OnlineControlwithAdversarialDisturbancesNamanAgarwal1BrianBullins21EladHazan21ShamM.Kakade341KaranSingh21AbstractChallenge1.Perhapsthemostimportantchallengeweaddressisindealingwitharbitrarydisturba...
OnlineAlgorithmsforRent-or-BuywithExpertAdviceSreenivasGollapudi1DebmalyaPanigrahi2AbstractOnlinealgorithms(Medina&Vassilvitskii,2017;Lykouris&Vassilvitskii,2018;Kumaretal.,2018;Mitzenmacher,Westud...
OnlineAdaptivePrincipalComponentAnalysisandItsextensionsJianjunYuan1AndrewLamperski1AbstractThestandardperformancemetricforOnlinelearningmea-suresthedifferencebetweenthedecisionmaker’scumula-Wepro...
Matrix-FreePreconditioninginOnlineLearningAshokCutkosky1TamasSarlos1AbstractOurgoalistoobtainadaptiveregretboundssothatRT(w˚)maybemuchsmallerineasierproblemswhilestillmaintain-WeprovideanOnlinecon...
IncrementalRandomizedSketchingforOnlineKernelLearningXiaoZhang1ShizhongLiao1Abstractupdatingtimesignificantly(Wangetal.,2012).Tosolvetheproblem,budgetedOnlinekernellearninghasbeenproposedRandomized...
CautiousRegretMinimization:OnlineOptimizationwithLong-TermBudgetConstraintsNikolaosLiakopoulos12ApostolosDestounis1GeorgiosPaschos1ThrasyvoulosSpyropoulos2PanayotisMertikopoulos3Abstractafunctionof...
BeyondBackprop:OnlineAlternatingMinimizationwithAuxiliaryVariablesAnnaChoromanska1BenjaminCowen1SadhanaKumaravel2RonnyLuss2MattiaRigotti2IrinaRish2BrianKingsbury2PaoloDiAchille2ViatcheslavGurev2Rav...
AdversarialOnlineLearningwithnoiseAlonResler1YishayMansour12Abstract&Lugosi,2006;Bubeck&Cesa-Bianchi,2012)).Wepresentandstudymodelsofadversarialon-Bothmodelsassumethattheobservedfeedbackisexact,lin...
AdaptiveScale-InvariantOnlineAlgorithmsforLearningLinearModelsMichałKempka1WojciechKotłowski1ManfredK.Warmuth2AbstractShwartz,2011;Hazan,2015).WeconsiderOnlinelearningwithlinearmodels,Oneofthemos...
SAFFRON:anAdaptiveAlgorithmforOnlineControloftheFalseDiscoveryRateAadityaRamdas1TijanaZrnic2MartinJ.Wainwright1MichaelI.Jordan1Abstract1.IntroductionIntheOnlinefalsediscoveryrate(FDR)problem,Itisno...
Projection-FreeOnlineOptimizationwithStochasticGradient:FromConvexitytoSubmodularityLinChen12ChristopherHarshaw13HamedHassani4AminKarbasi12Abstract1.IntroductionOnlineoptimizationhasbeenasuccessful...
OnlineConvolutionalSparseCodingwithSample-DependentDictionaryYaqingWang1QuanmingYao12JamesT.Kwok1LionelM.Ni3Abstract(Kavukcuogluetal.,2010;Zeileretal.,2010;Bristowetal.,2013;Heideetal.,2015;Sˇorel...
OnlineLearningwithAbstentionCorinnaCortes1GiuliaDeSalvo1ClaudioGentile12MehryarMohri31ScottYang⇤4Abstractorabstainandrequestfurtherlaboratorytests,whichcanrepresentbothatimedelayandafinancialcost....
OnlineLinearQuadraticControlAlonCohen12AvinatanHassidim13TomerKoren4NevenaLazic4YishayMansour15KunalTalwar4Abstractinthepresenceoftime-varyingenergycosts,duetoenergyauctionsorunexpecteddemandfluctu...
TheSampleComplexityofOnlineOne-ClassCollaborativeFilteringReinhardHeckel1KannanRamchandran1Abstractuserlikes,basedonratingsthatthisuserandalargenum-berofotherusershaveprovidedinthepast.Tothisend,We...
ThePriceofDifferentialPrivacyforOnlineLearningNamanAgarwal1KaranSingh1Abstractthefullinformationandpartialinformation(bandit)set-tings.ThisresultimprovestheknownbestregretboundsWedesigndifferential...
Second-OrderKernelOnlineConvexOptimizationwithAdaptiveSketchingDanieleCalandriello1AlessandroLazaric1MichalValko1Abstractminimizetheregret,definedasthedifferencebetweenthelossesofthepredictionsobta...
Projection-freeDistributedOnlineLearninginNetworksWenpengZhang1PeilinZhao2WenwuZhu1StevenC.H.Hoi3TongZhang4Abstractants(Hazan&Kale,2012)(Hazan,2016)(Hazan&Luo,2016),fastervariantsoverspecialtypesof...
OnlinePartialLeastSquareOptimization:DroppingConvexityforBetterEfficiencyandScalabilityZhehuiChen1LinF.Yang2ChrisJ.Li3TuoZhao1Abstract2011).Althoughthesedataareusuallyunlabeled,thereex-Multiviewrep...
OnlineLearningtoRankinStochasticClickModelsMasrourZoghi1TomasTunys2MohammadGhavamzadeh3BranislavKveton4CsabaSzepesvari5ZhengWen4Abstractetal.,2006;Zoghietal.,2016)thatthefeedbackofusers,thatisclick...
