PredictthenInterpolate:ASimpleAlgorithmtoLearnStableClassifiersYujiaBao1ShiyuChang2ReginaBarzilay3Abstractthelabelmayvary.Insteadofhandcraftingenvironmentsbasedonexplicit,task-dependentbiases,these...
PHEW:ConstructingSparseNetworksthatLearnFastandGeneralizeWellWithoutTrainingDataShreyasMalakarjunPatil1ConstantineDovrolis1Abstracterally,suchmethodsuseanedgescoringmechanismforeliminatingthelessim...
LeveragingLanguagetoLearnProgramAbstractionsandSearchHeuristicsCatherineWong1KevinEllis2JoshuaB.Tenenbaum13JacobAndreas1Abstractmodelsusingnaturallanguagesupervision.InLAPS,lan-guageguidesLearningo...
HowtoLearnwhenDataReactstoYourModel:PerformativeGradientDescentZacharyIzzo1LexingYing12JamesZou3Abstractimagingdatafromonehospitalisdeployedatadifferenthospitalduetothedifferenceinimagingdevices.Ti...
FinitemixturemodelsdonotreliablyLearnthenumberofcomponentsDianaCai1TrevorCampbell2TamaraBroderick3Abstracthakaranetal.,2016),microscopygroups(Rubin-Delanchyetal.,2015;Griffie´etal.,2016),haplotype...
DecidingWhattoLearn:ARate-DistortionApproachDilipArumugam1BenjaminVanRoy1Abstractofinformationthat,whileinsufficienttofullyidentifytheenvironment,sufficestoguideeffectivedecisions.Then,Agentsthatle...
APolicyGradientAlgorithmforLearningtoLearninMultiagentReinforcementLearningDong-KiKim12MiaoLiu23MatthewRiemer23ChuangchuangSun12MarwaAbdulhai12GolnazHabibi12SebastianLopez-Cot12GeraldTesauro23Jonat...
TwoSimpleWaystoLearnIndividualFairnessMetricsfromDataDebarghyaMukherjee1MikhailYurochkin2MoulinathBanerjee1YuekaiSun1Abstractfeaturespaceinto(non-overlapping)protectedsubsetsandimposesinvarianceoft...
LearningtoLearnKernelswithVariationalRandomFeaturesXiantongZhen12HaoliangSun3YingjunDu2JunXu4YilongYin3LingShao51CeesSnoek2Abstractfromrelatedtaskstoenablefastadaptationtoanewtaskwithalimitedamount...
It’sNotWhatMachinesCanLearn,It’sWhatWeCannotTeachGalYehuda1MosheGabel2AssafSchuster1AbstractdatasetgenerationprocesscomplexityofresultingtaskCandeepneuralnetworksLearntosolveanytask,harderandinpa...
Explore,DiscoverandLearn:UnsupervisedDiscoveryofState-CoveringSkillsV´ıctorCampos1AlexTrott2CaimingXiong2RichardSocher2XavierGiro-i-Nieto3JordiTorres1AbstractFigure1.SkillsLearnedonamazewithbottl...
LearntoGrow:AContinualStructureLearningFrameworkforOvercomingCatastrophicForgettingXilaiLi†1YingboZhou2TianfuWu1RichardSocher2CaimingXiong2AbstractLearningwithdeepneuralnetworks(DNNs).Whenpre-sent...
LearnfromYourNeighbor:LearningMulti-modalMappingsfromSparseAnnotationsAshwinKalyan1StefanLee1AnithaKannan2DhruvBatra13AbstractAhomekitchenwithwoodencabinetsandadinningtable.Manystructuredprediction...
LearningtoLearnwithoutGradientDescentbyGradientDescentYutianChen1MatthewW.Hoffman1SergioGo´mezColmenarejo1MishaDenil1TimothyP.Lillicrap1MattBotvinick1NandodeFreitas1Abstractdientdescent,evolutiona...
DeepValueNetworksLearntoEvaluateandIterativelyRefineStructuredOutputsMichaelGygli1MohammadNorouzi2AneliaAngelova2Abstractcomplicatedhighlevelreasoningtoresolveambiguity.Weapproachstructuredoutputpr...