NeurIPS今年共收录1900篇论文，我该怎么阅读？GoogleNeural论文阅读AI

BentengMa(NorthwesternPolytechnicalUniversity)·JingZhang(TheUniversityofSydney)·YongXia(NorthwesternPolytechnicalUniversity,Research&DevelopmentInstituteofNorthwesternPolytechnicalUniversityinShenzhen)·DachengTao(UniversityofSydney)

2、BayesianAttentionModules

XinjieFan(UTAustin)·ShujianZhang(UTAustin)·BoChen(XidianUniversity)·MingyuanZhou(UniversityofTexasatAustin)

3、ImprovingNaturalLanguageProcessingTaskswithHumanGaze-GuidedNeuralAttention

EktaSood(UniversityofStuttgart,Simtech)·SimonTannert(InstituteforNaturalLanguageProcessing,UniversityofStuttgart)·PhilippMueller(VIS,UniversityofStuttgart)·AndreasBulling(UniversityofStuttgart)

4、ProphetAttention:PredictingAttentionwithFutureAttentionforImprovedImageCaptioning

FenglinLiu(PekingUniversity)·XuanchengRen(PekingUniversity)·XianWu(TencentMedicalAILab)·ShenGe(TencentMedicalAILab)·WeiFan(Tencent)·YuexianZou(PekingUniversity)·XuSun(PekingUniversity)

5、KalmanFilteringAttentionforUserBehaviorModelinginCTRPrediction

HuLiu(JD.com)·JingLU(BusinessGrowthBUJD.com)·XiweiZhao(JD.com)·SulongXu(JD.com)·HaoPeng(JD.com)·YutongLiu(JD.com)·ZehuaZhang(JD.com)·JianLi(JD.com)·JunshengJin(JD.com)·YongjunBao(JD.com)·WeipengYan(JD.com)

6、RANet:RegionAttentionNetworkforSemanticSegmentation

DingguoShen(ShenzhenUniversity)·YuanfengJi(CityUniversityofHongKong)·PingLi(TheHongKongPolytechnicUniversity)·YiWang(ShenzhenUniversity)·DiLin(TianjinUniversity)

7、SE(3)-Transformers:3DRoto-TranslationEquivariantAttentionNetworks

FabianFuchs(UniversityofOxford)·DanielWorrall(UniversityofAmsterdam)·VolkerFischer(RobertBoschGmbH,BoschCenterforArtificialIntelligence)·MaxWelling(UniversityofAmsterdam/QualcommAIResearch)

8、ComplementaryAttentionSelf-DistillationforWeakly-SupervisedObjectDetection

ZeyiHuang(carnegiemellonuniversity)·YangZou(CarnegieMellonUniversity)·B.V.K.VijayaKumar(CMU,USA)·DongHuang(CarnegieMellonUniversity)

9、ModernHopfieldNetworksandAttentionforImmuneRepertoireClassification

MichaelWidrich(LITAILab/UniversityLinz)·BernhardSchfl(JKULinz)·MilenaPavlovi(DepartmentofInformatics,UniversityofOslo)·HubertRamsauer(LITAILab,InstituteforMachineLearning,JohannesKeplerUniversityLinz,Austria)·LukasGruber(JohannesKeplerUniversity)·MarkusHolzleitner(LITAILab/UniversityLinz)·JohannesBrandstetter(LITAILab/UniversityLinz)·GeirKjetilSandve(DepartmentofInformatics,UniversityofOslo)·VictorGreiff(DepartmentofImmunology,UniversityofOslo)·SeppHochreiter(LITAILab/UniversityLinz/IARAI)·GünterKlambauer(LITAILab/UniversityLinz)

10、Untanglingtradeoffsbetweenrecurrenceandself-attentioninartificialneuralnetworks

GiancarloKerg(MILA)·BhargavKanuparthi(MontrealInstituteforLearningAlgorithms)·AnirudhGoyalALIASPARTHGOYAL(UniversitédeMontréal)·KyleGoyette(UniversityofMontreal)·YoshuaBengio(Mila/U.Montreal)·GuillaumeLajoie(Mila,UniversitédeMontréal)

11、RATT:RecurrentAttentiontoTransientTasksforContinualImageCaptioning

RiccardoDelChiaro(UniversityofFlorence)·BartomiejTwardowski(ComputerVisionCenter,UAB)·AndrewDBagdanov(UniversityofFlorence)·JoostvandeWeijer(ComputerVisionCenterBarcelona)

12、Multi-TaskTemporalShiftAttentionNetworksforOn-DeviceContactlessVitalsMeasurement

XinLiu(UniversityofWashington)·JoshFromm(OctoML)·ShwetakPatel(UniversityofWashington)·DanielMcDuff(MicrosoftResearch)

13、SAC:AcceleratingandStructuringSelf-AttentionviaSparseAdaptiveConnection

XiaoyaLi(Shannon.AI)·YuxianMeng(Shannon.AI)·MingxinZhou(Shannon.AI)·QinghongHan(Shannon.AI)·FeiWu(ZhejiangUniversity)·JiweiLi(Shannon.AI)

14、FastTransformerswithClusteredAttention

ApoorvVyas(IdiapResearchInstitute)·AngelosKatharopoulos(Idiap)·FranoisFleuret(UniversityofGeneva)

15、SparseandContinuousAttentionMechanisms

AndréMartins()·MarcosTreviso(InstitutodeTelecomunicacoes)·AntónioFarinhas(InstitutoSuperiorTécnico)·VladNiculae(InstitutodeTelecomunicaes)·MarioFigueiredo(UniversityofLisbon)·PedroAguiar(InstitutoSuperiorTécnico)

16、LearningtoExecuteProgramswithInstructionPointerAttentionGraphNeuralNetworks

DavidBieber(GoogleBrain)·CharlesSutton(Google)·HugoLarochelle(GoogleBrain)·DanielTarlow(GoogleBrain)

17、Neuralencodingwithvisualattention

MeenakshiKhosla(CornellUniversity)·GiaNgo(CornellUniversity)·KeithJamison(CornellUniversity)·AmyKuceyeski(CornellUniversity)·MertSabuncu(Cornell)

18、DeepReinforcementLearningwithStackedHierarchicalAttentionforText-basedGames

YunqiuXu(UniversityofTechnologySydney)·MengFang(Tencent)·LingChen("UniversityofTechnology,Sydney,Australia")·YaliDu(UniversityCollegeLondon)·JoeyTianyiZhou(IHPC,A*STAR)·ChengqiZhang(UniversityofTechnologySydney)

19、Object-CentricLearningwithSlotAttention

FrancescoLocatello(ETHZürich-MPITübingen)·DirkWeissenborn(Google)·ThomasUnterthiner(GoogleResearch,BrainTeam)·AravindhMahendran(Google)·GeorgHeigold(Google)·JakobUszkoreit(Google,Inc.)·AlexeyDosovitskiy(GoogleResearch)·ThomasKipf(GoogleResearch)

20、SMYRF-Efficientattentionusingasymmetricclustering

GiannisDaras(NationalTechnicalUniversityofAthens)·NikitaKitaev(UniversityofCalifornia,Berkeley)·AugustusOdena(GoogleBrain)·AlexandrosDimakis(UniversityofTexas,Austin)

21、FocusofAttentionImprovesInformationTransferinVisualFeatures

MatteoTiezzi(UniversityofSiena)·StefanoMelacci(UniversityofSiena)·AlessandroBetti(UniversityofSiena)·MarcoMaggini(UniversityofSiena)·MarcoGori(UniversityofSiena)

22、AttendLight:UniversalAttention-BasedReinforcementLearningModelforTrafficSignalControl

AfshinOroojlooy(SASInstitute,Inc)·MohammadrezaNazari(SASInstituteInc.)·DavoodHajinezhad(SASInstituteInc.)·JorgeSilva(SAS)

23、Multi-agentTrajectoryPredictionwithFuzzyQueryAttention

NitinKamra(UniversityofSouthernCalifornia)·HaoZhu(PekingUniversity)·DweepKumarbhaiTrivedi(UniversityofSouthernCalifornia)·MingZhang(PekingUniversity)·YanLiu(UniversityofSouthernCalifornia)

24、LimitstoDepthEfficienciesofSelf-Attention

YoavLevine(HUJI)·NoamWies(HebrewUniversityofJerusalem)·OrSharir(HebrewUniversityofJerusalem)·HofitBata(HebrewUniversityofJerusalem)·AmnonShashua(HebrewUniversityofJerusalem)

25、ImprovingNaturalLanguageProcessingTaskswithHumanGaze-GuidedNeuralAttention

EktaSood(UniversityofStuttgart,Simtech)·SimonTannert(InstituteforNaturalLanguageProcessing,UniversityofStuttgart)·PhilippMueller(VIS,UniversityofStuttgart)·AndreasBulling(UniversityofStuttgart

1、FastTransformerswithClusteredAttention

2、DeepTransformerswithLatentDepth

XianLi(Facebook)·AsaCooperStickland(UniversityofEdinburgh)·YuqingTang(FacebookAI)·XiangKong(CarnegieMellonUniversity)

3、CrossTransformers:spatially-awarefew-shottransfer

CarlDoersch(DeepMind)·AnkushGupta(DeepMind)·AndrewZisserman(DeepMind&UniversityofOxford)

