Learning-to-LearnStochasticGradientDescentwithBiasedRegularizationGiuliaDenevi12CarloCiliberto34RiccardoGrazzi14MassimilianoPontil14Abstracttasksfromaprescribedfamily.Tohighlightthedifferencebetwee...
Learninginterpretablecontinuous-timemodelsoflatentStochasticdynamicalsystemsLeaDuncker1Gergo˝Bohner1JulienBoussard2ManeeshSahani1Abstractaccuratelymodelledusingadiscretetimegrid.Wedevelopanapproac...
FeatureGroupingasaStochasticRegularizerforHigh-DimensionalStructuredDataSergu¨lAydo¨re1BertrandThirion2Gae¨lVaroquaux2Abstract1.Largefeaturedimension:Neuroimagingdataareveryhigh-dimensional,duet...
FasterStochasticAlternatingDirectionMethodofMultipliersforNonconvexOptimizationFeihuHuang1SongcanChen23HengHuang14Abstract1.IntroductionInthispaper,weproposeafasterStochasticalter-Alternatingdirect...
EstimateSequencesforVariance-ReducedStochasticCompositeOptimizationAndreiKulunchakov1JulienMairal1AbstractWhilethefinite-sumsettingisaparticularcaseofexpecta-tion,thedeterministicnatureoftheresulti...
DOUBLESQUEEZE:ParallelStochasticGradientDescentwithDouble-passError-CompensatedCompressionHanlinTang1XiangruLian1ChenYu1TongZhang2JiLiu31Abstract1.IntroductionAstandardapproachinlargescalemachinele...
DecentralizedStochasticOptimizationandGossipAlgorithmswithCompressedCommunicationAnastasiaKoloskova1SebastianU.Stich1MartinJaggi1Abstracttionwithneighboringdevices.Thiscoversforinstancetheclassicse...
DataPoisoningAttacksonStochasticBanditsFangLiu1NessShroff12Abstractismotivatedbymodernindustrialscaleapplicationsofma-chinelearningsystems,wheredatacollectionandpolicyStochasticmulti-armedbanditsfo...
ConditionalGradientMethodsviaStochasticPath-IntegratedDifferentialEstimatorAlpYurtsever1SuvritSra2VolkanCevher1AbstractarelatedworkbyHazan&Luo(2016)),constraineddeeplearningproblems(e.g.,Ravietal.(...
BeatingStochasticandAdversarialSemi-banditsOptimallyandSimultaneouslyJulianZimmert1HaipengLuo2Chen-YuWei2Abstracttrary,theminimaxoptimalregretisoforderO(√T)(Aueretal.,2002).Wedevelopthefirstgenera...
AdaptiveStochasticNaturalGradientMethodforOne-ShotNeuralArchitectureSearchYouheiAkimoto1ShinichiShirakawa2NozomuYoshinari2KentoUchida2ShotaSaito23KouheiNishida4AbstractWorkpublishedbefore2017oftenf...
AcceleratedLinearConvergenceofStochasticMomentumMethodsinWassersteinDistancesBugraCan1MertGurbuzbalaban1LingjiongZhu2Abstractsupervisedlearningincludelinearandnon-linearregressionproblems,supportve...
ATail-IndexAnalysisofStochasticGradientNoiseinDeepNeuralNetworksUmutS¸ims¸ekli1LeventSagun2MertGu¨rbu¨zbalaban3Abstractmanyapplicationdomains(LeCunetal.,2015;Krizhevskyetal.,2012;Hintonetal.,20...
Zeno:DistributedStochasticGradientDescentwithSuspicion-basedFault-toleranceCongXie1OluwasanmiKoyejo1IndranilGupta1Abstractvarianceandmagnitude,makingthemhardtodistinguish.Itisalsopossiblethatindiff...
TowardsMoreEfficientStochasticDecentralizedLearning:FasterConvergenceandSparseCommunicationZebangShen12AryanMokhtari3TengfeiZhou1PeilinZhao4HuiQian1Abstractvariableofnoden,theproblemofinterestisRec...
StochasticWassersteinBarycentersSebastianClaici1EdwardChien1JustinSolomon1AbstractsumofsquaredWassersteindistancestotheinputdistribu-WepresentaStochasticalgorithmtocomputethetions(Agueh&Carlier,201...
StochasticVariance-ReducedHamiltonMonteCarloMethodsDifanZou1PanXu1QuanquanGu1Abstractconvergestoitsstationarydistribution,a.k.a.,theGibbsmeasure⇡/exp(f(x)).Notethat⇡issmoothandWeproposeafaststoch...
StochasticVariance-ReducedPolicyGradientMatteoPapini1DamianoBinaghi1GiuseppeCanonaco1MatteoPirotta2MarcelloRestelli1Abstractavaluefunction,ordirectlyapolicydefiningtheagent’sbehaviour.Furthermore,...
StochasticVideoGenerationwithaLearnedPriorEmilyDenton1RobFergus12AbstractdependentStochasticlatentvariables.Weproposetwovari-antsofourmodel:onewithafixedprioroverthelatentGeneratingvideoframesthata...
StochasticTrainingofGraphConvolutionalNetworkswithVarianceReductionJianfeiChen1JunZhu1LeSong23Abstractdonotusethegraphstructure,andgraphembeddingap-proaches(Perozzietal.,2014;Tangetal.,2015;Grover&...