OptiDICE:OfflinePolicyOptimizationviaStationaryDistributionCorrectionEstimationJongminLee1WonseokJeon23Byung-JunLee4JoellePineau235Kee-EungKim16Abstractandthentodeploythemodelwithitsparameterfixedw...
LearningNodeRepresentationsUsingStationaryFlowPredictiononLargePaymentandCashTransactionNetworksCiwanCeylan12SallaFranze´n2FlorianT.Pokorny1AbstractannualGDP(UnitedNationsofficeondrugsandcrime,201...
TheComplexityofFindingStationaryPointswithStochasticGradientDescentYoelDrori1OhadShamir12Abstractisnottominimizef(x)overx,butrather∇f(x).ThisquestionoffindingStationarypointshasgainedmoreatten-Wes...
SpectralSubsamplingMCMCforStationaryTimeSeriesRobertSalomone1MatiasQuiroz2RobertKohn1MattiasVillani34Minh-NgocTran5Abstractaweightedcoresetofdatapointsfoundbyoptimization(Campbell&Broderick,2018;Ca...
GradientDICE:RethinkingGeneralizedOfflineEstimationofStationaryValuesShangtongZhang1BoLiu2ShimonWhiteson1Abstractevaluationismoreflexible.Wecanevaluateanewpolicywithexistingdatainareplaybuffer(Lin,...
ComplexityofFindingStationaryPointsofNonsmoothNonconvexFunctionsJingzhaoZhang1HongzhouLin1StefanieJegelka1SuvritSra1AliJadbabaie1AbstractTable1.Whentheproblemisnonconvexandnonsmooth,find-inga-stati...
BatchStationaryDistributionEstimationJunfengWen1BoDai2LihongLi2DaleSchuurmans12Abstractunderlyingprocess.Nevertheless,onewouldstillliketoestimatetargetpropertiesoftheStationarydistribution,suchWeco...
GradientPrimal-DualAlgorithmConvergestoSecond-OrderStationarySolutionforNonconvexDistributedOptimizationOverNetworksMingyiHong1JasonD.Lee2MeisamRazaviyayn3AbstractthefollowingproblemInthiswork,west...