4、SE(3)-Transformers:3DRoto-TranslationEquivariantAttentionNetworks

5、Funnel-Transformer:FilteringoutSequentialRedundancyforEfficientLanguageProcessing

ZihangDai(CarnegieMellonUniversity)·GuokunLai(CarnegieMellonUniversity)·YimingYang(CMU)·QuocVLe(Google)

6、AdversarialSparseTransformerforTimeSeriesForecasting

SifanWu(TsinghuaUniversity)·XiXiao(TsinghuaUniversity)·QianggangDing(TsinghuaUniversity)·PeilinZhao(TencentAILab)·YingWei(TencentAILab)·JunzhouHuang(UniversityofTexasatArlington/TencentAILab)

7、AcceleratingTrainingofTransformer-BasedLanguageModelswithProgressiveLayerDropping

MinjiaZhang(Microsoft)·YuxiongHe(Microsoft)

8、COOT:CooperativeHierarchicalTransformerforVideo-TextRepresentationLearning

MohammadrezaZolfaghari(UniversityofFreiburg)·SimonGing(UniFreiburg)·HamedPirsiavash(UniversityofMaryland,BaltimoreCounty)·ThomasBrox(UniversityofFreiburg)

9、CascadedTextGenerationwithMarkovTransformers

YuntianDeng(HarvardUniversity)·AlexanderRush(CornellUniversity)

10、GROVER:Self-SupervisedMessagePassingTransformeronLarge-scaleMolecularGraphs

YuRong(TencentAILab)·YataoBian(TencentAILab)·TingyangXu(TencentAILab)·WeiyangXie(TencentAILab)·YingWEI(TencentAILab)·WenbingHuang(TsinghuaUniversity)·JunzhouHuang(UniversityofTexasatArlington/TencentAILab)

11、LearningtoCommunicateinMulti-AgentSystemsviaTransformer-GuidedProgramSynthesis

JeevanaPriyaInala(MIT)·YichenYang(MIT)·JamesPaulos(UniversityofPennsylvania)·YewenPu(MIT)·OsbertBastani(UniversityofPennysylvania)·VijayKumar(UniversityofPennsylvania)·MartinRinard(MIT)·ArmandoSolar-Lezama(MIT)

12、MeasuringSystematicGeneralizationinNeuralProofGenerationwithTransformers

NicolasGontier(Mila,PolytechniqueMontréal)·KoustuvSinha(McGillUniversity/Mila/FAIR)·SivaReddy(McGillUniversity)·ChrisPal(MontrealInstituteforLearningAlgorithms,écolePolytechnique,UniversitédeMontréal)

13、O(n)ConnectionsareExpressiveEnough:UniversalApproximabilityofSparseTransformers

ChulheeYun(MIT)·Yin-WenChang(GoogleInc.)·SrinadhBhojanapalli(GoogleAI)·AnkitSinghRawat(GoogleResearch)·SashankReddi(Google)·SanjivKumar(GoogleResearch)

14、MiniLM:DeepSelf-AttentionDistillationforTask-AgnosticCompressionofPre-TrainedTransformers

WenhuiWang(MSRA)·FuruWei(MicrosoftResearchAsia)·LiDong(MicrosoftResearch)·HangboBao(HarbinInstituteofTechnology)·NanYang(MicrosoftResearchAsia)·MingZhou(MicrosoftResearch)

1、Pre-trainingviaParaphrasing

MikeLewis(FacebookAIResearch)·MarjanGhazvininejad(FacebookAIResearch)·GargiGhosh(Facebook)·ArmenAghajanyan(Facebook)·SidaWang(FacebookAIResearch)·LukeZettlemoyer(UniversityofWashingtonandAllenInstituteforArtificialIntelligence)

2、Pre-TrainingGraphNeuralNetworks:AContrastiveLearningFrameworkwithAugmentations

YuningYou(TexasA&MUniversity)·TianlongChen(UnversityofTexasatAustin)·YongduoSui(UniversityofScienceandTechnologyofChina)·TingChen(Google)·ZhangyangWang(UniversityofTexasatAustin)·YangShen(TexasA&MUniversity)

3、RethinkingPre-trainingandSelf-training

BarretZoph(GoogleBrain)·GolnazGhiasi(Google)·Tsung-YiLin(GoogleBrain)·YinCui(Google)·HanxiaoLiu(GoogleBrain)·EkinDogusCubuk(GoogleBrain)·QuocVLe(Google)

4、MPNet:MaskedandPermutedPre-trainingforLanguageUnderstanding

KaitaoSong(NanjingUniversityofScienceandtechnology)·XuTan(MicrosoftResearch)·TaoQin(MicrosoftResearch)·JianfengLu(NanjingUniversityofScienceandTechnology)·Tie-YanLiu(MicrosoftResearchAsia)

5、AdversarialContrastiveLearning:HarvestingMoreRobustnessfromUnsupervisedPre-Training

ZiyuJiang(TexasA&MUniversity)·TianlongChen(UnversityofTexasatAustin)·TingChen(Google)·ZhangyangWang(UniversityofTexasatAustin)

1、ARanking-based,BalancedLossFunctionforBothClassificationandLocalisationinObjectDetection

KemalOksuz(MiddleEastTechnicalUniversity)·BarisCanCam(Roketsan)·EmreAkbas(MiddleEastTechnicalUniversity)·SinanKalkan(MiddleEastTechnicalUniversity)

2、UWSOD:TowardFully-Supervised-LevelPerformanceWeaklySupervisedObjectDetection

YunhangShen(XiamenUniversity)·RongrongJi(XiamenUniversity,China)·ZhiweiChen(XiamenUniversity)·YongjianWu(TencentTechnology(Shanghai)Co.,Ltd)·FeiyueHuang(Tencent)

3、GeneralizedFocalLoss:LearningQualifiedandDistributedBoundingBoxesforDenseObjectDetection

XiangLi(NJUST)·WenhaiWang(NanjingUniversity)·LijunWu(SunYat-senUniversity)·ShuoChen(NanjingUniversityofScienceandTechnology)·XiaolinHu(TsinghuaUniversity)·JunLi(NanjingUniversityofScienceandTechnology)·JinhuiTang(NanjingUniversityofScienceandTechnology)·JianYang(NanjingUniversityofScienceandTechnology)

4、EveryViewCounts:Cross-ViewConsistencyin3DObjectDetectionwithHybrid-Cylindrical-SphericalVoxelization

QiChen(JohnsHopkinsUniversity)·LinSun(Samsung,Stanford,HKUST)·ErnestCheung(Samsung)·AlanYuille(JohnsHopkinsUniversity)

5、ComplementaryAttentionSelf-DistillationforWeakly-SupervisedObjectDetection

6、Few-CostSalientObjectDetectionwithAdversarial-PacedLearning

DingwenZhang(XidianUniversity)·HaiBinTian(XidianUniversity)·JungongHan(UniversityofWarwick)

7、BridgingVisualRepresentationsforObjectDetection

ChengChi(UniversityofChineseAcademyofSciences)·FangyunWei(MicrosoftResearchAsia)·HanHu(MicrosoftResearchAsia)

8、Fine-GrainedDynamicHeadforObjectDetection

9、DetectionasRegression:CertifiedObjectDetectionwithMedianSmoothing

Ping-yehChiang(UniversityofMaryland,CollegePark)·MichaelCurry(UniversityofMaryland)·AhmedAbdelkader(UniversityofMaryland,CollegePark)·AounonKumar(UniversityofMaryland,CollegePark)·JohnDickerson(UniversityofMaryland)·TomGoldstein(UniversityofMaryland)

10、RepPointsv2:VerificationMeetsRegressionforObjectDetection

YihongChen(PekingUniversity)·ZhengZhang(MSRA)·YueCao(MicrosoftResearch)·LiweiWang(PekingUniversity)·StephenLin(MicrosoftResearch)·HanHu(MicrosoftResearchAsia)

11、CoADNet:CollaborativeAggregation-and-DistributionNetworksforCo-SalientObjectDetection

QijianZhang(CityUniversityofHongKong)·RunminCong(BeijingJiaotongUniversity)·JunhuiHou(CityUniversityofHongKong,HongKong)·ChongyiLi(NanyangTechnologicalUniversity)·YaoZhao(BeijingJiaotongUniversity)

12、RestoringNegativeInformationinFew-ShotObjectDetection

1、VideoObjectSegmentationwithAdaptiveFeatureBankandUncertain-RegionRefinement

YongqingLiang(LouisianaStateUniversity)·XinLi(LouisianaStateUniversity)·NavidJafari(LouisianaStateUniversity)·JimChen(NortheasternUniversity)

2、MakeOne-ShotVideoObjectSegmentationEfficientAgain

TimMeinhardt(TUM)·LauraLeal-Taixé(TUM)

3、DelvingintotheCyclicMechanisminSemi-supervisedVideoObjectSegmentation

YuxiLi(ShanghaiJiaoTongUniversity)·JinlongPeng(TencentYoutuLab)·NingXu(AdobeResearch)·JohnSee(MultimediaUniversity)·WeiyaoLin(ShanghaiJiaoTonguniversity)

