ExplicitInductiveBiasforTransferLearningwithConvolutionalNetworksXuhongLI1YvesGRANDVALET1FranckDAVOINE1Abstractlearningfromthelarge-scaledatabaseofthesourcetaskandthisknowledgeisthentransferredtoth...
EscapingSaddleswithStochasticGradientsHadiDaneshmand1JonasKohler1AurelienLucchi1ThomasHofmann1Abstractthroughaconservativestepsize(Nesterov,2013)orviaexplicitvariance-reductiontechniques(Johnson&Zh...
EfficientModel–BasedDeepReinforcementLearningwithVariationalStateTabulationDaneCorneil1WulframGerstner1JohanniBrea1Abstractstates(e.g.Mnihetal.(2015;2016))andlearningapproxi-matedynamicstoperformp...
DVAE++:DiscreteVariationalAutoencoderswithOverlappingTransformationsArashVahdat1WilliamG.Macready1ZhengbingBian1AmirKhoshaman1EvgenyAndriyash1AbstractSoftmaxtechnique(Maddisonetal.,2016;Jangetal.,2...
DistributedAsynchronousOptimizationwithUnboundedDelays:HowSlowCanYouGo?ZhengyuanZhou1PanayotisMertikopoulos2NicholasBambos1PeterGlynn1YinyuYe1Li-JiaLi3LiFei-Fei13Abstractcommensuratesurgeofinterest...
Dimensionality-DrivenLearningwithNoisyLabelsXingjunMa1YisenWang2MichaelE.Houle3ShuoZhou1SarahM.Erfani1Shu-TaoXia2SudanthiWijewickrema1JamesBailey1Abstractachievegoodgeneralizationperformanceinthepr...
Differentiableplasticity:trainingplasticneuralnetworkswithbackpropagationThomasMiconi1JeffClune1KennethO.Stanley1Abstractexamples.Bycontrast,biologicalagentsexhibitaremark-ableabilitytolearnquickly...
DetectingandCorrectingforLabelShiftwithBlackBoxPredictorsZacharyC.Lipton12Yu-XiangWang23AlexanderJ.Smola2Abstractiidassumption.Absentfamiliarguarantees,wewonder:Isfstillaccurate?What’stherealcurre...
DeepLinearNetworkswithArbitraryLoss:AllLocalMinimaAreGlobalThomasLaurent1JamesH.vonBrecht2Abstractdeepnonlinearnetworksduringtraining(Saxeetal.,2014).Resultsofthissortprovideasmallpieceofevidenceth...
Deepk-Means:Re-TrainingandParameterSharingwithHarderClusterAssignmentsforCompressingDeepConvolutionsJunruWu1YueWang2ZhenyuWu1ZhangyangWang1AshokVeeraraghavan2YingyanLin2Abstract1.IntroductionThecur...
DecoupledParallelBackpropagationwithConvergenceGuaranteeZhouyuanHuo1BinGu1QianYang1HengHuang1AbstractFigure1.Wesplitamultilayerfeedforwardneuralnetworkintothreemodules.Eachmoduleisastackoflayers.Ba...
DCFNet:DeepNeuralNetworkwithDecomposedConvolutionalFiltersQiangQiu1XiuyuanCheng1RobertCalderbank1GuillermoSapiro1AbstractFigure1.InaDCFNet,anL×L×M×Mconvolutionallayerisdecomposedintotheproductof...
Cut-PursuitAlgorithmforRegularizingNonsmoothFunctionalswithGraphTotalVariationHugoRaguet1LoïcLandrieu2AbstractustofindstationarypointsofF,thatistosaypointsatwhichalldirectionalderivativesofFarenon...
CrowdsourcingwithArbitraryAdversariesMattha¨usKleindessner1PranjalAwasthi1Abstracttosolvetoomanytasksandthedatacuratorwantingtogethigh-qualitylabelsatalowprice.ThecanonicalexampleMostexistingworks...
CoVeR:LearningCovariate-SpecificVectorRepresentationswithTensorDecompositionsKevinTian1TengZhang2JamesZou3Abstract1.IntroductionWordembeddingisausefulapproachtocap-Theuseoffactorizationsofco-occurr...
ConvergentTREEBACKUPandRETRACEwithFunctionApproximationAhmedTouati12Pierre-LucBacon3DoinaPrecup34PascalVincent124Abstractdifferenttargetswhichmaytaketheformofvaluefunctionscorrespondingtodifferentp...
ContinualReinforcementLearningwithComplexSynapsesChristosKaplanis12MurrayShanahan13ClaudiaClopath2Abstractoldmemories-aparadoxoftenreferredtoasthestability-plasticitydilemma(Carpenter&Grossberg,198...
ComposablePlanningwithAttributesAmyZhang1AdamLerer1SainbayarSukhbaatar2RobFergus12ArthurSzlam1Abstractmakingpancakesoranomelette.Ifthespaceoftaskswewantanagenttobeabletosolvehascompositionalstructu...
CompetitiveMulti-agentInverseReinforcementLearningwithSub-optimalDemonstrationsXingyuWang1DiegoKlabjan1Abstractoftherewardfunction,oratleastobservationsofimmediatereward.Somelearningtasks,however,p...
CompetitiveCachingwithMachineLearnedAdviceThodorisLykouris1SergeiVassilvitskii2Abstractdoingso,thesystemmayinvestitseffortsonreducingtheerroronthemajorityofinputs,attheexpenseofincreasedWedevelopaf...