LearningIntra-BatchConnectionsforDeepMetricLearningJennySeidenschwarz1IsmailElezi1LauraLeal-Taixe´1AbstractTolearnthemappingfunction,currentapproachesutilizesiamesenetworks(Bromleyetal.,1994),typi...
LearningCurvesforAnalysisofDeepNetworksDerekHoiem1TanmayGupta2ZhizhongLi1MichalM.Shlapentokh-Rothman1Abstracttrapolateratherthanevaluateandhavetypicallyrequiredlarge-scaleexperimentsthatareoutsidet...
LearningDeepNeuralNetworksunderAgnosticCorruptedSupervisionBoyangLiu1MengyingSun1DingWang1Pang-NingTan1JiayuZhou1Abstractduringtraining.Bydetectingandfiltering(orre-weighting)thepossiblecorruptedsa...
GlobalOptimalityBeyondTwoLayers:TrainingDeepReLUNetworksviaConvexProgramsTolgaErgen1MertPilanci1AbstractOutputUnderstandingthefundamentalmechanismbe-InputhindthesuccessofDeepneuralnetworksisoneofth...
GeneralizableEpisodicMemoryforDeepReinforcementLearningHaoHu1JianingYe2GuangxiangZhu1ZhizhouRen3ChongjieZhang1AbstractDiscreteEpisodicMemoryEpisodicmemory-basedmethodscanrapidlyKeyValuelatchontopas...
Large-ScaleMulti-AgentDeepFBSDEsTianrongChen1ZiyiWang2IoannisExarchos3EvangelosA.Theodorou24AbstractAttheequilibrium,eachplayercannotgainanybenefitbymodifyinghis/herownstrategygivenopponents’strat...
LAMDA:LabelMatchingDeepDomainAdaptationTrungLe1TuanNguyen1NhatHo2HungBui3DinhPhung13Abstractconsumingtocollectandlabelhigh-qualitydatasufficientlylargetotrainaccurateDeepmodels,suchasinthedomainDee...
FederatedDeepAUCMaximizationforHeterogeneousDatawithaConstantCommunicationComplexityZhuoningYuan1ZhishuaiGuo1YiXu2YimingYing3TianbaoYang1Abstractdistributedovermultipleclients,e.g.,mobilephones,org...
EmphaticAlgorithmsforDeepReinforcementLearningRayJiang1TomZahavy1ZhongwenXu1AdamWhite12MatteoHessel1CharlesBlundell1HadovanHasselt1AbstractManyreinforcementlearning(RL)agentslearnoff-policytosomeex...
DiscoveringsymbolicpolicieswithDeepreinforcementlearningMikelLandajuela1BrendenK.Petersen1SookyungKim1ClaudioP.Santiago1RubenGlatt1T.NathanMundhenk1JacobF.Pettit1DanielM.Faissol1AbstractFigure1:Alg...
DescendingthroughaCrowdedValley—BenchmarkingDeepLearningOptimizersRobinM.Schmidt1FrankSchneider1PhilippHennig12Abstract1.IntroductionChoosingtheoptimizerisconsideredtobeamongLarge-scalestochastico...
DelvingintoDeepImbalancedRegressionYuzheYang1KaiwenZha1Ying-CongChen1HaoWang2DinaKatabi1AbstractNumberofsamplesDeepImbalancedRegressionReal-worlddataoftenexhibitimbalanceddistri-Imbalanceddistribut...
DeepReinforcementLearningamidstContinualStructuredNon-StationarityAnnieXie1JamesHarrison1ChelseaFinn1Abstractstationaritymanifestsitselfinchangingterrainsandweatherconditions.Insomesituations,notev...
DeepLearningforFunctionalDataAnalysiswithAdaptiveBasisLayersJunwenYao1JonasMueller2Jane-LingWang1Abstractindividualsubjectinourdataset.Withoutlossofgeneral-ityweassumethattheintervalis[0,1].Thecurv...
DeepkernelprocessesLaurenceAitchison1AdamX.Yang1SebastianW.Ober2Abstractalreadyexist.Inthesemethods,whicharecloselyre-latedtoinfiniteBayesianneuralnetworks(Leeetal.,2017;WedefineDeepkernelprocesses...
DeepCoherentExplorationforContinuousControlYijieZhang1HerkevanHoof2Abstractstrategiesandundirectedstrategies(Thrun,1992;Plappertetal.,2018).Whiledirectedstrategiesaimtoextractuse-Inpolicysearchmeth...
DeepGenerativeLearningviaSchro¨dingerBridgeGefeiWang1YulingJiao2QianXu3YangWang14CanYang14AbstractChoietal.,2020),semanticimageediting(Zhuetal.,2016;Shenetal.,2020)andaudiosynthesis(VanDenOordetal...
DeepContinuousNetworksNergisTomen1SilviaL.Pintea1JanC.vanGemert1Abstractcalcircuits(Schrimpfetal.,2018),andemployCNNsasmodelsofbiologicalvision(Zhuangetal.,2020a).Specif-CNNsandcomputationalmodelso...
DeepAdaptiveDesign:AmortizingSequentialBayesianExperimentalDesignAdamFoster1DesiR.Ivanova1IlyasMalik2TomRainforth1Abstractusingalikelihoodp(yθ,ξ)andapriorp(θ),whereξisourcontrollabledesignandθ...