SignaturedDeepFictitiousPlayforMeanFieldGameswithCommonNoiseMingMin1RuimengHu12Abstractrealisticmodels,theproblemusuallylackstractabilityandneedsnumericalmethods.WithalargenumberofplayersExistingde...
SimAM:ASimple,Parameter-FreeAttentionModuleforConvolutionalNeuralNetworksLingxiaoYang123Ru-YuanZhang45LidaLi6XiaohuaXie123AbstractResNet-50Inthispaper,weproposeaconceptuallysimple+SEbutveryeffectiv...
Shortest-PathConstrainedReinforcementLearningforSparseRewardTasksSungryullSohn12SungtaeLee3JongwookChoi1HarmvanSeijen4MehdiFatemi4HonglakLee21AbstractMoreover,thesuccessoftheRLalgorithmheavilyhinge...
SharperGeneralizationBoundsforClusteringShaojieLi12YongLiu12Abstractclusteringalgorithmdesignandapplication,thestatisticaltheoryofclusteringmayappeartobenotsufficient.TheExistinggeneralizationanaly...
SGA:ARobustAlgorithmforPartialRecoveryofTree-StructuredGraphicalModelswithNoisySamplesAnshooTandon1AldricJ.Y.Han2VincentY.F.Tan12Abstractnetworks(Lauritzen,1996)andcomputervision(Besag,1986).forade...
Self-TuningforData-EfficientDeepLearningXimeiWang1JinghanGao1MingshengLong1JianminWang1Abstractmustbedonebyanexpertsuchasadoctorinmedicalapplications.Tomitigatetherequirementforlabeleddata,Deeplear...
Self-supervisedandSupervisedJointTrainingforResource-richMachineTranslationYongCheng1WeiWang†LuJiang12WolfgangMacherey1Abstractsupervisedtaskonabundantunlabeleddata(i.e.monolin-gualsentences).Inth...
Self-PacedContextEvaluationforContextualReinforcementLearningTheresaEimer1Andre´Biedenkapp2FrankHutter23MariusLindauer1AbstractFigure1:ExampleinstancesofthecontextualPointMassenvironment.Theagent...
SelectingDataAugmentationforSimulatingInterventionsMaximilianIlse1JakubM.Tomczak2Patrickforre´1AbstractInthefieldofdomaingeneralization,onetriestofindarep-resentationthatgeneralizesacrossdifferent...
SECANT:Self-ExpertCloningforZero-ShotGeneralizationofVisualPoliciesLinxiFan12GuanzhiWang1De-AnHuang2ZhidingYu2LiFei-Fei1YukeZhu32AnimaAnandkumar42AbstractTrainingZero-shotEvaluationGeneralizationha...
ScalableOptimalTransportinHighDimensionsforGraphDistances,EmbeddingAlignment,andMoreJohannesKlicpera1MartenLienen1StephanGünnemann1Abstractcostw.r.t.somepointwisecostfunction(e.g.theEuclideandista...
ScalableMarginalLikelihoodEstimationforModelSelectioninDeepLearningAlexanderImmer12MatthiasBauer†34Vincentfortuin1GunnarRätsch12MohammadEmtiyazKhan5Abstract3layers,5221params1layer,151paramsMargL...
ScalableNormalizingFlowsforPermutationInvariantDensitiesMarinBiloš1StephanGünnemann1Abstractt0t1ModelingsetsisanimportantprobleminmachineBasedistributionfTargetdistributionlearningsincethistypeof...
SAINT-ACC:Safety-AwareIntelligentAdaptiveCruiseControlforAutonomousVehiclesUsingDeepReinforcementLearningLokeshDas1MyounggyuWon1Abstractenhancingtrafficflow,overlookingtheimpactofadaptiveadjustment...
SagaNet:ASmallSampleGatedNetworkforPediatricCancerDiagnosisYuhanLiu1ShiliangSun1Abstracttodevotealotoftimeandendeavorsduringbusywork.Second,fortheprotectionofdataprivacy,manyhospitalsorThescarcityo...
RRL:ResnetasrepresentationforReinforcementLearningRutavShah1VikashKumar2AbstractSupervisedLearningTheabilitytoautonomouslylearnbehaviorsviaReinforcementdirectinteractionsinuninstrumentedenviron-Lea...
RobustInferenceforHigh-DimensionalLinearModelsviaResidualRandomizationY.SamuelWang1SiKaiLee1PanosToulis1MladenKolar1Abstractsamplesplittingprocedurestoformvalidp-values.Zhang&Zhang(2014),VandeGeere...
RobustLearningforDataPoisoningAttacksYunjuanWang1PooryaMianjy1RamanArora1Abstractinsettingswhereanadversarycanaffectanypartofthetrainingdata.Therefore,inthispaper,weareinterestedinWeinvestigatether...
RepresentationSubspaceDistanceforDomainAdaptationRegressionXinyangChen1SinanWang1JianminWang1MingshengLong1Abstractsuchasobjectlocalization,imageregistration,humanposeestimation,tonameafew(Lathuili...
ReservePriceOptimizationforFirstPriceAuctionsinDisplayAdvertisingZheFeng1SébastienLahaie2JonSchneider2JinchaoYe2Abstracttimizationinfirst-price(i.e.,pay-your-bid)auctions,mo-tivatedbythefactthatal...