1、DeepVariationalInstanceSegmentation

JialinYuan(OregonStateUniversity)·ChaoChen(StonyBrookUniversity)·FuxinLi(OregonStateUniversity)

2、DFIS:DynamicandFastInstanceSegmentation

XinlongWang(UniversityofAdelaide)·RufengZhang(TongjiUniversity)·TaoKong(Bytedance)·LeiLi(ByteDanceAILab)·ChunhuaShen(UniversityofAdelaide)

1、ReinforcementLearningforControlwithMultipleFrequencies

JongminLee(KAIST)·ByungJunLee(KAIST)·Kee-EungKim(KAIST)

2、ReinforcementLearningwithGeneralValueFunctionApproximation:ProvablyEfficientApproachviaBoundedEluderDimension

RuosongWang(CarnegieMellonUniversity)·RussSalakhutdinov(CarnegieMellonUniversity)·LinYang(UCLA)

3、ReinforcementLearninginFactoredMDPs:Oracle-EfficientAlgorithmsandTighterRegretBoundsfortheNon-EpisodicSetting

ZipingXu(UniversityofMichigan)·AmbujTewari(UniversityofMichigan)

4、ReinforcementLearningwithFeedbackGraphs

ChristophDann(CarnegieMellonUniversity)·YishayMansour(Google)·MehryarMohri(CourantInst.ofMath.Sciences&GoogleResearch)·AyushSekhari(CornellUniversity)·KarthikSridharan(CornellUniversity)

5、ReinforcementLearningwithAugmentedData

MishaLaskin(UCBerkeley)·KiminLee(UCBerkeley)·AdamStooke(UCBerkeley)·LerrelPinto(NewYorkUniversity)·PieterAbbeel(UCBerkeley&covariant.ai)·AravindSrinivas(UCBerkeley)

6、ReinforcementLearningwithCombinatorialActions:AnApplicationtoVehicleRouting

ArthurDelarue(MIT)·RossAnderson(GoogleResearch)·ChristianTjandraatmadja(Google)

7、BreakingtheSampleSizeBarrierinModel-BasedReinforcementLearningwithaGenerativeModel

GenLi(TsinghuaUniversity)·YutingWei(CarnegieMellonUniversity)·YuejieChi(CMU)·YuantaoGu(TsinghuaUniversity)·YuxinChen(PrincetonUniversity)

8、AlmostOptimalModel-FreeReinforcementLearningviaReference-AdvantageDecomposition

ZihanZhang(TsinghuaUniversity)·YuanZhou(UIUC)·XiangyangJi(TsinghuaUniversity)

9、EffectiveDiversityinPopulationBasedReinforcementLearning

JackParker-Holder(UniversityofOxford)·AldoPacchiano(UCBerkeley)·KrzysztofMChoromanski(GoogleBrainRobotics)·StephenJRoberts(UniversityofOxford)

10、ABooleanTaskAlgebraforReinforcementLearning

GeraudNangueTasse(UniversityoftheWitwatersrand)·StevenJames(UniversityoftheWitwatersrand)·BenjaminRosman(UniversityoftheWitwatersrand/CSIR)

11、KnowledgeTransferinMulti-TaskDeepReinforcementLearningforContinuousControl

ZhiyuanXu(SyracuseUniversity)·KunWu(SyracuseUniversity)·ZhengpingChe(DiDiAILabs,DidiChuxing)·JianTang(DiDiAILabs,DiDiChuxing)·JiepingYe(DidiChuxing)

12、Multi-taskBatchReinforcementLearningwithMetricLearning

JiachenLi(UniversityofCalifornia,SanDiego)·QuanVuong(UniversityofCaliforniaSanDiego)·ShuangLiu(UniversityofCalifornia,SanDiego)·MinghuaLiu(UCSD)·KamilCiosek(Microsoft)·HenrikChristensen(UCSanDiego)·HaoSu(UCSD)

13、OntheStabilityandConvergenceofRobustAdversarialReinforcementLearning:ACaseStudyonLinearQuadraticSystems

KaiqingZhang(UniversityofIllinoisatUrbana-Champaign(UIUC))·BinHu(UniversityofIllinoisatUrbana-Champaign)·TamerBasar(UniversityofIllinoisatUrbana-Champaign)

14、TowardsPlayingFullMOBAGameswithDeepReinforcementLearning

DehengYe(Tencent)·GuibinChen(Tencent)·WenZhang(Tencent)·chensheng(qq)·BoYuan(Tencent)·BoLiu(Tencent)·JiaChen(Tencent)·HongshengYu(Tencent)·ZhaoLiu(Tencent)·FuhaoQiu(TencentAILab)·LiangWang(Tencent)·TengfeiShi(Tencent)·YinyutingYin(Tencent)·BeiShi(TencentAILab)·LanxiaoHuang(Tencent)·qiangfu(TencentAILab)·WeiYang(TencentAILab)·WeiLiu(TencentAILab)

15、PromotingCoordinationthroughPolicyRegularizationinMulti-AgentDeepReinforcementLearning

JulienRoy(Mila)·PaulBarde(QuebecAIinstitute-UbisoftLaForge)·FélixGHarvey(PolytechniqueMontréal)·DerekNowrouzezahrai(McGillUniversity)·ChrisPal(MILA,PolytechniqueMontréal,ElementAI)

16、Confounding-RobustPolicyEvaluationinInfinite-HorizonReinforcementLearning

NathanKallus(CornellUniversity)·AngelaZhou(CornellUniversity)

17、LearningRetrospectiveKnowledgewithReverseReinforcementLearning

ShangtongZhang(UniversityofOxford)·VivekVeeriah(UniversityofMichigan)·ShimonWhiteson(UniversityofOxford)

18、CombiningDeepReinforcementLearningandSearchforImperfect-InformationGames

NoamBrown(FacebookAIResearch)·AntonBakhtin(FacebookAIResearch)·AdamLerer(FacebookAIResearch)·QuchengGong(FacebookAIResearch)

19、POMO:PolicyOptimizationwithMultipleOptimaforReinforcementLearning

Yeong-DaeKwon(SamsungSDS)·JinhoChoo(SamsungSDS)·ByoungjipKim(SamsungSDS)·IljooYoon(SamsungSDS)·YoungjuneGwon(SamsungSDS)·SeungjaiMin(SamsungSDS)

20、Self-PacedDeepReinforcementLearning

21、EfficientModel-BasedReinforcementLearningthroughOptimisticPolicySearchandPlanning

SebastianCuri(ETHz)·FelixBerkenkamp(BoschCenterforArtificialIntelligence)·AndreasKrause(ETHZurich)

22、Weakly-SupervisedReinforcementLearningforControllableBehavior

LisaLee(CMU/GoogleBrain/Stanford)·BenEysenbach(CarnegieMellonUniversity)·RussSalakhutdinov(CarnegieMellonUniversity)·Shixiang(Shane)Gu(GoogleBrain)·ChelseaFinn(Stanford)

23、MOReL:Model-BasedOfflineReinforcementLearning

RahulKidambi(CornellUniversity)·AravindRajeswaran(UniversityofWashington)·PraneethNetrapalli(MicrosoftResearch)·ThorstenJoachims(Cornell)

24、SecurityAnalysisofSafeandSeldonianReinforcementLearningAlgorithms

PinarOzisik(UMassAmherst)·PhilipThomas(UniversityofMassachusettsAmherst)

25、Model-basedAdversarialMeta-ReinforcementLearning

ZichuanLin(TsinghuaUniversity)·GarrettW.Thomas(StanfordUniversity)·GuangwenYang(TsinghuaUniversity)·TengyuMa(StanfordUniversity)

26、SafeReinforcementLearningviaCurriculumInduction

MatteoTurchetta(ETHZurich)·AndreyKolobov(MicrosoftResearch)·ShitalShah(Microsoft)·AndreasKrause(ETHZurich)·AlekhAgarwal(MicrosoftResearch)

27、ConservativeQ-LearningforOfflineReinforcementLearning

AviralKumar(UCBerkeley)·AurickZhou(UniversityofCalifornia,Berkeley)·GeorgeTucker(GoogleBrain)·SergeyLevine(UCBerkeley)

28、MunchausenReinforcementLearning

NinoVieillard(GoogleBrain)·OlivierPietquin(GoogleResearchBrainTeam)·MatthieuGeist(GoogleBrain)

29、Non-CrossingQuantileRegressionforDistributionalReinforcementLearning

FanZhou(ShanghaiUniversityofFinanceandEconomics)·JianingWang(ShanghaiUniversityofFinanceandEconomics)·XingdongFeng(ShanghaiUniversityofFinanceandEconomics)

30、OnlineDecisionBasedVisualTrackingviaReinforcementLearning

keSong(Shandonguniversity)·WeiZhang(ShandongUniversity)·RanSong(SchoolofControlScienceandEngineering,ShandongUniversity)·YibinLi(ShandongUniversity)

31、DiscoveringReinforcementLearningAlgorithms

JunhyukOh(DeepMind)·MatteoHessel(GoogleDeepMind)·WojciechCzarnecki(DeepMind)·ZhongwenXu(DeepMind)·HadovanHasselt(DeepMind)·SatinderSingh(DeepMind)·DavidSilver(DeepMind)

