VarianceReducedTrainingwithStratifiedSamplingforForecastingModelsYuchengLu12YoungsukPark2LifanChen2YuyangWang2ChristopherDeSa1DeanFoster34Abstract2004)arethefolkloremethodsformodelingthedynamicsofa...
PracticalandPrivate(Deep)LearningWithoutSamplingorShufflingPeterKairouz1BrendanMcMahan1ShuangSong1OmThakkar1AbhradeepThakurta1ZhengXu1Abstractinthecontextofdistributedsettingslikefederatedlearn-ing...
ParallelandFlexibleSamplingfromAutoregressiveModelsviaLangevinDynamicsVivekJayaram1JohnThickstun1Abstractlimittheusefulnessofautoregressivemodelsinpracticalsettings.First,ancestralSamplinghastimeco...
OptimalThompsonSamplingstrategiesforsupport-awareCVaRbanditsDorianBaudry1RomainGautron23EmilieKaufmann1Odalric-AmbrymMaillard1AbstractValueatRisk(CVaR)aswellasmoregenericcoherentspec-tralriskmeasur...
OopsITookAGradient:ScalableSamplingforDiscreteDistributionsWillGrathwohl12KevinSwersky2MiladHashemi2DavidDuvenaud12ChrisJ.Maddison1AbstractFigure1.Ourapproachvisualized.Oftendiscretedistributionsar...
MOTS:MinimaxOptimalThompsonSamplingTianyuanJin1PanXu2JiemingShi3XiaokuiXiao1QuanquanGu2Abstractplayingthebestarmandplayingthearmaccordingtothestrategy,whichisalsocalledtheregretofabanditstrategy.Th...
Meta-ThompsonSamplingBranislavKveton1MikhailKonobeev2ManzilZaheer1Chih-weiHsu1MartinMladenov1CraigBoutilier1CsabaSzepesva´ri32Abstractwhichthepriordistributionovermeanarmrewards,avitalpartofTS,isu...
Instance-OptimalCompressedSensingviaPosteriorSamplingAjilJalal1SushrutKarmalkar2AlexandrosG.Dimakis1EricPrice2AbstractforameasurementmatrixA∈Rm×nandnoisevectorWecharacterizethemeasurementcomplexi...
GeometricConvergenceofEllipticalSliceSamplingViacheslavNatarovskii1DanielRudolf1Bjo¨rnSprungk2AbstractonRdtakestheformForBayesianlearning,givenlikelihoodfunction(x)andGaussianprior,theellipticalsl...
DisentanglingLabelingandSamplingBiasforLearninginLarge-outputSpacesAnkitSinghRawat1AdityaKrishnaMenon1WittawatJitkrittum1SadeepJayasumana1FelixX.Yu1SashankJ.Reddi1SanjivKumar1Abstractcloselyascheme...
ClusteredSampling:Low-VarianceandImprovedRepresentativityforClientsSelectioninFederatedLearningYannFraboni12RichardVidal2LaetitiaKameni2MarcoLorenzi1Abstractsametime.Theseconsiderationsledtosignifi...
AutoSampling:SearchforEffectiveDataSamplingSchedulesMingSun1HaoxuanDou1BaopuLi2LeiCui1JunjieYan1WanliOuyang3AbstractHowever,existinglearning-basedSamplingmethodsstillrelyonhumanpriorsasproxiestoopt...
AdaptiveSamplingforBestPolicyIdentificationinMarkovDecisionProcessesAymenAlMarjani1AlexandreProutiere2Abstractcertainty.Thispaper,asmostrelatedworkinthisfield,fo-cusesonsystemsandcontrolobjectivest...
VarianceReductioninStochasticParticle-OptimizationSamplingJianyiZhang1YangZhao2RuiyiZhang1LawrenceCarin1ChangyouChen2AbstractThesemethodshavefacilitatedimportantreal-worldappli-cationsandachievedim...
ThompsonSamplingviaLocalUncertaintyZhendongWang1MingyuanZhou1Abstractbecomeacommonpractice.Sincethemodeltraininganddatacollectionusuallyhappenatthesametime,themodelThompsonSamplingisanefficientalgo...
ThompsonSamplingAlgorithmsforMean-VarianceBanditsQiuyuZhu1VincentY.F.Tan123AbstractTheprimaryconcernofthisbodyofliteratureistofindalearningalgorithmwhichcanmaximizetheexpectedcu-Themulti-armedbandi...
ReducingSamplingErrorinBatchTemporalDifferenceLearningBrahmaS.Pavse1IshanDurugkar1JosiahP.Hanna23PeterStone14Abstractpolicy(Puterman&Shin,1978;Bertsekas,1987;Konda&Tsitsiklis,2000).Thesealgorithmsr...
PredictiveSamplingwithForecastingAutoregressiveModelsAukeWiggers1EmielHoogeboom23AbstractFigure1.OverviewofpredictiveSampling.Asequence-so-farofARMsamplesx0,...,xi−1isextendedwithforecastsAutoregr...
OnThompsonSamplingwithLangevinAlgorithmsEricMazumdar1AldoPacchiano1Yi-AnMa23PeterL.Bartlett14MichaelI.Jordan14Abstractexploitationtradeoffs(Aueretal.,2002;LattimoreandSzepesva´ri,2020),whereinanal...
NegativeSamplinginsemi-supervisedlearningJohnChen1VatsalShah2AnastasiosKyrillidis1AbstractThisformoflearningissemi-supervisedlearning(Chapelle&Scholkopf,2006)(SSL).Unlikesupervisedlearning,theWeint...