AsynchronousStochasticQuasi-NewtonMCMCforNon-ConvexOptimizationUmutS¸ims¸ekli1C¸ag˘atayYıldız2ThanhHuyNguyen1Gae¨lRichard1A.TaylanCemgil3AbstractwhereUisatwicecontinuouslydifferentiablefunct...
AsynchronousDecentralizedParallelStochasticGradientDescentXiangruLian1WeiZhang2CeZhang3JiLiu41AbstractFigure1.Centralizednetworkanddecentralizednetwork.MostcommonlyuseddistributedmachinelearningS-P...
StochasticVarianceReductionMethodsforPolicyEvaluationSimonS.Du1JianshuChen2LihongLi2LinXiao2DengyongZhou2Abstractimportantinformationfortheagenttooptimizeitspolicy.Forexample,policy-iterationalgori...
StochasticGradientMonomialGammaSamplerYizheZhang1ChangyouChen1ZheGan1RicardoHenao1LawrenceCarin1Abstractics,leadingtoHamiltonianMonteCarlo(HMC)(Duaneetal.,1987).Aidedbygradientinformation,HMCisable...
StochasticModifiedEquationsandAdaptiveStochasticGradientAlgorithmsQianxiaoLi1ChengTai23WeinanE234Abstractwherek≥0and{γk}arei.i.duniformvariatestakingval-uesin{1,2,···,n}.Thestep-sizeηisthelea...
StochasticGradientMCMCMethodsforHiddenMarkovModelsYi-AnMa1NicholasJ.Foti1EmilyB.Fox1Abstractdistributioninthepresenceofsuchnoise.Significanthead-wayhasbeenmadeindevelopingsuchcorrectSG-MCMCStochast...
StochasticDCAfortheLarge-sumofNon-convexFunctionsProblemanditsApplicationtoGroupVariableSelectioninClassificationHoaiAnLeThi1HoaiMinhLe1DuyNhatPhan1BachTran1AbstractNowadays,thegrowthoftechnologies...
StochasticGenerativeHashingBoDai1RuiqiGuo2SanjivKumar2NiaoHe3LeSong1AbstractshowninthesupplementarymaterialD.Brute-forcelinearsearchisexpensiveforlargedatasets.ToalleviatethetimeLearning-basedbinar...
StochasticConvexOptimization:FasterLocalGrowthImpliesFasterGlobalConvergenceYiXu1QihangLin2TianbaoYang1Abstract1.IntroductionInthispaper,anewtheoryisdevelopedforfirst-Inthispaper,weareinterestedins...
StochasticAdaptiveQuasi-NewtonMethodsforMinimizingExpectedValuesChaoxuZhou∗1WenboGao∗1DonaldGoldfarb1AbstractinfeasibletoanalyticallycomputeEf(x,ξ).ThiscanberesolvedbyreplacingtheexpectationEf(x...
StochasticBouncyParticleSamplerAriPakman1DarGilboa1DavidCarlson2LiamPaninski1Abstractinclude(Ahnetal.,2012;Dingetal.,2014).WeintroduceaStochasticversionofthenon-Despitethesuccessoftheaboveapproach,...
RobustGuaranteesofStochasticGreedyAlgorithmsAvinatanHassidim1YaronSinger2Abstractf(H).Manyfundamentalmeasuressuchasentropy,di-versity,andclusteringcanbemodeledassubmodularfunc-Inthispaperweanalyzet...
OnlineLearningtoRankinStochasticClickModelsMasrourZoghi1TomasTunys2MohammadGhavamzadeh3BranislavKveton4CsabaSzepesvari5ZhengWen4Abstractetal.,2006;Zoghietal.,2016)thatthefeedbackofusers,thatisclick...
Natasha:FasterNon-ConvexStochasticOptimizationviaStronglyNon-ConvexParameterZeyuanAllen-Zhu1Abstractrandom∇fi(x).Givenanon-convexfunctionf(x)thatisanav-•Theso-calledproximaltermψ(x)addsmoregener...
LearningStableStochasticNonlinearDynamicalSystemsJonasUmlauft1SandraHirche1Abstractrobotictaskisgiventhroughhumandemonstrations,e.g.,objectgrasping.ThegoalistorepresentthemotionwithaAdata-drivenide...
ImprovingStochasticPolicyGradientsinContinuousControlwithDeepReinforcementLearningusingtheBetaDistributionPo-WeiChou1DanielMaturana1SebastianScherer1AbstractFigure1.Anexampleofcontinuouscontrolwith...
High-DimensionalVariance-ReducedStochasticGradientExpectation-MaximizationAlgorithmRongdaZhu1LingxiaoWang2ChengxiangZhai3QuanquanGu2Abstractstudies(Balakrishnanetal.,2014;Wangetal.,2014;Yi&Caramani...
DeepLatentDirichletAllocationwithTopic-Layer-AdaptiveStochasticGradientRiemannianMCMCYulaiCong1BoChen1HongweiLiu1MingyuanZhou2Abstractsuchasdeepbeliefnetwork(DBN)(Hintonetal.,2006)anddeepBoltzmannm...
ConditionalAcceleratedLazyStochasticGradientDescentGuanghuiLan1SebastianPokutta1YiZhou1DanielZink1AbstractComparedtomostotherfirst-ordermethods,suchase.g.,gradientdescentalgorithmsandacceleratedgra...
Communication-efficientAlgorithmsforDistributedStochasticPrincipalComponentAnalysisDanGarber1OhadShamir2NathanSrebro3Abstractchinelearning.FordatathatconsistsofNvectorsinWestudythefundamentalproble...