32、SharedExperienceActor-CriticforMulti-AgentReinforcementLearning

FilipposChristianos(UniversityofEdinburgh)·LukasSchfer(UniversityofEdinburgh)·StefanoAlbrecht(UniversityofEdinburgh)

33、TheLoCARegret:AConsistentMetrictoEvaluateModel-BasedBehaviorinReinforcementLearning

HarmVanSeijen(MicrosoftResearch)·HadiNekoei(MILA)·EvanRacah(Mila,UniversitédeMontréal)·SarathChandar(Mila/écolePolytechniquedeMontréal)

34、LeveragetheAverage:anAnalysisofKLRegularizationinReinforcementLearning

NinoVieillard(GoogleBrain)·TadashiKozuno(OkinawaInstituteofScienceandTechnology)·BrunoScherrer(INRIA)·OlivierPietquin(GoogleResearchBrainTeam)·RemiMunos(DeepMind)·MatthieuGeist(GoogleBrain)

35、Task-agnosticExplorationinReinforcementLearning

XuezhouZhang(UW-Madison)·YuzheMa(UniversityofWisconsin-Madison)·AdishSingla(MPI-SWS)

36、GeneratingAdjacency-ConstrainedSubgoalsinHierarchicalReinforcementLearning

TianrenZhang(TsinghuaUniversity)·ShangqiGuo(TsinghuaUniversity)·TianTan(StanfordUniversity)·XiaolinHu(TsinghuaUniversity)·FengChen(TsinghuaUniversity)

37、StorageEfficientandDynamicFlexibleRuntimeChannelPruningviaDeepReinforcementLearning

JiandaChen(NanyangTechnologicalUniversity)·ShangyuChen(NanyangTechnologicalUniversity,Singapore)·SinnoJialinPan(NanyangTechnologicalUniversity,Singapore)

38、Multi-TaskReinforcementLearningwithSoftModularization

RuihanYang(UCSanDiego)·HuazheXu(UCBerkeley)·YIWU(UCBerkeley)·XiaolongWang(UCSD/UCBerkeley)

39、WeightedQMIX:ImprovingMonotonicValueFunctionFactorisationforDeepMulti-AgentReinforcementLearning

TabishRashid(UniversityofOxford)·GregoryFarquhar(UniversityofOxford)·BeiPeng(UniversityofOxford)·ShimonWhiteson(UniversityofOxford)

40、MDPHomomorphicNetworks:GroupSymmetriesinReinforcementLearning

ElisevanderPol(UniversityofAmsterdam)·DanielWorrall(UniversityofAmsterdam)·HerkevanHoof(UniversityofAmsterdam)·FransOliehoek(TUDelft)·MaxWelling(UniversityofAmsterdam/QualcommAIResearch)

41、OnEfficiencyinHierarchicalReinforcementLearning

ZhengWen(DeepMind)·DoinaPrecup(DeepMind)·MortezaIbrahimi(DeepMind)·AndreBarreto(DeepMind)·BenjaminVanRoy(StanfordUniversity)·SatinderSingh(DeepMind)

42、VariationalPolicyGradientMethodforReinforcementLearningwithGeneralUtilities

JunyuZhang(PrincetonUniversity)·AlecKoppel(U.S.ArmyResearchLaboratory)·AmritSinghBedi(USArmyResearchLaboratory)·CsabaSzepesvari(DeepMind/UniversityofAlberta)·MengdiWang(PrincetonUniversity)

43、Model-basedReinforcementLearningforSemi-MarkovDecisionProcesseswithNeuralODEs

JianzhunDu(HarvardUniversity)·JosephFutoma(HarvardUniversity)·FinaleDoshi-Velez(Harvard)

44、DisCor:CorrectiveFeedbackinReinforcementLearningviaDistributionCorrection

AviralKumar(UCBerkeley)·AbhishekGupta(UniversityofCalifornia,Berkeley)·SergeyLevine(UCBerkeley)

45、NeurosymbolicReinforcementLearningwithFormallyVerifiedExploration

GregAnderson(UniversityofTexasatAustin)·AbhinavVerma(RiceUniversity)·IsilDillig(UTAustin)·SwaratChaudhuri(TheUniversityofTexasatAustin)

46、GeneralizedHindsightforReinforcementLearning

AlexanderLi(UCBerkeley)·LerrelPinto(NewYorkUniversity)·PieterAbbeel(UCBerkeley&covariant.ai)

47、Meta-GradientReinforcementLearningwithanObjectiveDiscoveredOnline

ZhongwenXu(DeepMind)·HadovanHasselt(DeepMind)·MatteoHessel(GoogleDeepMind)·JunhyukOh(DeepMind)·SatinderSingh(DeepMind)·DavidSilver(DeepMind)

48、TorsionNet:AReinforcementLearningApproachtoSequentialConformerSearch

TarunGogineni(UniversityofMichigan)·ZipingXu(UniversityofMichigan)·ExequielPunzalan(UniversityofMichigan)·RunxuanJiang(UniversityofMichigan)·JoshuaKammeraad(UniversityofMichigan)·AmbujTewari(UniversityofMichigan)·PaulZimmerman(UniversityofMichigan)

49、LearningtoDispatchforJobShopSchedulingviaDeepReinforcementLearning

CongZhang(NanyangTechnologicalUniversity)·WenSong(InstituteofMarineScineceandTechnology,ShandongUniversity)·ZhiguangCao(NationalUniversityofSingapore)·JieZhang(NanyangTechnologicalUniversity)·PuaySiewTan(SIMTECH)·XuChi(SingaporeInstituteofManufacturingTechnology,A-Star)

50、IsPlug-inSolverSample-EfficientforFeature-basedReinforcementLearning

QiwenCui(PekingUniversity)·LinYang(UCLA)

51、Instance-basedGeneralizationinReinforcementLearning

MartinBertran(DukeUniversity)·NataliaLMartinez(DukeUniversity)·MarianoPhielipp(IntelAILabs)·GuillermoSapiro(DukeUniversity)

52、Preference-basedReinforcementLearningwithFinite-TimeGuarantees

YichongXu(CarnegieMellonUniversity)·RuosongWang(CarnegieMellonUniversity)·LinYang(UCLA)·AartiSingh(CMU)·ArturDubrawski(CarnegieMellonUniversity)

53、LearningtoDecode:ReinforcementLearningforDecodingofSparseGraph-BasedChannelCodes

SalmanHabib(NewJerseyInstituteofTech)·AllisonBeemer(NewJerseyInstituteofTechnology)·JoergKliewer(NewJerseyInstituteofTechnology)

54、BAIL:Best-ActionImitationLearningforBatchDeepReinforcementLearning

XinyueChen(NYUShanghai)·ZijianZhou(NYUShanghai)·ZhengWang(NYUShanghai)·CheWang(NewYorkUniversity)·YanqiuWu(NewYorkUniversity)·KeithRoss(NYUShanghai)

55、Task-AgnosticOnlineReinforcementLearningwithanInfiniteMixtureofGaussianProcesses

MengdiXu(CarnegieMellonUniversity)·WenhaoDing(CarnegieMellonUniversity)·JiachengZhu(CarnegieMellonUniversity)·ZUXINLIU(CarnegieMellonUniversity)·BaimingChen(TsinghuaUniversity)·DingZhao(CarnegieMellonUniversity)

56、OnReward-FreeReinforcementLearningwithLinearFunctionApproximation

RuosongWang(CarnegieMellonUniversity)·SimonDu(InstituteforAdvancedStudy)·LinYang(UCLA)·RussSalakhutdinov(CarnegieMellonUniversity)

57、Near-OptimalReinforcementLearningwithSelf-Play

YuBai(SalesforceResearch)·ChiJin(PrincetonUniversity)·TianchengYu(MIT)

58、RobustMulti-AgentReinforcementLearningwithModelUncertainty

KaiqingZhang(UniversityofIllinoisatUrbana-Champaign(UIUC))·TAOSUN(Amazon.com)·YunzheTao(AmazonArtificialIntelligence)·SahikaGenc(AmazonArtificialIntelligence)·SunilMallya(AmazonAWS)·TamerBasar(UniversityofIllinoisatUrbana-Champaign)

59、TowardsMinimaxOptimalReinforcementLearninginFactoredMarkovDecisionProcesses

YiTian(MIT)·JianQian(MIT)·SuvritSra(MIT)

60、ScalableMulti-AgentReinforcementLearningforNetworkedSystemswithAverageReward

GuannanQu(CaliforniaInstituteofTechnology)·YihengLin(CaliforniaInstituteofTechnology)·AdamWierman(CaliforniaInstituteofTechnology)·NaLi(HarvardUniversity)

61、Constrainedepisodicreinforcementlearninginconcave-convexandknapsacksettings

KiantéBrantley(TheUniversityofMarylandCollegePark)·MiroDudik(MicrosoftResearch)·ThodorisLykouris(MicrosoftResearchNYC)·SobhanMiryoosefi(PrincetonUniversity)·MaxSimchowitz(Berkeley)·AleksandrsSlivkins(MicrosoftResearch)·WenSun(MicrosoftResearchNYC)

