NormalizedLossFunctionsforDeepLearningwithNoisyLabelsXingjunMa1HanxunHuang1YisenWang2SimoneRomanoSarahErfani1JamesBailey1Abstract2018;Hanetal.,2018b);and4)robustlossfunctionsthatareinherentlytolera...
Non-StationaryDelayedBanditswithIntermediateObservationsClaireVernade1Andra´sGyo¨rgy1TimothyA.Mann1AbstractDelayedfeedbackinonlinelearninghavebeenaddressedbothinthefullinformationsetting(see,e.g....
Non-autoregressiveMachineTranslationwithDisentangledContextTransformerJungoKasai1JamesCross2MarjanGhazvininejad2JiataoGu2Abstractconditionalindependenceandpreventsthemodelfromprop-erlycapturingtheh...
NeuralTopicModelingwithContinualLifelongLearningPankajGupta1YatinChaudhary12ThomasRunkler1HinrichSchu¨tze2Abstract(productline)(operatingKnowledgeBaseKnowledgeipad,apple,system)ofTopicsAccumulatio...
NeuralNetworkControlPolicyVerificationwithPersistentAdversarialPerturbationsYuh-ShyangWang1Tsui-WeiWeng2LucaDaniel2Abstractneuralnetworksaresurprisinglyvulnerabletoadversarialexamplesandattacks(Hua...
NeuralContextualBanditswithUCB-basedExplorationDongruoZhou1LihongLi2QuanquanGu1Abstracttheexpectedrewardateachroundislinearinthefeaturevector.Whilesuccessfulinboththeoryandpractice(LiWestudythestoc...
Near-lineartimeGaussianprocessoptimizationwithadaptivebatchingandresparsificationDanieleCalandriello1LuigiCarratino2AlessandroLazaric3MichalValko4LorenzoRosasco256Abstractsequentiallearningproblem,...
Multi-TaskLearningwithUserPreferences:GradientDescentwithControlledAscentinParetoOptimizationDebabrataMahapatra1VaibhavRajan2Abstract2019a),naturallanguageprocessing(Liuetal.,2019b)andbioinformatic...
MultinomialLogitBanditwithLowSwitchingCostKefanDong1YingkaiLi2QinZhang3YuanZhou4Abstractthatno-purchaseisthemostfrequentchoice,whichisverynaturalinretailing.W.l.o.g.,weassumev0=1,andvi1Westudymul...
Multi-fidelityBayesianOptimizationwithMax-valueEntropySearchanditsParallelizationShionTakeno12HitoshiFukuoka3YuhkiTsukada34ToshiyukiKoyama3MotokiShiga245IchiroTakeuchi12MasayukiKarasuyama146Abstrac...
Model-BasedReinforcementLearningwithValue-TargetedRegressionAlexAyoub1ZeyuJia2CsabaSzepesva´ri13MengdiWang43LinF.Yang5Abstractmains,suchasgames,roboticsandscience,haswitnessedphenomenalempiricalad...
ModelFusionwithKullback–LeiblerDivergenceSebastianClaici12MikhailYurochkin23SoumyaGhosh23JustinSolomon12Abstract(a)BayesianneuralnetworktrainedonbiaseddataWeproposeamethodtofuseposteriordistribu-t...
Minimax-OptimalOff-PolicyEvaluationwithLinearFunctionApproximationYaqiDuan1ZeyuJia2MengdiWang34Abstractvalue)tobeearnedbyanewpolicybasedonloggedhistory.Thispaperstudiesthestatisticaltheoryofoff-Int...
MinimallyDistortedAdversarialExampleswithaFastAdaptiveBoundaryAttackFrancescoCroce1MatthiasHein1Abstracttherobustnessisevaluatedapproximatingthesolutionoftheminimaladversarialperturbationproblemthr...
Meta-LearningwithSharedAmortizedVariationalInferenceEkaterinaIakovleva1JakobVerbeek2KarteekAlahari1Abstract2016),nearestclass-meanapproaches(Dvorniketal.,2019;Mensinketal.,2012;Renetal.,2018;Snelle...
Meta-learningwithStochasticLinearBanditsLeonardoCella12AlessandroLazaric3MassimilianoPontil2AbstractsolidatedMABsettinginwhicheacharmisassociatedwithavectoroffeaturesandthearmpayofffunctionismod-We...
MetaFun:Meta-LearningwithIterativeFunctionalUpdatesJinXu1Jean-FrancoisTon1HyunjikKim2AdamR.Kosiorek13YeeWhyeTeh1AbstractTheobjectiveofmeta-learningisthentolearntheencoderandthedecodersuchthatthepro...
Margin-awareAdversarialDomainAdaptationwithOptimalTransportSofienDhouib1IevgenRedko2CaroleLartizien1Abstract2010),tonameafew.Whilemanuallabelingmaybecon-sideredasatractablesolution,suchanapproachis...
LogarithmicRegretforAdversarialOnlineControlDylanJ.Foster1MaxSimchowitz2Abstractbyawell-behavedstochasticprocessordrivenbyaworst-caseprocesstowhichthelearnermustremainrobustinWeintroduceanewalgorit...
LogisticRegressionforMassiveDatawithRareEventsHaiYingWang1Abstractapplications.However,severalimportantquestionsremainunansweredthatareessentialforvaliddataanalysisandThispaperstudiesbinarylogistic...