TowardsTightBoundsontheSampleComplexityofAverage-rewardMDPsYujiaJin1AaronSidford1Abstractmakingunderuncertaintyandreinforcementlearning(Puter-man,2014;Sutton&Barto,2018).Itisaprominenttheoret-Wepro...
TighterBoundsontheLogMarginalLikelihoodofGaussianProcessRegressionusingConjugateGradientsArtemArtemev12DavidR.Burt3MarkvanderWilk1Abstractdientbasedmethodsinordertoautomaticallyselectmodelhyperpara...
TighteningtheDependenceonHorizonintheSampleComplexityofQ-LearningGenLi1ChangxiaoCai2YuxinChen2YuantaoGu1YutingWei3YuejieChi4AbstractQ-learning(Borkar&Meyn,2000;Jaakkolaetal.,1994;Szepesva´ri,1998;...
TightBoundsontheSmallestEigenvalueoftheNeuralTangentKernelforDeepReLUNetworksQuynhNguyen1MarcoMondelli2GuidoMontufar13AbstractWeassumethatthenetworkhasasingleoutput,namelynL=1andWL∈RnL−1.Forconsi...
TheImpactofRecordLinkageonLearningfromFeaturePartitionedDataRichardNock1StephenHardy2WilkoHenecka2HamishIvey-Law3JakubNabaglo3GiorgioPatrini4GuillaumeSmith2BrianThorne5Abstract"whenisaglobaltrained...
SKIingonSimplices:KernelInterpolationonthePermutohedralLatticeforScalableGaussianProcessesSanyamKapoor1MarcFinzi1KeAlexanderWang2AndrewGordonWilson1AbstractFigure1.Comparisonofthenumberofgridpoints...
SigGPDE:ScalingSparseGaussianProcessesonSequentialDataMaudLemercier1CristopherSalvi2ThomasCass3EdwinV.Bonilla4TheodorosDamoulas1TerryLyons2AbstractvationsN,withnaïveapproacheshavingatimecomplexity...
SampleComplexityofRobustLinearClassificationonSeparatedDataRobiBhattacharjee1SomeshJha2KamalikaChaudhuri1Abstractthusaimstofindaclassifierthatmaximizesaccuracyonexamplesthataredistancerormorefromth...
Quasi-GlobalMomentum:AcceleratingDecentralizedDeepLearningonHeterogeneousDataTaoLin1SaiPraneethKarimireddy1SebastianU.Stich1MartinJaggi1Abstractiskeptlocally(nevertransmittedduringtraining).Decentr...
ProblemDependentViewonStructuredThresholdingBanditProblemsJamesCheshire1PierreMe´nard1AlexandraCarpentier1Abstractoferror-i.e.theprobabilitythatthelearnermis-classifiesatleastonearm-andconsiderthe...
ParalleltemperingonoptimizedpathsSaifuddinSyed1VittorioRomaniello1TrevorCampbell1AlexandreBouchard-Coˆte´1AbstractSupposeweseektoapproximateanexpectationwithrespecttoanintractabletargetdensityπ1...
ontheOptimalityofBatchPolicyOptimizationAlgorithmsChenjunXiao12YifanWu3TorLittlemore4BoDai2JinchengMei12LihongLi†5CsabaSzepesvari14DaleSchuurmans12Abstractafixeddatasetofpreviouslycollectedexperie...
onthePowerofLocalizedPerceptronforLabel-OptimalLearningofHalfspaceswithAdversarialNoiseJieShen1Abstractthelearnermustpayforeachlabelitwishestoberevealed.Thegoalistodesignqueryingstrategiestoavoidle...
ontheInherentRegularizationEffectsofNoiseInjectionDuringTrainingOussamaDhifallah1YueM.Lu1Abstract2008)underGaussianinputandperturbationvectors.OuranalysisparticularlyshowsthatGaussiannoiseinjection...
ontheImplicitBiasofInitializationShape:BeyondInfinitesimalMirrorDescentShaharAzulay1EdwardMoroshko2MorShpigelNacson2BlakeWoodworth3NathanSrebro3AmirGloberson1DanielSoudry2Abstractparameterizedmodel...
ontheGeneralizationPowerofOverfittedTwo-LayerNeuralTangentKernelModelsPeizhongJu1XiaojunLin1NessB.Shroff2AbstractMuthukumaretal.,2019;Juetal.,2020),aninteresting“double-descent”phenomenonhasbeeno...
ontheDifficultyofUnbiasedAlphaDivergenceMinimizationTomasGeffner1JustinDomke1AbstractExistingalpha-divergenceminimizationalgorithmscanbeclassifiedintotwobroadgroups:biasedmethods(Li&Severalapproxim...
ontheExplicitRoleofInitializationontheConvergenceandImplicitBiasofOverparametrizedLinearNetworksHanchengMin12SalmaTarmoun13Rene´Vidal14EnriqueMallada12Abstractwithoutexplicitregularization,enjoysg...
ontheExplicitRoleofInitializationontheConvergenceandImplicitBiasofOverparametrizedLinearNetworksHanchengMin12SalmaTarmoun13Rene´Vidal14EnriqueMallada12Abstractwithoutexplicitregularization,enjoysg...
ontheConvergenceofHamiltonianMonteCarlowithStochasticGradientsDifanZou1QuanquanGu1AbstracttionssuchasBayesianinference,reinforcementlearning,andcomputervision.Inthepastdecades,manyMCMCHamiltonianMo...