62、SampleEfficientReinforcementLearningviaLow-RankMatrixEstimation

DevavratShah(MassachusettsInstituteofTechnology)·DogyoonSong(MassachusettsInstituteofTechnology)·ZhiXu(MIT)·YuzheYang(MIT)

63、Trajectory-wiseMultipleChoiceLearningforDynamicsGeneralizationinReinforcementLearning

YounggyoSeo(KAIST)·KiminLee(UCBerkeley)·IgnasiClaveraGilaberte(UCBerkeley)·ThanardKurutach(UniversityofCaliforniaBerkeley)·JinwooShin(KAIST)·PieterAbbeel(UCBerkeley&covariant.ai)

64、CooperativeHeterogeneousDeepReinforcementLearning

HanZheng(UTS)·PengfeiWei(NationalUniversityofSingapore)·JingJiang(UniversityofTechnologySydney)·GuodongLong(UniversityofTechnologySydney(UTS))·QinghuaLu(Data61,CSIRO)·ChengqiZhang(UniversityofTechnologySydney)

65、ImplicitDistributionalReinforcementLearning

YuguangYue(UniversityofTexasatAustin)·ZhendongWang(UniversityofTexas,Austin)·MingyuanZhou(UniversityofTexasatAustin)

66、EfficientExplorationofRewardFunctionsinInverseReinforcementLearningviaBayesianOptimization

SreejithBalakrishnan(NationalUniversityofSingapore)·QuocPhongNguyen(NationalUniversityofSingapore)·BryanKianHsiangLow(NationalUniversityofSingapore)·HaroldSoh(NationalUniversitySingapore)

67、EPOC:AProvablyCorrectPolicyGradientApproachtoReinforcementLearning

AlekhAgarwal(MicrosoftResearch)·MikaelHenaff(Microsoft)·ShamKakade(UniversityofWashington)·WenSun(MicrosoftResearchNYC)

68、ProvablyEfficientReinforcementLearningwithKernelandNeuralFunctionApproximations

ZhuoranYang(Princeton)·ChiJin(PrincetonUniversity)·ZhaoranWang(NorthwesternUniversity)·MengdiWang(PrincetonUniversity)·MichaelJordan(UCBerkeley)

69、DecoupledPolicyGradientMethodsforCompetitiveReinforcementLearning

ConstantinosDaskalakis(MIT)·DylanFoster(MIT)·NoahGolowich(MassachusettsInstituteofTechnology)

70、UpperConfidencePrimal-DualReinforcementLearningforCMDPwithAdversarialLoss

ShuangQiu(UniversityofMichigan)·XiaohanWei(UniversityofSouthernCalifornia)·ZhuoranYang(Princeton)·JiepingYe(UniversityofMichigan)·ZhaoranWang(NorthwesternUniversity)

71、ImprovingGeneralizationinReinforcementLearningwithMixtureRegularization

KAIXINWANG(NationalUniversityofSingapore)·BingyiKang(NationalUniversityofSingapore)·JieShao(FudanUniversity)·JiashiFeng(NationalUniversityofSingapore)

72、Agame-theoreticanalysisofnetworkedsystemcontrolforcommon-poolresourcemanagementusingmulti-agentreinforcementlearning

ArnuPretorius(InstaDeep)·ScottCameron(Instadeep)·ElanvanBiljon(StellenboschUniversity)·ThomasMakkink(InstaDeep)·ShahilMawjee(InstaDeep)·JeremyduPlessis(UniversityofCapeTown)·JonathanShock(UniversityofCapeTown)·AlexandreLaterre(InstaDeep)·KarimBeguir(InstaDeep)

73、DeepReinforcementLearningwithStackedHierarchicalAttentionforText-basedGames

74、RobustReinforcementLearningviaAdversarialtrainingwithLangevinDynamics

ParameswaranKamalaruban(EPFL)·Yu-TingHuang(EPFL)·Ya-PingHsieh(EPFL)·PaulRolland(EPFL)·ChengShi(UnversityofBasel)·VolkanCevher(EPFL)

75、Interferobot:aligninganopticalinterferometerbyareinforcementlearningagent

DmitrySorokin(RussianQuantumCenter)·AlexanderUlanov(RussianQuantumCenter)·EkaterinaSazhina(RussianQuantumCenter)·AlexanderLvovsky(OxfordUniversity)

76、Risk-SensitiveReinforcementLearning:Near-OptimalRisk-SampleTradeoffinRegret

YingjieFei(CornellUniversity)·ZhuoranYang(Princeton)·YudongChen(CornellUniversity)·ZhaoranWang(NorthwesternUniversity)·QiaominXie(CornellUniversity)

77、Expert-SupervisedReinforcementLearningforOfflinePolicyLearningandEvaluation

AaronSonabend(HarvardUniversity)·JunweiLu()·LeoAnthonyCeli(MassachusettsInstituteofTechnology)·TianxiCai(HarvardSchoolofPublicHealth)·PeterSzolovits(MIT)

78、Dynamicallocationoflimitedmemoryresourcesinreinforcementlearning

NisheetPatel(UniversityofGeneva)·LuigiAcerbi(UniversityofHelsinki)·AlexandrePouget(UniversityofGeneva)

79、AttendLight:UniversalAttention-BasedReinforcementLearningModelforTrafficSignalControl

80、Sample-EfficientReinforcementLearningofUndercompletePOMDPs

ChiJin(PrincetonUniversity)·ShamKakade(UniversityofWashington)·AkshayKrishnamurthy(Microsoft)·QinghuaLiu(PrincetonUniversity)

81、RLUnplugged:ACollectionofBenchmarksforOfflineReinforcementLearning

ZiyuWang(Deepmind)·CaglarGulcehre(Deepmind)·AlexanderNovikov(DeepMind)·ThomasPaine(DeepMind)·SergioGómez(DeepMind)·KonradZolna(DeepMind)·RishabhAgarwal(GoogleResearch,BrainTeam)·JoshMerel(DeepMind)·DanielMankowitz(DeepMind)·CosminPaduraru(DeepMind)·GabrielDulac-Arnold(GoogleResearch)·JerryLi(Google)·MohammadNorouzi(GoogleBrain)·MatthewHoffman(DeepMind)·NicolasHeess(GoogleDeepMind)·NandodeFreitas(DeepMind)

82、Alocaltemporaldifferencecodefordistributionalreinforcementlearning

PabloTano(UniversityofGeneva)·PeterDayan(MaxPlanckInstituteforBiologicalCybernetics)·AlexandrePouget(UniversityofGeneva)

83、TheValueEquivalencePrincipleforModel-BasedReinforcementLearning

ChristopherGrimm(UniversityofMichigan)·AndreBarreto(DeepMind)·SatinderSingh(DeepMind)·DavidSilver(DeepMind)

84、SteadyStateAnalysisofEpisodicReinforcementLearning

HuangBojun(RakutenInstituteofTechnology)

85、Information-theoreticTaskSelectionforMeta-ReinforcementLearning

RicardoLunaGutierrez(UniversityofLeeds)·MatteoLeonetti(UniversityofLeeds)

86、AUnifyingViewofOptimisminEpisodicReinforcementLearning

GergelyNeu(UniversitatPompeuFabra)·CiaraPike-Burke(ImperialCollegeLondon)

87、AcceleratingReinforcementLearningthroughGPUAtariEmulation

StevenDalton(Nvidia)·iurifrosio(nvidia)

88、RobustDeepReinforcementLearningagainstAdversarialPerturbationsonStateObservations

HuanZhang(UCLA)·HonggeChen(MIT)·ChaoweiXiao(UniversityofMichigan,AnnArbor)·BoLi(UIUC)·mingyanliu(universityofMichigan,AnnArbor)·DuaneBoning(MassachusettsInstituteofTechnology)·Cho-JuiHsieh(UCLA)

89、BridgingImaginationandRealityforModel-BasedDeepReinforcementLearning

GuangxiangZhu(Tsinghuauniversity)·MinghaoZhang(TsinghuaUniversity)·HonglakLee(Google/U.Michigan)·ChongjieZhang(TsinghuaUniversity)

90、AdaptiveDiscretizationforModel-BasedReinforcementLearning

SeanSinclair(CornellUniversity)·TianyuWang(DukeUniversity)·GauriJain(CornellUniversity)·SiddharthaBanerjee(CornellUniversity)·ChristinaYu(CornellUniversity)

91、ProvablyGoodBatchOff-PolicyReinforcementLearningWithoutGreatExploration

YaoLiu(StanfordUniversity)·AdithSwaminathan(MicrosoftResearch)·AlekhAgarwal(MicrosoftResearch)·EmmaBrunskill(StanfordUniversity)

92、Provablyadaptivereinforcementlearninginmetricspaces

TongyiCao(UniversityofMassachusettsAmherst)·AkshayKrishnamurthy(Microsoft)

93、StochasticLatentActor-Critic:DeepReinforcementLearningwithaLatentVariableModel

AlexLee(UCBerkeley)·AnushaNagabandi(UCBerkeley)·PieterAbbeel(UCBerkeley&covariant.ai)·SergeyLevine(UCBerkeley)

94、InverseReinforcementLearningfromaGradient-basedLearner

GiorgiaRamponi(PolitecnicodiMilano)·GianlucaDrappo(PolitecnicodiMilano)·MarcelloRestelli(PolitecnicodiMilano)

