VarianceReductionviaPrimal-DualAcceleratedDualAveragingforNonsmoothConvexFinite-SumsChaobingSong1StephenJ.Wright1JelenaDiakonikolas1Abstractvectorswithntypicallylarge;gi:R!R,i=1,2,...,n,bepossiblyn...
VarianceReducedTrainingwithStratifiedSamplingforForecastingModelsYuchengLu12YoungsukPark2LifanChen2YuyangWang2ChristopherDeSa1DeanFoster34Abstract2004)arethefolkloremethodsformodelingthedynamicsofa...
BeyondVarianceReduction:UnderstandingtheTrueImpactofBaselinesonPolicyOptimizationWesleyChung1ValentinThomas2MarlosC.Machado345NicolasLeRoux612Abstract&Cesa-Bianchi,2012).Whiletheformermeasureisofte...
AsynchronousDecentralizedOptimizationWithImplicitStochasticVarianceReductionKentaNiwa12GuoqiangZhang3W.BastiaanKleijn4NoboruHarada12HiroshiSawada1AkinoriFujino1AbstractOurgoalistofacilitateMLmodelt...
VarianceReductioninStochasticParticle-OptimizationSamplingJianyiZhang1YangZhao2RuiyiZhang1LawrenceCarin1ChangyouChen2AbstractThesemethodshavefacilitatedimportantreal-worldappli-cationsandachievedim...
VarianceReductionandQuasi-NewtonforParticle-BasedVariationalInferenceMichaelH.Zhu1ChangLiu2JunZhu3AbstractexactestimatorofEp[f(X)]asM→∞.Variationalin-ference(VI)methods(Wainwrightetal.,2008;Bleie...
VarianceReducedCoordinateDescentwithAcceleration:NewMethodWithaSurprisingApplicationtoFinite-SumProblemsFilipHanzely1DmitryKovalev1PeterRichta´rik1Abstractcontrast,ifψisnotseparable,thecorrespond...
MetaVarianceTransfer:LearningtoAugmentfromTheOthersSeong-JinPark1SeungjuHan1JiwonBaek1InsooKim1JuhwanSong1HaeBeomLee2Jae-JoonHan1SungJuHwang2Abstractcepts.However,collectingacompletedatasetwithallp...
LowBiasLowVarianceGradientEstimatesforHierarchicalBooleanStochasticNetworksAdeelPervez1TacoCohen2EfstratiosGavves1Abstractgradients,onecansamplegradientsfromsomedistribu-tion.Thesampleestimatescanb...
History-GradientAidedBatchSizeAdaptationforVarianceReducedAlgorithmsKaiyiJi1ZheWang1BowenWeng1YiZhou2WeiZhang3YingbinLiang1AbstracthavebeenproposedtoreducetheVarianceofSGD.SuchVariancereductiontech...
DoubleTroubleinDoubleDescent:BiasandVariance(s)intheLazyRegimeSte´phaned’Ascoli1MariaRefinetti1GiulioBiroli1FlorentKrzakala1Abstractrecognition(Hintonetal.,2012),andautomatictransla-tion(Sutskeve...
AlmostTune-FreeVarianceReductionBingcongLi1LingdaWang2GeorgiosB.Giannakis1AbstractThestandardapproachtosolve(1)isgradientdescent(GD)(Nesterov,2004),whichupdatesthedecisionvariableviaTheVarianceredu...
OnlineVarianceReductionwithMixturesZalánBorsos1SebastianCuri1KfirY.Levy1AndreasKrause1AbstractWhymixtures?Themajorityofexistingworksonadap-tivesamplingdistributionsareunabletoexploitsimilaritiesAd...
NonconvexVarianceReducedOptimizationwithArbitrarySamplingSamuelHorváth1PeterRichtárik123Abstractwherexcorrespondstotheparametersdefiningamodel,fi(x)isthelossofthemodelxassociatedwithdatapointWepr...
ImprovedZeroth-OrderVarianceReducedAlgorithmsandAnalysisforNonconvexOptimizationKaiyiJi1ZheWang1YiZhou2YingbinLiang1Abstract1.IntroductionTwotypesofzeroth-orderstochasticalgorithmsZeroth-orderoptim...
ControlRegularizationforReducedVarianceReinforcementLearningRichardCheng1AbhinavVerma2Ga´borOrosz3SwaratChaudhuri2YisongYue1JoelW.Burdick1Abstractrithmsfocusonmaximizingthelong-termrewardthroughtr...
AdaptiveAntitheticSamplingforVarianceReductionHongyuRen1ShengjiaZhao1StefanoErmon1AbstractbytheVarianceoftheestimator.Thus,withlowervari-ancewecouldachievebetterestimationerrorguarantees.Variancere...
OntheTheoryofVarianceReductionforStochasticGradientMonteCarloNiladriS.Chatterji1NicolasFlammarion2Yi-AnMa2PeterL.Bartlett23MichaelI.Jordan23AbstractsothatefficientapproachestoMonteCarlosamplingarer...
FastVarianceReductionMethodwithStochasticBatchSizeXuanqingLiu1Cho-JuiHsieh12AbstractHereweassumeeachfi(w)isaµ-stronglyconvex,L-smoothfunction,theregularizationtermg(w)isconvexInthispaperwestudyafa...
DissipativityTheoryforAcceleratingStochasticVarianceReduction:AUnifiedAnalysisofSVRGandKatyushaUsingSemidefiniteProgramsBinHu1StephenWright1LaurentLessard1AbstractMonro,1951;Bottou&LeCun,2003).Rece...