UncertaintyWeightedActor-CriticforOfflineReinforcementLearningYueWu12ShuangfeiZhai1NitishSrivastava1JoshuaSusskind1JianZhang1RuslanSalakhutdinov2HanlinGoh1Abstractleveragingpriorexperience(Langeeta...
UncertaintyPrinciplesofEncodingGANsRuiliFeng1ZhouchenLin‡23JiapengZhu4DeliZhao5JinrenZhou5Zheng-JunZha†1Abstract1.IntroductionThecompellingsynthesisresultsofGenerativeGenerativeAdversarialNetwork...
ReinforcementLearningUnderMoralUncertaintyAdrienEcoffet12JoelLehman12AbstractWhilesuchaccomplishmentsaresignificant,progresshasbeenlessstraight-forwardinapplyingRLtounstructuredAnambitiousgoalforma...
EvaluatingRobustnessofPredictiveUncertaintyEstimation:AreDirichlet-basedModelsReliable?Anna-KathrinKopetzki1BertrandCharpentier1DanielZügner1SandhyaGiri1StephanGünnemann1AbstractFigure1.Visualiza...
ABitMoreBayesian:Domain-InvariantLearningwithUncertaintyZehaoXiao1JiayiShen1XiantongZhen12LingShao2CeesG.M.Snoek1AbstractLietal.,2018a)orspecificarchitectures(Lietal.,2017;D’Innocente&Caputo,2018)...
UnlabelledDataImprovesBayesianUncertaintyCalibrationunderCovariateShiftAlexJ.Chan1AhmedM.Alaa2ZhaozhiQian1MihaelavanderSchaar123Abstracttityoflabelledi.i.ddataareavailable(Krizhevskyetal.,2012).How...
Uncertaintyquantificationfornonconvextensorcompletion:Confidenceintervals,heteroscedasticityandoptimalityChangxiaoCai1H.VincentPoor1YuxinChen1Abstractinformationabouttheunknowntensorplaysapivotalro...
ThompsonSamplingviaLocalUncertaintyZhendongWang1MingyuanZhou1Abstractbecomeacommonpractice.Sincethemodeltraininganddatacollectionusuallyhappenatthesametime,themodelThompsonsamplingisanefficientalgo...
UncertaintyEstimationUsingaSingleDeepDeterministicNeuralNetworkJoostvanAmersfoort1LewisSmith1YeeWhyeTeh2YarinGal1Abstract(a)DeepEnsembles(b)Ourmodel-DUQWeproposeamethodfortrainingadeterminis-Figure...
SDE-Net:EquippingDeepNeuralNetworkswithUncertaintyEstimatesLingkaiKong1JimengSun2ChaoZhang1Abstractbilitiesforclassification(Guoetal.,2017).Moreover,theycanmakeerroneousyetwildlyconfidentprediction...
NADS:NeuralArchitectureDistributionSearchforUncertaintyAwarenessRandyArdywibowo1ShahinBoluki1XinyuGong2ZhangyangWang2XiaoningQian1Abstractlousdatacancomeinsettingssuchasinautonomousdriv-ing(Kendall...
Mix-n-Match:EnsembleandCompositionalMethodsforUncertaintyCalibrationinDeepLearningJizeZhang1BhavyaKailkhura1T.Yong-JinHan1AbstractFigure1.(Top):(left)TemperatureScaling(TS)(Guoetal.,2017)isdata-ef...
FrequentistUncertaintyinRecurrentNeuralNetworksviaBlockwiseInfluenceFunctionsAhmedM.Alaa1MihaelavanderSchaar12Abstract(a)Blockwiseresampling(b)SequentialconfidenceintervalsRNNPredictionsRecurrentne...
EstimatingModelUncertaintyofNeuralNetworksinSparseInformationFormJongseokLee1MatthiasHumt1JianxiangFeng12RudolphTriebel12Abstractferencewhatlinearmapsareforalgebra.Forexample,oncetheposteriordistri...
DiscriminativeJackknife:QuantifyingUncertaintyinDeepLearningviaHigher-OrderInfluenceFunctionsAhmedM.Alaa1MihaelavanderSchaar12Abstractsupport(Alaa&vanderSchaar,2017),autonomousve-hicles,andfinancia...
OnDiscriminativeLearningofPredictionUncertaintyVojtechFranc1DanielPrusa1Abstractplug-inruleobtainedafterreplacingtheposteriorprobabili-tiesbytheirestimates.Aqualityoftheplug-inruleheavilyInclassifi...
HiringUnderUncertaintyManishRaghavan1ManishPurohit2SreenivasGollapudi2AbstracttheproblemandthekeyquestiontackledishowtofindagoodsetofcandidateswhenthepooloffuturecandidatesInthispaperweintroducethe...
ExploitingStructureofUncertaintyforEfficientMatroidSemi-BanditsPierrePerrault12VianneyPerchet23MichalValko14Abstracttimeandspacecomplexity)oftheircombinatorialgeneral-ization,inwhichtheagentselects...
DirectUncertaintyPredictionforMedicalSecondOpinionsMaithraRaghu12KatyBlumer2RorySayres2ZiadObermeyer3RobertKleinberg1SendhilMullainathan4JonKleinberg1Abstractlabellersnowbeinghighlytrainedmedicalex...
TheUncertaintyBellmanEquationandExplorationBrendanO’Donoghue1IanOsband1RemiMunos1VolodymyrMnih1Abstracttionsthatmaximizerewardsgivenitscurrentknowledge?Weconsidertheexploration/exploitationprob-Se...