PAPRIKA:PrivateOnlineFalseDiscoveryRateControlWanrongZhang1GautamKamath2RachelCummings3Abstractoflarge-scaledatasetsandeaseofdataanalysis,whilebene-ficialtosociety,hascreatedaseverecrisisofreproduc...
OnlineSubmodularResourceAllocationwithApplicationstoRebalancingSharedMobilitySystemsPierGiuseppeSessa1IlijaBogunovic1AndreasKrause1MaryamKamgarpour1Abstracttion(i.e.,thequalitymeasureofagivenalloca...
OnlineUnrelatedMachineLoadBalancingwithPredictionsRevisitedShiLi1JiayiXian1Abstractlearnedeasily.Aspredictionsareoftenerror-prone,ide-allytheperformanceofthealgorithmshoulddeteriorateWestudytheonli...
OnlineSelectionProblemsagainstConstrainedAdversaryZhihaoJiang1PinyanLu2ZhihaoGavinTang2YuhaoZhang3AbstractlearnedadvicetoOnlinealgorithmdesigns.Inparticular,thealgorithmisgivensomeextrainformationa...
OnlinePolicyGradientforModelFre√eLearningofLinearQuadraticRegulatorswithTRegretAsafCassel1TomerKoren12AbstractModel-basedmethods,whichperformplanningbasedonasystemidentificationprocedurethatestima...
OnlineOptimizationinGamesviaControlTheory:ConnectingRegret,PassivityandPoincare´RecurrenceYunKuenCheung1GeorgiosPiliouras2AbstracttheoryandOnlineoptimization.Wepresentanovelcontrol-theoreticunders...
OnlineLimitedMemoryNeural-LinearBanditswithLikelihoodMatchingOfirNabati1TomZahavy12ShieMannor13Abstractplorationduringtherepresentationlearningphaseisstillanopenproblem.The-greedypolicy(Langford&Zh...
OnlineLearningforLoadBalancingofUnknownMonotoneResourceAllocationGamesAbstractIlaiBistritz1NicholasBambos12018;Boursier&Perchet,2019;Mehrabianetal.,2020;ConsiderNplayersthateachusesamixtureofNayyar...
OnlineLearningwithOptimismandDelayGenevieveFlaspohler12FrancescoOrabona3JudahCohen4SoukaynaMouatadid5MirunaOprescu6PauloOrenstein7LesterMackey6AbstractialOnlinelearningalgorithmsproviderobustperfor...
OnlineLearninginUnknownMarkovGamesYiTian1YuanhaoWang2TianchengYu1SuvritSra1Abstractcontrolboth/allplayersandaimtominimizethenumberofepisodesrequiredtofindagoodpolicy;and(2)theOnlineWestudyOnlinelea...
OnlineGraphDictionaryLearningCe´dricVincent-Cuaz1TitouanVayer2Re´miFlamary3MarcoCorneli14NicolasCourty5Abstractchallenging,astheirnatureisbyessencenon-vectorial,andrequiresdedicatedmodellingofthe...
OnlineA-OptimalDesignandActiveLinearRegressionXavierFontaine1PierrePerrault2MichalValko3VianneyPerchet45Abstractwaytoconstructanestimatoristomakeexperimentsandtogatherdataontheestimand.Inthepolling...
RegularizedOnlineAllocationProblems:FairnessandBeyondSantiagoBalseiro12HaihaoLu32VahabMirrokni2Abstractapublishertypicallysignscontractswithmanyadvertisersagreeingtodeliverafixednumberofimpressions...
NeighborhoodContrastiveLearningAppliedtoOnlinePatientMonitoringHugoYe`che1GideonDresdner1FrancescoLocatello2MatthiasHu¨ser1GunnarRa¨tsch1Abstractpliedthismethodologytomedicaltime-seriesdata(Cheng...
Multi-ReceiverOnlineBayesianPersuasionMatteoCastiglioni1AlbertoMarchesi1AndreaCelli1NicolaGatti1Abstractacommonpriordistributionandobservedbythesenderonly.Then,thesenderdecideshowmuchofher/hispriva...
MessagePassingAdaptiveResonanceTheoryforOnlineActiveSemi-supervisedLearningTaehyeongKim12InjuneHwang1HyundoLee2HyunseoKim2Won-SeokChoi2JosephJ.Lim13Byoung-TakZhang2Abstractuseofdeeplearninginreal-w...
MemoryEfficientOnlineMetaLearningDurmusAlpEmreAcar1RuizhaoZhu1VenkateshSaligrama1AbstractWhilehumanlearningisevidentlytheinspirationfortradi-tionalmeta-learningapproaches,therearesignificantdif-Wep...
LearningOnlineAlgorithmswithDistributionalAdviceIliasDiakonikolas1VasilisKontonis1ChristosTzamos1AliVakilian2NikosZarifis1Abstractversary(Koutsoupias&Papadimitriou,2000).Amorere-centlineofworkstudi...
JointOnlineLearningandDecision-makingviaDualMirrorDescentAlfonsoLobos1PaulGrigas1ZhengWen2Abstractensuringthatwedonotincurtoomanycoststooearly,(ii)ensuringthatenoughcostsareincurredtomeetthelowerWe...
FairnessandBiasinOnlineSelectionJose´Correa1Andre´sCristi1PaulDu¨tting2AshkanNorouzi-Fard2Abstractalsoitnaturallyencompassesmanyreal-worlddecisionmak-ingprocesseswherebiasedevaluationsshouldbeav...