1、BlockGAN:Learning3DObject-awareSceneRepresentationsfromUnlabelledImages

ThuNguyen-Phuoc(UniversityofBath)·ChristianRichardt(UniversityofBath)·LongMai(AdobeResearch)·YongliangYang(UniversityofBath)·NiloyMitra(UniversityCollegeLondon)

2、TaylorGAN:Neighbor-AugmentedPolicyUpdateTowardsSample-EfficientNaturalLanguageGeneration

Chun-HsingLin(NationalTaiwanUniversity)·Siang-RueiWu(NationalTaiwanUniversity)·Hung-yiLee(NationalTaiwanUniversity)·Yun-NungChen(NationalTaiwanUniversity)

3、CircleGAN:GenerativeAdversarialLearningacrossSphericalCircles

WoohyeonShim(Postech)·MinsuCho(POSTECH)

4、COT-GAN:GeneratingSequentialDataviaCausalOptimalTransport

TianlinXu(LondonSchoolofEconomicsandPoliticalScience)·WenliangLe(GatsbyUnit,UCL)·MichaelMunn(Google)·BeatriceAcciaio(LondonSchoolofEconomics)

5、HiFi-GAN:GenerativeAdversarialNetworksforEfficientandHighFidelitySpeechSynthesis

6、GramGAN:Deep3DTextureSynthesisFrom2DExemplars

TizianoPortenier(ETHZurich)·SiavashArjomandBigdeli(CSEM)·OrcunGoksel(ETHZurich)

7、ColdGANs:TamingLanguageGANswithCautiousSamplingStrategies

ThomasScialom(reciTAL)·Paul-AlexisDray(reciTAL)·SylvainLamprier(LIP6-UPMC)·BenjaminPiwowarski(LIP6,UPMC/CNRS,Paris,France)·JacopoStaiano(reciTAL)

8、PlanGAN:Model-basedPlanningWithSparseRewardsandMultipleGoals

HenryCharlesworth(UniversityofWarwick)·GiovanniMontana(UniversityofWarwick)

JungilKong(KakaoEnterprise)·JaehyeonKim(KakaoEnterprise)·JaekyoungBae(KakaoEnterprise)

9、GS-WGAN:AGradient-SanitizedApproachforLearningDifferentiallyPrivateGenerators

DingfanChen(CISPA-HelmholtzCenterforInformationSecurity)·TribhuvaneshOrekondy(MaxPlanckInstituteforInformatics)·MarioFritz(CISPAHelmholtzCenteri.G.)

10、GANSpace:DiscoveringInterpretableGANControls

ErikHrknen(AaltoUniversity)·AaronHertzmann(Adobe)·JaakkoLehtinen(AaltoUniversity&NVIDIA)·SylvainParis(Adobe)

11、GANMemorywithNoForgetting

ChunyuanLi(MicrosoftResearch)·MiaoyunZhao(UNC)·JianqiaoLi(DukeUniversity)·SijiaWang(DukeUniversity)·LawrenceCarin(DukeUniversity)

12、ImprovingGANTrainingwithProbabilityRatioClippingandSampleReweighting

YueWu(CarnegieMellonUniversity)·PanZhou(NationalUniversityofSingapore)·AndrewGordonWilson(NewYorkUniversity)·EricXing(PetuumInc./CarnegieMellonUniversity)·ZhitingHu(CarnegieMellonUniversity)

13、InstanceSelectionforGANs

TerranceDeVries(UniversityofGuelph)·MichalDrozdzal(FAIR)·GrahamWTaylor(UniversityofGuelph)

14、DistributionalRobustnesswithIPMsandlinkstoRegularizationandGANs

HishamHusain(TheAustralianNationalUniversity&Data61)

15、HierarchicalPatchVAE-GAN:GeneratingDiverseVideosfromaSingleSample

ShirGur(TelAvivUniversity)·SagieBenaim(TelAvivUniversity)·LiorWolf(FacebookAIResearch)

16、YourGANisSecretlyanEnergy-basedModelandYouShouldUseDiscriminatorDrivenLatentSampling

TongChe(MILA)·RuixiangZHANG(Mila/UdeM)·JaschaSohl-Dickstein(GoogleBrain)·HugoLarochelle(GoogleBrain)·LiamPaull(UniversitédeMontréal)·YuanCao(GoogleBrain)·YoshuaBengio(Mila/U.Montreal)

17、TeachingaGANWhatNottoLearn

SiddarthAsokan(IndianInstituteofScience)·ChandraSeelamantula(IIScBangalore)

18、Top-kTrainingofGANs:ImprovingGANPerformancebyThrowingAwayBadSamples

SamarthSinha(UniversityofToronto,VectorInstitute)·ZhengliZhao(UCI,GoogleBrain)·AnirudhGoyalALIASPARTHGOYAL(UniversitédeMontréal)·ColinARaffel(GoogleBrain)·AugustusOdena(GoogleBrain)

19、DifferentiableAugmentationforData-EfficientGANTraining

ShengyuZhao(TsinghuaUniversity)·ZhijianLiu(MIT)·JiLin(MIT)·Jun-YanZhu(MIT)·SongHan(MIT)

20、DeepI2I:EnablingDeepHierarchicalImage-to-ImageTranslationbyTransferringfromGANs

yaxingwang(CentredeVisióperComputador(CVC))·LuYu(computervisioncenter,UAB)·JoostvandeWeijer(ComputerVisionCenterBarcelona)

21、ReconstructingPerceptiveImagesfromBrainActivitybyShape-SemanticGAN

TaoFang(ZhejiangUniversity)·YuQi(ZhejiangUniversity)·GangPan(ZhejiangUniversity

1、UnsupervisedLearningofDenseVisualRepresentations

PedroO.Pinheiro(ElementAI)·AmjadAlmahairi(ElementAI)·RyanBenmalek(CornellUniversity)·FlorianGolemo(MILA/ElementAI)·AaronCourville(U.Montreal)

2、UnsupervisedLearningofVisualFeaturesbyContrastingClusterAssignments

MathildeCaron(INRIA/FAIR)·IshanMisra(FacebookAIResearch)·JulienMairal(Inria)·PriyaGoyal(FacebookAIResearch)·PiotrBojanowski(Facebook)·ArmandJoulin(FacebookAIresearch)

3、UnsupervisedLearningofObjectLandmarksviaSelf-TrainingCorrespondence

DimitriosMallis(ComputerVisionLaboratory-UniversityofNottingham)·EnriqueSanchez(SamsungAICentre)·MatthewBell(UniversityofNottingham)·GeorgiosTzimiropoulos(QueenMaryUniversityofLondon)

YaofengDesmondZhong(PrincetonUniversity)·NaomiLeonard(PrincetonUniversity)

5、ErdosGoesNeural:anUnsupervisedLearningFrameworkforCombinatorialOptimizationonGraphs

NikolaosKaralias(EPFL)·AndreasLoukas(EPFL)

6、ProvablyEfficientExplorationforRLwithUnsupervisedLearning

FeiFeng(UniversityofCalifornia,LosAngeles)·RuosongWang(CarnegieMellonUniversity)·WotaoYin(AlibabaUS,DAMOAcademy)·SimonDu(InstituteforAdvancedStudy)·LinYang(UCLA

1、Self-supervisedlearningthroughtheeyesofachild

EminOrhan(NewYorkUniversity)·VaibhavGupta(NewYorkUniversity)·BrendenLake(NewYorkUniversity)

2、Self-SupervisedLearningbyCross-ModalAudio-VideoClustering

HumamAlwassel(KAUST)·DhruvMahajan(Facebook)·BrunoKorbar(Facebook)·LorenzoTorresani(FacebookAI)·BernardGhanem(KAUST)·DuTran(FacebookAI)

3、DemystifyingContrastiveSelf-SupervisedLearning:Invariances,AugmentationsandDatasetBiases

SenthilPurushwalkamShivaPrakash(CarnegieMellonUniversity)·AbhinavGupta(FacebookAIResearch/CMU)

4、LoopReg:Self-supervisedLearningofImplicitSurfaceCorrespondences,PoseandShapefor3DHumanMeshRegistration

BharatBhatnagar(MPI-INF)·CristianSminchisescu(GoogleResearch)·ChristianTheobalt(MPIInformatik)·GerardPons-Moll(MPII,Germany)

5、Patch2Self:DenoisingDiffusionMRIwithSelf-SupervisedLearning

ShreyasFadnavis(IndianaUniversityBloomington)·JoshuaBatson(CZBiohub)·EleftheriosGaryfallidis(IndianaUniversity)

6、BootstrapYourOwnLatent-ANewApproachtoSelf-SupervisedLearning

Jean-BastienGrill(DeepMind)·FlorianStrub(DeepMind)·FlorentAltché(DeepMind)·CorentinTallec(Deepmind)·PierreRichemond(ImperialCollege)·ElenaBuchatskaya(DeepMind)·CarlDoersch(DeepMind)·BernardoAvilaPires(DeepMind)·ZhaohanGuo(DeepMind)·MohammadGheshlaghiAzar(DeepMind)·BilalPiot(DeepMind)·koraykavukcuoglu(DeepMind)·RemiMunos(DeepMind)·MichalValko(DeepMind)

