RewardIdentificationinInverseReinforcementLearningKunoKim1KirankumarShiragur1ShivamGarg1StefanoErmon1AbstractMDPstobuildcomputationalmodels(Niv,2009)ofreal-world,rationaldecisionmakerssuchasinvesto...
QuantileBanditsforBestArmsIdentificationMengyanZhang12ChengSoonOng21AbstractMean0.5-QuantileMean0.8-QuantileWeconsideravariantofthebestarmidentifica-A3.503.50C1.452.33tiontaskinstochasticmulti-arme...
ProbabilisticSequentialShrinking:ABestArmIdentificationAlgorithmforStochasticBanditswithCorruptionsZixinZhong1WangChiCheung23VincentY.F.Tan134Abstractofoptions,sayL=10,todesignanear-optimalvaccine....
LenientRegretandGood-ActionIdentificationinGaussianProcessBanditsXuCai1SelwynGomes1JonathanScarlett12Abstractgorithmscanoftenbeappliedinaunifiedmannerinthesetwosettings.Inthispaper,westudytheproble...
FeatureClusteringforSupportIdentificationinExtremeRegionsHamidJalalzai12Re´miLeluc1Abstractseveralrecentstudies:inanomalydetection(Roberts,1999;Cliftonetal.,2011;Goixetal.,2016;Thomasetal.,2017),U...
DiffusionSourceIdentificationonNetworkswithStatisticalConfidenceQuinlanDawkins1TianxiLi2HaifengXu1Abstractleakageproblems(Newmanetal.,2002;Halperin&Al-mogy,2002;Xu&Ren,2016).ThenegativeimpactsstemD...
BestArmIdentificationinGraphicalBilinearBanditsGeovaniRizk12AlbertThomas2IgorColin2RidaLaraki13YannChevaleyre1Abstractagent(e.g.,alltheconfigurationparametersoftheantennas),andreceivesanassociatedg...
BestModelIdentification:ARestedBanditFormulationLeonardoCella1MassimilianoPontil12ClaudioGentile3Abstract2002),thefeedbackgeneratedwhenpullinganarmismod-Weintroduceandanalyzeabestarmidentifica-eled...
AdaptiveSamplingforBestPolicyIdentificationinMarkovDecisionProcessesAymenAlMarjani1AlexandreProutiere2Abstractcertainty.Thispaper,asmostrelatedworkinthisfield,fo-cusesonsystemsandcontrolobjectivest...
ScalableIdentificationofPartiallyObservedSystemswithCertainty-EquivalentEMKunalMenda1JeandeBecdelie`vre1JayeshK.Gupta1IlanKroo1MykelJ.Kochenderfer1ZacharyManchester1Abstract···xtxt+1···System...
RobustOutlierArmIdentificationYinglunZhu1SumeetKatariya2RobertNowak1Abstractobservedvalues,thebanditalgorithmhastodecidewhichitemtosampleateverytimet,soastoidentifytheoptimalWestudytheproblemofRobu...
ProgressiveIdentificationofTrueLabelsforPartial-LabelLearningJiaqiLv1MiaoXu23LeiFeng4GangNiu2XinGeng1MasashiSugiyama25Abstractingproblemcalledpartial-labellearning(PLL)(Nguyen&Caruana,2008;Couretal...
ManifoldIdentificationforUltimatelyCommunication-EfficientDistributedOptimizationYu-ShengLi1Wei-LinChiang1Ching-peiLee2Abstractinrecentyears.Indistributedoptimization,theadditionalcomputingpowerand...
FullLawIdentificationinGraphicalModelsofMissingData:CompletenessResultsRaziehNabi1RohitBhattacharya1IlyaShpitser1Abstractetal.,2008;Marstonetal.,2010).MNARmechanismsareexpectedtooccurquiteofteninpr...
EfficientIdentificationinLinearStructuralCausalModelswithAuxiliaryCutsetsDanielKumor1CarlosCinelli2EliasBareinboim3Abstractysisinthefirstplace.Forinstance,ahealthscientistmaybeinterestedinknowingth...
BestArmIdentificationforCascadingBanditsintheFixedConfidenceSettingZixinZhong1WangChiCheung23VincentY.F.Tan134Abstractnextoneotherwise.Thisprocessstopswhensheclicksononeiteminthelistorifnoitemiscli...
PACIdentificationofManyGoodArmsinStochasticMulti-ArmedBanditsArghyaRoyChaudhuri1ShivaramKalyanakrishnan1Abstractdecision,whichproducesareal-valuedreward.Therewardisdrawni.i.d.fromadistributioncorre...
NearoptimalfinitetimeidentificationofarbitrarylineardynamicalsystemsTuhinSarkar1AlexanderRakhlin2Abstractpopularlinearfeedbackcontrolsystemfoundinavarietyofdevices,fromplanetarysoftlandingsystemsfo...
CausalIdentificationunderMarkovEquivalence:CompletenessResultsAminJaber1JijiZhang2EliasBareinboim1Abstractcities,andeventuallythescienceandtechnology-basedciv-ilizationweenjoytoday.Allbecauseweaske...
FeasibleArmIdentificationJulianKatz-Samuels1ClaytonScott1Abstractagoodarmaremulti-dimensionalinnature.Forexam-ple,incrowdsourcingitisimportanttodistinguishgoodWeintroducethefeasiblearmidentificatio...