UncertaintyWeightedActor-CriticforOfflineReinforcementLearningYueWu12ShuangfeiZhai1NitishSrivastava1JoshuaSusskind1JianZhang1RuslanSalakhutdinov2HanlinGoh1Abstractleveragingpriorexperience(Langeeta...
Non-ExponentiallyWeightedAggregation:RegretBoundsforUnboundedLossFunctionsPierreAlquier1Abstractthesub-g√radientoftcanbeused.SuchstrategiesleadtoregretinTundertheadditionalassumptionthatthetareWet...
LeveragedWeightedLossforPartialLabelLearning1HongweiWen2JingyiCui1HanyuanHang2JiabinLiu3YisenWang1ZhouchenLin14Abstract2012),etc,andsubsequentlyattractsalotofattentiononmethodologystudies(Fengetal....
FederatedContinualLearningwithWeightedInter-clientTransferJaehongYoon1WonyongJeong12GiwoongLee1EunhoYang12SungJuHwang12AbstractFigure1.Concept.Acontinuallearneratahospitalwhichlearnsonsequenceofdis...
DiscriminativeComplementary-LabelLearningwithWeightedLossYiGao12Min-LingZhang23Abstracttion,includingbutnotlimitedto,semi-supervisedlearning(Chapelleetal.,2006;Oliveretal.,2018;Calderetal.,Compleme...
AdditiveErrorGuaranteesforWeightedLowRankApproximationAdityaBhaskara1AravindaKanchanaRuwanpathirana1MaheshakyaWijewardena1Abstractmatrixversionturnsouttobechallenging.Formally,theLow-rankapproximat...
HierarchicalImportanceWeightedAutoencodersChin-WeiHuang12KrisSankaran1EeshanDhekane1AlexandreLacoste2AaronCourville13Abstractboundswithprogressivelysmallergapusingmultiplei.i.d.samplesfromthevariat...
DistributedWeightedMatchingviaRandomizedComposableCoresetsSepehrAssadi1MohammadHosseinBateni2VahabMirrokni2AbstractBergeretal.,2008).Otherapplicationsareintradingmar-ketsandcomputationaladvertising...
CoresetsforOrderedWeightedClusteringVladimirBraverman1ShaofengH.-C.Jiang2RobertKrauthgamer2XuanWu1Abstractofthesedistances,usingpredefinedweightsv1≥···≥vn≥0.Theseclusteringproblemscaninterpol...
TheWeightedKendallandHigh-orderKernelsforPermutationsYunlongJiao1Jean-PhilippeVert2Abstractwherenisthenumberofitems;however,inspiteofcom-putationaltricks,thisleadstoalgorithmswithO(nn)com-Wepropose...
ImportanceWeightedTransferofSamplesinReinforcementLearningAndreaTirinzoni1AndreaSessa1MatteoPirotta2MarcelloRestelli1Abstracttions,parameters,policies,etc.)andinthecriteriausedtoestablishwhethersuc...
IMPALA:ScalableDistributedDeep-RLwithImportanceWeightedActor-LearnerArchitecturesLasseEspeholt1HubertSoyer1RemiMunos1KarenSimonyan1VolodymyrMnih1TomWard1YotamDoron1VladFiroiu1TimHarley1IainDunning1...