7、CompReSS:CompressingRepresentationsforSelf-SupervisedLearning

SoroushAbbasiKoohpayegani(UniversityofMarylandBaltimoreCounty)·AjinkyaTejankar(UniversityofMarylandBaltimoreCounty)·HamedPirsiavash(UniversityofMaryland,BaltimoreCounty)

8、wav2vec2.0:AFrameworkforSelf-SupervisedLearningofSpeechRepresentations

AlexeiBaevski(FacebookAIResearch)·YuhaoZhou(UniversityofToronto)·Abdel-rahmanMohamed(FacebookAIResearch(FAIR))·MichaelAuli(FacebookAIResearch

1、Semi-SupervisedNeuralArchitectureSearch

RenqianLuo(UniversityofScienceandTechnologyofChina)·XuTan(MicrosoftResearch)·RuiWang(MicrosoftResearchAsia)·TaoQin(MicrosoftResearch)·EnhongChen

2、Semi-SupervisedPartialLabelLearningviaConfidence-RatedMarginMaximization

WeiWang(SoutheastUniversity)·Min-LingZhang(SoutheastUniversity)

3、UnsupervisedSemanticAggregationandDeformableTemplateMatchingforSemi-SupervisedLearning

QiWang(NorthwesternPolytechnicalUniversity)·TaoHan(NorthwesternPolytechnicalUniversity)·JunyuGao(NorthwesternPolytechnicalUniversity,CenterforOPTicalIMageryAnalysisandLearning)·YuanYuan(NorthwesternPolytechnicalUniversity)

4、FixMatch:SimplifyingSemi-SupervisedLearningwithConsistencyandConfidence

KihyukSohn(NECLaboratoriesAmerica)·DavidBerthelot(GoogleBrain)·NicholasCarlini(Google)·ZizhaoZhang(Google)·HanZhang(Google)·ColinARaffel(GoogleBrain)·EkinDogusCubuk(GoogleBrain)·AlexeyKurakin(GoogleBrain)·Chun-LiangLi(Google)

5、NotAllUnlabeledDataareEqual:LearningtoWeightDatainSemi-supervisedLearning

ZhongzhengRen(UIUC)·RaymondYeh(UniversityofIllinoisatUrbana–Champaign)·AlexanderSchwing(UniversityofIllinoisatUrbana-Champaign)

6、VIME:ExtendingtheSuccessofSelf-andSemi-supervisedLearningtoTabularDomain

JinsungYoon(UniversityofCalifornia,LosAngeles)·YaoZhang(UniversityofCambridge)·JamesJordon(UniversityofOxford)·MihaelavanderSchaar(UniversityofCambridge)

7、DelvingintotheCyclicMechanisminSemi-supervisedVideoObjectSegmentation

(UniversityofScienceandTechnologyofChina)·Tie-YanLiu(MicrosoftResearchAsia)

8、GraphStochasticNeuralNetworksforSemi-supervisedLearning

HaiboWang(TsinghuaUniversity)·ChuanZhou(ChineseAcademyofSciences)·XinChen(InstituteforNetworkSciencesandCyberspace,TsinghuaUniversity)·JiaWu(MacquarieUniversity)·ShiruiPan(MonashUniversity)·JilongWang(TsinghuaUniversity)

9、GraphRandomNeuralNetworksforSemi-SupervisedLearningonGraphs

WenzhengFeng(TsinghuaUniversity)·JieZhang(WebankCo.,Ltd)·YuxiaoDong(Microsoft)·YuHan(TsinghuaUniversity)·HuanboLuan(TsinghuaUniversity)·QianXu(WeBank)·QiangYang(WeBankandHKUST)·EvgenyKharlamov(BoschCenterforArtificialIntelligence)·JieTang(TsinghuaUniversity)

10、Stronglylocalp-norm-cutalgorithmsforsemi-supervisedlearningandlocalgraphclustering

MengLiu(PurdueUniversity)·DavidGleich(PurdueUniversity)

11、UncertaintyAwareSemi-SupervisedLearningonGraphData

XujiangZhao(TheUniversityofTexasatDallas)·FengChen(UTDallas)·ShuHu(UniversityatBuffalo,StateUniversityofNewYork)·Jin-HeeCho(VirginiaTech)

12、DistributionAligningRefineryofPseudo-labelforImbalancedSemi-supervisedLearning

JaehyungKim(KAIST)·YoungbumHur(SamsungAdvancedInstituteofTechnology)·SejunPark(KAIST)·EunhoYang(KoreaAdvancedInstituteofScienceandTechnology;AItrics)·SungJuHwang(KAIST,AITRICS)·JinwooShin(KAIST)

13、DeepGraphPose:asemi-superviseddeepgraphicalmodelforimprovedanimalposetracking

AnqiWu()·E.KellyBuchanan(ColumbiaUniversity)·MatthewWhiteway(ColumbiaUniversity)·MichaelSchartner(UniversityofGeneva)·GuidoMeijer(ChampalimaudCenterfortheUnknown)·Jean-PaulNoel(NewYorkUniversity)·EricaRodriguez(ColumbiaUniversity)·ClaireEverett(ColumbiaUniversity)·AmyNorovich(ColumbiaUniversity)·EvanSchaffer(ColumbiaUniversity)·NeeliMishra(ColumbiaUniversity)·C.DanielSalzman(ColumbiaUniversity)·DoraAngelaki(NewYorkUniversity)·AndrésBendesky(ColumbiaUniversity)·TheInternationalBrainLaboratoryTheInternationalBrainLaboratory(TheInternationalBrainLaboratory)·JohnCunningham(UniversityofColumbia)·LiamPaninski(ColumbiaUniversity)

14、TheUnreasonableEffectivenessofBigModelsforSemi-SupervisedLearning

TingChen(Google)·SimonKornblith(GoogleBrain)·KevinSwersky(Google)·MohammadNorouzi(GoogleBrain)·GeoffreyEHinton(Google&UniversityofToronto)

1、TransferLearningvia1Regularization

MasaakiTakada(ToshibaCorporation)·HironoriFujisawa(TheInstituteofStatisticalMathematics)

2、TinyTransferLearning:TowardsMemory-EfficientOn-DeviceLearning

HanCai(MassachusettsInstituteofTechnology)·ChuangGan(MIT-IBMWatsonAILab)·LigengZhu(MIT)·SongHan(MIT)

3、Co-TuningforTransferLearning

KaichaoYou(TsinghuaUniversity)·ZhiKou(TsinghuaUniversity)·MingshengLong(TsinghuaUniversity)·JianminWang(TsinghuaUniversity)

4、SharedSpaceTransferLearningforanalyzingmulti-sitefMRIdata

MuhammadYousefnezhad(UniversityofAlberta)·AlessandroSelvitella(PurdueUniversityFortWayne)·DaoqiangZhang(NanjingUniversityofAeronauticsandAstronautics)·AndrewGreenshaw(UniversityofAlberta)·RussellGreiner(UniversityofAlberta)

5、OntheTheoryofTransferLearning:TheImportanceofTaskDiversity

NileshTripuraneni(UCBerkeley)·MichaelJordan(UCBerkeley)·ChiJin(PrincetonUniversity)

6、HierarchicalGranularityTransferLearning

ShaoboMin(USTC)·HongtaoXie(UniversityofScienceandTechnologyofChina)·HantaoYao(InstituteofAutomation,ChineseAcademyofSciences)·XuranDeng(UniversityofScienceandTechnologyofChina)·Zheng-JunZha(UniversityofScienceandTechnologyofChina)·YongdongZhang(UniversityofScienceandTechnologyofChina)

7、Whatisbeingtransferredintransferlearning

BehnamNeyshabur(Google)·HanieSedghi(GoogleBrain)·ChiyuanZhang(GoogleBrain)

8、MinimaxLowerBoundsforTransferLearningwithLinearandOne-hiddenLayerNeuralNetworks

MirMohammadrezaMousaviKalan(UniversityofSouthernCalifornia)·ZalanFabian(UniversityofSouthernCalifornia)·SalmanAvestimehr(UniversityofSouthernCalifornia)·MahdiSoltanolkotabi(UniversityofSoutherncalifornia)

9、ACombinatorialPerspectiveonTransferLearning

JiananWang(DeepMind)·ErenSezener(DeepMind)·DavidBudden(DeepMind)·MarcusHutter(DeepMind)·JoelVeness(Deepmind)

1、ExemplarGuidedActiveLearning

JasonHartford(UniversityofBritishColumbia)·KevinLeyton-Brown(UniversityofBritishColumbia)·HadasRaviv(AI21Labs)·DanPadnos(AI21Labs)·ShaharLev(AI21Labs)·BarakLenz(AI21Labs)

2、FindingtheHomologyofDecisionBoundarieswithActiveLearning

WeizhiLi(ArizonaStateUniversity)·GautamDasarathy(ArizonaStateUniversity)·KarthikeyanNatesanRamamurthy(IBMResearch)·VisarBerisha(ArizonaStateUniversity)

3、Efficientactivelearningofsparsehalfspaceswitharbitraryboundednoise

ChichengZhang(UniversityofArizona)·JieShen(StevensInstituteofTechnology)·PranjalAwasthi(RutgersUniversity/Google)

