MetaCURE:MetaReinforcementLearningwithEmpowerment-DrivenExplorationJinZhang1JianhaoWang1HaoHu1TongChen1YingfengChen2ChangjieFan2ChongjieZhang1Abstractwithsparserewardsremainschallenging,astask-rele...
Meta-learningHyperparameterPerformancePredictionwithNeuralProcessesYingWei1PeilinZhao2JunzhouHuang2AbstractFreefromthelimitationsofexhaustivesearch(Bergstra&Bengio,2012)beingcomputationallyexpensiv...
MatrixCompletionwithModel-freeWeightingJiayiWang1RaymondK.W.Wong1XiaojunMao2KwunChuenGaryChan3Abstractguptaetal.,2021)andquantumstatetomography(Wang,2013;Caietal.,2016).Matrixcompletionhasbeenpop-I...
MARINA:FasterNon-ConvexDistributedLearningwithCompressionEduardGorbunov123KonstantinBurlachenko3ZhizeLi3PeterRichta´rik3Abstractmentofnewefficientmethodsfornon-convexoptimizationproblems(Danilovae...
LogarithmicRegretforReinforcementLearningwithLinearFunctionApproximationJiafanHe1DongruoZhou1QuanquanGu1AbstractAcommonapproachtocopewithhigh-dimensionalstateandactionspacesistoutilizefunctionappro...
LocalCorrelationClusteringwithAsymmetricClassificationErrorsJafarJafarov1SanchitKalhan2KonstantinMakarychev2YuryMakarychev3Abstractteringproblemhasfounduseinavarietyofapplications,suchasco-referenc...
LipschitzNormalizationforSelf-AttentionLayerswithApplicationtoGraphNeuralNetworksGeorgeDasoulas12KevinScaman1AladinVirmaux1Abstractclassification(Velickovicetal.,2018;Lietal.,2016)andcomputervision...
LinkPredictionwithPersistentHomology:AnInteractiveViewZuoyuYan1TengfeiMa2LiangcaiGao1ZhiTang1ChaoChen3Abstractdistributionsoflinks,e.g.,nodeswithsimilarconnectivityfeaturestendtobeconnected.Betterp...
LearningOptimalAuctionswithCorrelatedValuationsfromSamplesChunxueYang1XiaohuiBei1Abstractsufficientandnecessarytoguaranteenear-optimalexpectedrevenue.Consequently,oneactivelineofresearchappliesInsi...
LearningOnlineAlgorithmswithDistributionalAdviceIliasDiakonikolas1VasilisKontonis1ChristosTzamos1AliVakilian2NikosZarifis1Abstractversary(Koutsoupias&Papadimitriou,2000).Amorere-centlineofworkstudi...
LearninginNonzero-SumStochasticGameswithPotentialsDavidMguni1YutongWu2YaliDu3YaodongYang13ZiyiWang2MinneLi3YingWen4JoelJennings1JunWang3Abstractautonomousvehiclesseekingtoarriveattheirindividualdes...
LearningfromNoisyLabelswithNoChangetotheTrainingProcessMingyuanZhang1JaneLee2ShivaniAgarwal1Abstract1.IntroductionTherehasbeenmuchinterestinrecentyearsInmanyapplicationsofmachinelearning,onereceive...
LearningfromNestedDatawithOrnsteinAuto-EncodersYoungwonChoi12SungdongLee1Joong-HoWon1Abstracttureforeachdigit.Inmulticenterelectronichealthrecords,patientsarenestedwithinahospital.Forsuchnesteddata...
ModelPerformanceScalingwithMultipleDataSourcesTatsunoriHashimoto1Abstractprovidespowerfultoolstoimproveandevaluatemodelbe-havior,butalsoposesanadditionalchallenge:whatistheReal-worldmachinelearning...
InstabilitiesofOfflineRLwithPre-TrainedNeuralRepresentationRuosongWang1YifanWu1RuslanSalakhutdinov1ShamM.Kakade23Abstract2018;Wangetal.,2018;Yuetal.,2019);itisseeingmuchrecentinterestduetothelargea...
InferringserialcorrelationwithdynamicbackgroundsSongWei1YaoXie1DobromirRahnev2Abstracttheseinfluencestakeaspecificparametricform.Whilesome(e.g.,learningorfatigue)arelikelytobemonotonic,Sequentialda...
InferenceforNetworkRegressionModelswithCommunityStructureMengjiePan1TylerH.McCormick2BaileyK.Fosdick3AbstractInthiswork,wefocusonacasewherecontinuousrelationsbetweenpairsofactorsaremodeledasalinear...
IncentivizingCompliancewithAlgorithmicInstrumentsDanielNgo1LoganStapleton1VasilisSyrgkanis2ZhiweiStevenWu3Abstractcausaleffectsrelyonrandomizedexperiments,whichran-domlyassigneachindividualinapopul...
IncentivizedBanditLearningwithSelf-ReinforcingUserPreferencesTianchenZhou1JiaLiu1ChaoshengDong2JingyuanDeng2Abstractaccumulatesmorepositivefeedbacks.Forexample,onamovierentalwebsite,currentcustomer...
ImprovingMolecularGraphNeuralNetworkExplainabilitywithOrthonormalizationandInducedSparsityRyanHenderson1Djork-Arne´Clevert1FlorianeMontanari1AbstractHowever,theopaquenatureofartificialneuralnetwor...