KernelRecursiveABC:PointEstimationwithIntractableLikelihoodTakafumiKajihara12MotonobuKanagawa3KeisukeYamazaki2KenjiFukumizu4Abstractpopulationgenetics(Pritchardetal.,1999)anddynamicalsystems(Toniet...
JointGAN:Multi-DomainJointDistributionLearningwithGenerativeAdversarialNetsYunchenPu1ShuyangDai2ZheGan3WeiyaoWang2GuoyinWang2YizheZhang3RicardoHenao2LawrenceCarin2AbstractTherehasbeenrecentinterest...
InterpretabilityBeyondFeatureAttribution:QuantitativeTestingwithConceptActivationVectors(TCAV)BeenKimMartinWattenbergJustinGilmerCarrieCaiJamesWexlerFernandaViegasRorySayresAbstractcoefficientweigh...
InterandIntraTopicStructureLearningwithWordEmbeddingsHeZhao1LanDu1WrayBuntine1MingyaunZhou2AbstractTable1.Examplelocaltopicswithtop10words1journalsciencebiologyresearchjournalsOneimportanttaskoftop...
InductiveTwo-layerModelingwithParametricBregmanTransferVigneshGanapathiraman1ZhanShi1XinhuaZhang1YaoliangYu2AbstractThefocusofthispaperisconditionalmodelingforsuper-visedlearning,wherelatentvariabl...
ImprovingSignRandomProjectionswithAdditionalInformationKeeganKang1WongWeiPin1Abstractgularsimilaritywithhighprobability.ThetimetakenunderthistechniquewouldbereducedtoO(npk+n2k).Signrandomprojection...
ImprovingRegressionPerformancewithDistributionalLossesEhsanImani1MarthaWhite1Abstractorabsoluteerrorforregression—butthoselossesarenotnecessarilydirectlyminimized.Thereisgrowingevidencethatconvert...
ImprovingOptimizationforModelswithContinuousSymmetryBreakingRobertBamler1StephanMandt1AbstractWeakcontinuoussymmetrybreakingleadstoanill-conditionedoptimizationproblem.WhenalossfunctionisManylossfu...
IMPALA:ScalableDistributedDeep-RLwithImportanceWeightedActor-LearnerArchitecturesLasseEspeholt1HubertSoyer1RemiMunos1KarenSimonyan1VolodymyrMnih1TomWard1YotamDoron1VladFiroiu1TimHarley1IainDunning1...
GraphRNN:GeneratingRealisticGraphswithDeepAuto-regressiveModelsJiaxuanYou1RexYing1XiangRen2WilliamL.Hamilton1JureLeskovec1Abstractgraphsbasedonaprioristructuralassumptions(Newman,2010).However,akey...
HierarchicalClusteringwithStructuralConstraintsVaggosChatziafratis1RadNiazadeh1MosesCharikar1Abstractgeneexpressiondataanalysis(Eisenetal.,1998),andalsohasbeenusedintheanalysisofsocialnetworks(Lesk...
Gradient-BasedMeta-LearningwithLearnedLayerwiseMetricandSubspaceYoonhoLee1SeungjinChoi1Abstractoperatesontheleveloftasks,gatheringinformationfromseveralinstancesoftask-specificlearners.Atask-speci...
GradientdescentwithidentityinitializationefficientlylearnspositivedefinitelineartransformationsbydeepresidualnetworksPeterL.Bartlett1DavidP.Helmbold2PhilipM.Long3Abstract1.IntroductionWeanalyzealgo...
GenerativeTemporalModelswithSpatialMemoryforPartiallyObservedEnvironmentsMarcoFraccaro1DaniloJimenezRezende2YoriZwols2AlexanderPritzel2S.M.AliEslami2FabioViola2Abstractcanbeusefulformodel-basedrein...
FullyDecentralizedMulti-AgentReinforcementLearningwithNetworkedAgentsKaiqingZhang1ZhuoranYang2HanLiu3TongZhang4TamerBas¸ar1Abstractagent.Inaddition,theagentsareallowedtoobserveonlyitsownreward,whi...
Frank-WolfewithSubsamplingOracleThomasKerdreux1FabianPedregosa23Alexandred’Aspremont41Abstractgorithmandvariantshaveseenanimpressiverevivalinrecentyears,duetotheirlowmemoryrequirementsandWeanalyze...
FastVarianceReductionMethodwithStochasticBatchSizeXuanqingLiu1Cho-JuiHsieh12AbstractHereweassumeeachfi(w)isaµ-stronglyconvex,L-smoothfunction,theregularizationtermg(w)isconvexInthispaperwestudyafa...
FastParametricLearningwithActivationMemorizationJackWRae12ChrisDyer1PeterDayan3TimothyPLillicrap12Abstractspondtoagivenclass.Whentrainedwithasupervisedloss,suchascross-entropy,eachstepofgradientdes...
FastStochasticAUCMaximizationwithO(1/n)-ConvergenceRateMingruiLiu1XiaoxuanZhang1ZaiyiChen2XiaoyuWang3TianbaoYang1Abstract1982).Comparedwithmisclassificationrate,AUCismorefavorableintheapplicationsw...
FastGradient-BasedMethodswithExponentialRate:AHybridControlFrameworkArmanSharifiKolarijani1PeymanMohajerinEsfahani1Tama´sKeciczky1Abstracttheanalysisanddesignofoptimizationalgorithms.Con-sideranit...