OnlineLimitedMemoryNeural-LinearBanditswithLikelihoodMatchingOfirNabati1TomZahavy12ShieMannor13Abstractplorationduringtherepresentationlearningphaseisstillanopenproblem.The-greedypolicy(Langford&Zh...
TeachingwithLimitedInformationontheLearner’sBehaviourFerdinandoCicalese1SergioFilho2EduardoLaber2MarcoMolinaro2Abstractbeenontheinteractivesetting(Liuetal.,2017;Chenetal.,2018;Liuetal.,2018;Dasgup...
SelectiveDyna-stylePlanningUnderLimitedModelCapacityMuhammadZaheer1SamuelSokota1ErinJ.Talvitie2MarthaWhite1Abstractdecisions.Incontrast,inmodel-basedreinforcementlearn-ing,theagentpossessesamodelof...
LearningClassifiersforTargetDomainwithLimitedorNoLabelsPengkaiZhu1HanxiaoWang1VenkateshSaligrama1Abstractcollectionviewpointsasexemplifiedbydomainadaptation(DA)(Tzengetal.,2017).Incomputervisionapp...
Black-boxAdversarialAttackswithLimitedQueriesandInformationAndrewIlyas12LoganEngstrom12AnishAthalye12JessyLin12Abstractasubstitutenetworktoemulatetheoriginalnetworkandthenattacksthesubstitutewithfi...
DistributedMeanEstimationwithLimitedCommunicationAnandaTheerthaSuresh1FelixX.Yu1SanjivKumar1H.BrendanMcMahan2Abstractthemeansofallclustersineachupdatestep.Similarly,forPCA,ifdatasamplesaredistribut...