HybridStochastic-DeterministicMinibatchProximalGradient:Less-Than-Single-PassOptimizationwithNearlyOptimalGeneralizationPanZhou1Xiao-TongYuan2Abstract1.IntroductionStochasticvariance-reducedgradien...
GraphOpt:LearningOptimizationModelsofGraphFormationRakshitTrivedi1JiachenYang1HongyuanZha12AbstractFigure1.⌦issetoflatentobjectivefunctions{Fi},anyofwhichcouldleadtoobservedgraphGwhenoptimised.Our...
GlobalConcavityandOptimizationinaClassofDynamicDiscreteChoiceModelsYidingFeng1EkaterinaKhmelnitskaya2DenisNekipelov2Abstract1.IntroductionDiscretechoicemodelswithunobservedhetero-Dynamicdiscretecho...
Finite-TimeConvergenceinContinuous-TimeOptimizationOrlandoRomero1MouhacineBenosman2AbstractsmoothBanachspaceX(typicallyaEuclideanorotherwisefinite-dimensionalrealvectorspaceinnonlinearprogram-Inthi...
ExplicitGradientLearningforBlack-BoxOptimizationEladSarafian1MorSinay1YoramLouzoun1NoaAgmon1SaritKraus1Abstractreal-worldphysicsornumericalsimulation.Black-BoxOp-timization(BBO)algorithms(Audet&Har...
ExpertLearningthroughGeneralizedInverseMultiobjectiveOptimization:Models,Insights,andAlgorithmsChaoshengDong1BoZeng1Abstractthehumandecisionmaker’sdecisionswhilecannotdirectlyaccessherunderlyingde...
DynamicKnapsackOptimizationTowardsEfficientMulti-ChannelSequentialAdvertisingXiaotianHao1ZhaoqingPeng2YiMa1GuanWang3JunqiJin2JianyeHao1ShanChen2RongquanBai2MingzhouXie2MiaoXu2ZhenzheZheng4ChuanYu2H...
DistributedOnlineOptimizationoveraHeterogeneousNetworkNimaEshraghi1BenLiang1Abstract2013),networking(Shietal.,2018),andmachinelearning(Shalev-Shwartz,2012).IndistributedonlineOptimizationoveracom-p...
DINO:DistributedNewton-TypeOptimizationMethodRixonCrane1FredRoosta12Abstractwhereiisalossfunctioncorrespondingtoxiandparam-eterizedbyw.Forexample,suchsettingsarepopularinWepresentanovelcommunicatio...
Communication-EfficientDistributedPCAbyRiemannianOptimizationLong-KaiHuang1SinnoJialinPan1Abstractfollowingempiricalriskminimization(ERM)problemInthispaper,westudytheleadingeigenvec-w∗=argminFˆ(w...
ChoiceSetOptimizationUnderDiscreteChoiceModelsofGroupDecisionsKiranTomlinson1AustinR.Benson1Abstractatownmightpreferdifferentgovernmentpolicies.Thewaythatpeoplemakechoicesorexhibitpref-Muchofthecom...
BidirectionalModel-basedPolicyOptimizationHangLai1JianShen1WeinanZhang1YongYu1Abstractbehindtheirmodel-freecounterpartsduetomodelerror,whichisespeciallysevereformulti-steprolloutbecauseofModel-base...
ASimplerApproachtoAcceleratedStochasticOptimization:IterativeAveragingMeetsOptimismPooriaJoulani1AnantRaj2Andra´sGyo¨rgy1CsabaSzepesva´ri13Abstractblynon-smooth)convexfunction.Whenφ=0,andgivena...
ADistributionalViewonMulti-ObjectivePolicyOptimizationAbbasAbdolmaleki1SandyH.Huang1LeonardHasenclever1MichaelNeunert1H.FrancisSong1MartinaZambelli1MuriloF.Martins1NicolasHeess1RaiaHadsell1MartinRi...
AChance-ConstrainedGenerativeFrameworkforSequenceOptimizationXianggenLiu12QiangLiu3SenSong1JianPeng2Abstractlong-rangeconstraints(e.g.,valencyconditionsinmoleculargeneration),pushingthediscretesear...
Trimmingthe1Regularizer:StatisticalAnalysis,Optimization,andApplicationstoDeepLearningJihunYun1PengZheng2EunhoYang13Aure´lieC.Lozano4AleksandrAravkin2Abstractconstraintsontheestimationparameters.S...
StochasticOptimizationforDCFunctionsandNon-smoothNon-convexRegularizerswithNon-asymptoticConvergenceYiXu1QiQi1QihangLin2RongJin3TianbaoYang1Abstractwhereg(·)andh(·)arereal-valuedlower-semicontinu...
SEVER:ARobustMeta-AlgorithmforStochasticOptimization1IliasDiakonikolas1GautamKamath2DanielM.Kane3JerryLi4JacobSteinhardt5AlistairStewart6Abstractbergetal.,2002;Lietal.,2008)requiringpainstakingman-...
Predictor-CorrectorPolicyOptimizationChing-AnCheng12XinyanYan1NathanRatliff2ByronBoots12AbstractModel-basedRLmethodsimprovesampleefficiencybyleveraginganaccuratemodelthatcancheaplysimulatein-Wepres...
OptimisticPolicyOptimizationviaMultipleImportanceSamplingMatteoPapini1AlbertoMariaMetelli1LorenzoLupo1MarcelloRestelli1Abstractpeholtetal.,2018).Thisiswellmotivated,asinteractingwithsomeenvironment...