T-SCI:ATwo-StageConformalInferenceAlgorithmwithGuaranteedCoverageforCox-MLPJiayeTeng1ZerenTan1YangYuan12AbstractFigure1.Biasincensoring.Ignoringordeletingcensoreddata(lightgreenpoints)causesbiascom...
SGA:ARobustAlgorithmforPartialRecoveryofTree-StructuredGraphicalModelswithNoisySamplesAnshooTandon1AldricJ.Y.Han2VincentY.F.Tan12Abstractnetworks(Lauritzen,1996)andcomputervision(Besag,1986).Forade...
ProbabilisticSequentialShrinking:ABestArmIdentificationAlgorithmforStochasticBanditswithCorruptionsZixinZhong1WangChiCheung23VincentY.F.Tan134Abstractofoptions,sayL=10,todesignanear-optimalvaccine....
PredictthenInterpolate:ASimpleAlgorithmtoLearnStableClassifiersYujiaBao1ShiyuChang2ReginaBarzilay3Abstractthelabelmayvary.Insteadofhandcraftingenvironmentsbasedonexplicit,task-dependentbiases,these...
PIDAcceleratedValueIterationAlgorithmAmir-massoudFarahmand12MohammadGhavamzadeh3Abstractapproximationofthevalueoraction-valuefunctions,i.e.,Vk+1←TπVkorQk+1←T∗Qk.FordiscountedMDPs,Theconvergence...
OptimalregretAlgorithmforPseudo-1dBanditConvexOptimizationAadirupaSaha1NagarajanNatarajan2PraneethNetrapalli23PrateekJain23Abstracttheproblemhasa"pseudo-1d"structureinthelossfunc-tionsft(w)=t(gt(w;...
Finite-SampleAnalysisofOff-PolicyNaturalActor-CriticAlgorithmSajadKhodadadian∗1ZaiweiChen∗2SivaThejaMaguluri1AbstractAnACAlgorithmcanbethoughtasageneralizedpolicyiter-ation(Puterman,1995),andcons...
BayesianAlgorithmExecution:EstimatingComputablePropertiesofBlack-boxFunctionsUsingMutualInformationWillieNeiswanger1KeAlexanderWang1StefanoErmon1AbstracttackledbyBayesianoptimizationmethods(Shahria...
AnAlgorithmforStochasticandAdversarialBanditswithSwitchingCostsChloe´Rouyer1YevgenySeldin1Nicolo`Cesa-Bianchi2Abstractanarmdifferentfromtheoneplayedinthepreviousround.Suchswitchingcostmayoccurinth...
AlmostOptimalAnytimeAlgorithmforBatchedMulti-ArmedBanditsTianyuanJin1JingTang2PanXu3KekeHuang1XiaokuiXiao1QuanquanGu3Abstractittoguidethenextaction.However,thisisimpracticalformanyrealapplicationsw...
AZeroth-OrderBlockCoordinateDescentAlgorithmforHuge-ScaleBlack-BoxOptimizationHanQinCai1YuchenLou2DanielMckenzie1WotaoYin3Abstractandonlinemarketing(Flaxmanetal.,2005).Lately,algo-rithmsforzeroth-o...
AScalableDeterministicGlobalOptimizationAlgorithmforClusteringProblemsKaixunHua1MingfeiShi1YankaiCao1AbstractThedifferentdefinitionsofcostfunctioninducedifferenttypesofclusteringAlgorithms.Inthispa...
APolicyGradientAlgorithmforLearningtoLearninMultiagentReinforcementLearningDong-KiKim12MiaoLiu23MatthewRiemer23ChuangchuangSun12MarwaAbdulhai12GolnazHabibi12SebastianLopez-Cot12GeraldTesauro23Jonat...
Tuning-freePlug-and-PlayProximalAlgorithmforInverseImagingProblemsKaixuanWei1AngelicaAviles-Rivero2JingweiLiang3YingFu1Carola-BibianeSchnlieb3HuaHuang1Abstracty∈RMisfundamentalincomputationalimagi...
TheFASTAlgorithmforSubmodularMaximizationAdamBreuer1EricBalkanski1YaronSinger1Abstract1.IntroductionInthispaperwedescribeanewparallelal-InthispaperwedescribeafastparallelAlgorithmforsub-gorithmcall...
SpectralFrank-WolfeAlgorithm:StrictComplementarityandLinearConvergenceLijunDing1YingjieFei1QiantongXu2ChengrunYang3AbstractThesetSniscalledthespectrahedron,whichisnonemptyandcompact.HenceProblem(1)...
SemismoothNewtonAlgorithmforEfficientProjectionsonto1,∞-normBallDejunChu1ChangshuiZhang1ShiliangSun2QingTao3AbstracttionproblemThestructuredsparsity-inducing1,∞-norm,asminL(W)+λR(W)(1)ageneraliz...
Self-ConcordantAnalysisofFrank-WolfeAlgorithmsPavelDvurechensky12PetrOstroukhov3KamilSafin3ShimritShtern4MathiasStaudigl5Abstractcondition(Bauschkeetal.,2017;Luetal.,2018),thecorner-stoneassumption...
RefinedBoundsforAlgorithmConfiguration:TheKnife-edgeofDualClassApproximabilityMaria-FlorinaBalcan1TuomasSandholm1234EllenVitercik1AbstractHutteretal.,2009;Kadiogluetal.,2010;Sandholm,2013):givenatr...