StochasticMulti-armedBanditswithUnrestrictedDelayDistributionsTalLancewicki1ShaharSegal1TomerKoren12YishayMansour12Abstracttion,likeintheclassicstochasticMABproblem.However,WestudythestochasticMult...
ResourceAllocationinMulti-armedBanditExploration:OvercomingSublinearScalingwithAdaptiveParallelismBrijenThananjeyan1KirthevasanKandasamy1IonStoica1MichaelI.Jordan1KenGoldberg1JosephE.Gonzalez1Abstr...
OptimalStreamingAlgorithmsforMulti-armedBanditsTianyuanJin1KekeHuang1JingTang2XiaokuiXiao1Abstractson,1933),onlineadvertisement(Bertsimas&Mersereau,2007),andcrowdsourcing(Zhouetal.,2014).Ittypicall...
AlmostOptimalAnytimeAlgorithmforBatchedMulti-armedBanditsTianyuanJin1JingTang2PanXu3KekeHuang1XiaokuiXiao1QuanquanGu3Abstractittoguidethenextaction.However,thisisimpracticalformanyrealapplicationsw...
OnconditionalversusmarginalbiasinMulti-armedbanditsJaehyeokShin1AlessandroRinaldo1AadityaRamdas12AbstractThedataarecollectedsequentiallyinstages,duringwhichtheanalystdrawsasamplefromoneamongfinitel...
DecentralizedExplorationinMulti-armedBanditsRaphaëlFéraud1RédaAlami1RomainLaroche2Abstractviceisconnectingtotheapplication,theapplicationpresentsanoptiontotheuserofthedevice.TheaimistomaximizeWe...
ContextualMulti-armedBanditAlgorithmforSemiparametricRewardModelGi-SooKim1MyungheeChoPaik1Abstract(Langfordetal.,2008),newsarticleplacementalgorithms(Lietal.,2010),revenuemanagement(Ferreiraetal.,2...
AdaptiveMonteCarloMultipleTestingviaMulti-armedBanditsMartinJ.Zhang1JamesZou123DavidTse1Abstractwhosegoalistoidentifyassociationsbetweenthegeno-types(singlenucleotidepolymorphismsorSNPs)andtheMonte...
MinimaxConcavePenalizedMulti-armedBanditModelwithHigh-DimensionalConvariatesXueWang1MikeMingchengWei2TaoYao1Abstractexample,doctors(i.e.,decision-makers)canpersonalizetreatmentsforpatients(i.e.,use...
OnKernelizedMulti-armedBanditsSayakRayChowdhury1AdityaGopalan1Abstractanceexplorationandexploitation,asavailableknowledgemustbetransferredefficientlyfromafinitesetofobser-Weconsiderthestochasticban...