcludethetruevalueisboundedbyaprespecifiedquantity.Inotherwords,theyWedevelopconfid...
Near-OptimalConfidenceSequencesforBoundedRandomVariablesArunKumarKuchibhotla1QinqingZheng2Abstractsequentialhypothesistestingproblemssuchastestingpos-itivenessofthemean(Zhaoetal.,2016),testingequal...
ImprovedConfidenceBoundsfortheLinearLogisticModelandApplicationstoBanditsKwang-SungJun1LalitJain2BlakeMason3HoussamNassif4Abstractafeaturevectorforeacharm.Acommonassumptionisthattherewardisanoisyli...
HighConfidenceGeneralizationforReinforcementLearningJamesE.Kostas1YashChandak1ScottM.Jordan1GeorgiosTheocharous2PhilipS.Thomas1AbstractformanceonMDPsdrawnfromthedistribution,includingMDPsnotinthetr...
ConfidenceScoresMakeInstance-dependentLabel-noiseLearningPossibleAntoninBerthon12BoHan31GangNiu1TongliangLiu4MasashiSugiyama15Abstractorizationeffects(Zhangetal.,2017).Thus,learningwithnoisylabelsh...
AsymptoticNormalityandConfidenceIntervalsforPredictionRiskoftheMin-normLeastSquaresEstimatorZengLi1ChuanlongXie2QinwenWang3Abstractclassicalbias-variancetrade-off,aU-shapecurve,andfur-thershowsthat...
Uncertaintyquantificationfornonconvextensorcompletion:Confidenceintervals,heteroscedasticityandoptimalityChangxiaoCai1H.VincentPoor1YuxinChen1Abstractinformationabouttheunknowntensorplaysapivotalro...
TighteningExplorationinUpperConfidenceReinforcementLearningHippolyteBourel1Odalric-AmbrymMaillard1MohammadSadeghTalebi2Abstract1.IntroductionTheupperconfidencereinforcementlearningInthispaper,wecon...
ConfidenceSetsandHypothesisTestinginaLikelihood-FreeInferenceSettingNiccolo`Dalmasso1RafaelIzbicki2AnnB.Lee1Abstract1.IntroductionParameterestimation,statisticaltestsandconfi-Parameterestimation,st...
ReinforcingAdversarialRobustnessusingModelConfidenceInducedbyAdversarialTrainingXiWu1UyeongJang2JiefengChen2LingjiaoChen2SomeshJha2Abstractbeendevotedtohardeningneuralnetworksagainstadver-sarialper...
Re-revisitingLearningonHypergraphs:ConfidenceIntervalandSubgradientMethodChenziZhang1ShuguangHu1ZhihaoGavinTang1T-H.HubertChan12AbstractInthispaper,weconsidersemi-supervisedlearningonanedge-weighte...