4、GraphPolicyNetworkforTransferableActiveLearningonGraphs

ShengdingHu(TsinghuaUniversity)·ZhengXiong(TsinghuaUniversity/UniversityofOxford)·MengQu(Mila)·XingdiYuan(MicrosoftResearch)·Marc-AlexandreCté(MicrosoftResearch)·ZhiyuanLiu(TsinghuaUniversity)·JianTang(Mila)

1、Meta-LearningthroughHebbianPlasticityinRandomNetworks

EliasNajarro(ITUniversityofCopenhagen)·SebastianRisi(ITUniversityofCopenhagen)

2、Meta-learningfromTaskswithHeterogeneousAttributeSpaces

TomoharuIwata(NTT)·AtsutoshiKumagai(NTTSoftwareInnovationCenter)

3、Meta-LearningStationaryStochasticProcessPredictionwithConvolutionalNeuralProcesses

4、Meta-LearningRequiresMeta-Augmentation

JanarthananRajendran(UniversityofMichigan)·AlexanderIrpan(GoogleBrain)·EricJang(GoogleBrain)

5、Ameta-learningapproachto(re)discoverplasticityrulesthatcarveadesiredfunctiontoaneuralnetwork

BasileConfavreux(UniversityofOxford)·FriedemannZenke(FriedrichMiescherInstitute)·EvertonAgnes(UniversityofOxford)·TimothyLillicrap(DeepMind&UCL)·TimVogels(InstituteofScienceandTechnology)

6、RobustMeta-learningforMixedLinearRegressionwithSmallBatches

WeihaoKong(StanfordUniversity)·RaghavSomani(UniversityofWashington)·ShamKakade(UniversityofWashington)·SewoongOh(UniversityofWashington)

7、ModularMeta-LearningwithShrinkage

YutianChen(DeepMind)·AbramFriesen(DeepMind)·FeryalBehbahani(DeepMind)·ArnaudDoucet(GoogleDeepMind)·DavidBudden(DeepMind)·MatthewHoffman(DeepMind)·NandodeFreitas(DeepMind)

8、BayesianMeta-LearningfortheFew-ShotSettingviaDeepKernels

9、MetaSDF:Meta-LearningSignedDistanceFunctions

VincentSitzmann(StanfordUniversity)·EricChan(StanfordUniversity)·RichardTucker(Google)·NoahSnavely(CornellUniversityandGoogleAI)·GordonWetzstein(StanfordUniversity)

10、OOD-MAML:Meta-LearningforFew-ShotOut-of-DistributionDetectionandClassification

TaewonJeong(KAIST)·HeeyoungKim(KAIST)

11、SubmodularMeta-Learning

ArmanAdibi(UniversityofPennsylvania)·AryanMokhtari(UTAustin)·HamedHassani(UPenn)

12、ContinuousMeta-LearningwithoutTasks

JamesHarrison(StanfordUniversity)·ApoorvaSharma(StanfordUniversity)·ChelseaFinn(Stanford)·MarcoPavone(StanfordUniversity)

AndrewFoong(UniversityofCambridge)·WesselBruinsma(InveniaLabsandUniversityofCambridge)·JonathanGordon(UniversityofCambridge)·YannDubois(FacebookAIResearch)·JamesRequeima(UniversityofCambridge/InveniaLabs)·RichardETurner(UniversityofCambridge)

13、OnlineStructuredMeta-learning

HuaxiuYao(PennsylvaniaStateUniversity)·YingboZhou(SalesforceResearch)·MehrdadMahdavi(PennsylvaniaStateUniversity)·Zhenhui(Jessie)Li(PennStateUniversity)·RichardSocher(Salesforce)·CaimingXiong(Salesforce)

14、ProbabilisticActiveMeta-Learning

JeanKaddour(ImperialCollegeLondon)·SteindorSaemundsson(ImperialCollegeLondon)·MarcDeisenroth(UniversityCollegeLondon)

15、Gradient-EMBayesianMeta-Learning

YayiZou(DidiResearchAmerica)·XiaoqiLu(ColumbiaUniversity)

16、Task-RobustModel-AgnosticMeta-Learning

LiamCollins(UniversityofTexasatAustin)·AryanMokhtari(UTAustin)·SanjayShakkottai(UniversityofTexasatAustin)

17、StructuredPredictionforConditionalMeta-Learning

RuohanWang(ImperialCollegeLondon)·YiannisDemiris(ImperialCollegeLondon)·CarloCiliberto(ImperialCollegeLondon)

18、ModelingandOptimizationTrade-offinMeta-learning

KatelynGao(IntelLabs)·OzanSener(IntelLabs)

19、AdversariallyRobustFew-ShotLearning:AMeta-LearningApproach

MicahGoldblum(UniversityofMaryland)·LiamFowl(UniversityofMaryland)·TomGoldstein(UniversityofMaryland)

20、ACloserLookattheTrainingStrategyforModernMeta-Learning

JIAXINCHEN(TheHongKongPolytechnicUniversity)·Xiao-MingWu(TheHongKongPolytechnicUniversity)·YankeLi(ETHZurich)·QimaiLI(TheHongKongPolyU)·Li-MingZhan(TheHongKongPolytechnicUniversity)·Fu-laiChung(TheHongKongPolytechnicUniversity)

21、ConvergenceofMeta-LearningwithTask-SpecificAdaptationoverPartialParameters

KaiyiJi(TheOhioStateUniversity)·JasonLee(PrincetonUniversity)·YingbinLiang(TheOhioStateUniversity)·H.VincentPoor(PrincetonUniversity)

22、TheAdvantageofConditionalMeta-LearningforBiasedRegularizationandFineTuning

GiuliaDenevi(IIT&UNIGE)·MassimilianoPontil(IIT&UCL)·CarloCiliberto(ImperialCollegeLondon)

23、PersonalizedFederatedLearningwithTheoreticalGuarantees:AModel-AgnosticMeta-LearningApproach

AlirezaFallah(MIT)·AryanMokhtari(UTAustin)·AsumanOzdaglar(MassachusettsInstituteofTechnology

1、RobustFederatedLearning:TheCaseofAffineDistributionShifts

AmirhosseinReisizadeh(UCSantaBarbara)·FarzanFarnia(StanfordUniversity)·RamtinPedarsani(UCSantaBarbara)·AliJadbabaie(MIT)

2、PersonalizedFederatedLearningwithMoreauEnvelopes

CanhT.Dinh(TheUniversityofSydney)·NguyenH.Tran(TheUniversityofSydney)·TuanDungNguyen(TheUniversityofMelbourne)

3、PersonalizedFederatedLearningwithTheoreticalGuarantees:AModel-AgnosticMeta-LearningApproach

AlirezaFallah(MIT)·AryanMokhtari(UTAustin)·AsumanOzdaglar(MassachusettsInstituteofTechnology)

4、AnEfficientFrameworkforClusteredFederatedLearning

AvishekGhosh(UniversityofCalifornia,Berkeley)·JichanChung(UniversityofCalifornia,Berkeley)·DongYin(DeepMind)·KannanRamchandran(UCBerkeley)

5、OptimalTopologyDesignforCross-SiloFederatedLearning

OthmaneMARFOQ(Inria/Accenture)·CHUANXU(InriaSophiaAntipolis)·

GiovanniNeglia(Inria)·RichardVidal(Accenture)

6、EnsembleDistillationforRobustModelFusioninFederatedLearning

TaoLin(EPFL)·LingjingKong(EPFL)·SebastianUStich(EPFL)·

MartinJaggi(EPFL)

7、AttackoftheTails:Yes,YouReallyCanBackdoorFederatedLearning

HongyiWang(UniversityofWisconsin-Madison)·KartikSreenivasan(UniversityofWisconsin-Madison)·ShashankRajput(UniversityofWisconsin-Madison)·HaritVishwakarma(UniversityofWisconsinMadison)·Jy-yongSohn(KAIST)·SaurabhAgarwal(UW-Madison)·KangwookLee(UWMadison)·DimitrisPapailiopoulos(UniversityofWisconsin-Madison)

8、InvertingGradients-Howeasyisittobreakprivacyinfederatedlearning

JonasGeiping(UniversityofSiegen)·HartmutBauermeister(UniversityofSiegen)·HannahDrge(UniversityofSiegen)·MichaelMoeller(UniversityofSiegen)

9、LowerBoundsandOptimalAlgorithmsforPersonalizedFederatedLearning

FilipHanzely(KAUST)·SlavomírHanzely(KAUST)·SamuelHorváth(KingAbdullahUniversityofScienceandTechnology)·PeterRichtarik(KAUST)

1、MultimodalGraphNetworksforCompositionalGeneralizationinVisualQuestionAnswering

RaeidSaqur(PrincetonUniversity)·KarthikNarasimhan(PrincetonUniversity)

2、MultimodalGenerativeLearningUtilizingJensen-Shannon-Divergence

ThomasMSutter(ETHZurich)·ImantDaunhawer(ETHZurich)·JuliaVogt(ETHZurich)

3、DeepMultimodalFusionbyChannelExchanging

YikaiWang(TsinghuaUniversity)·WenbingHuang(TsinghuaUniversity)·FuchunSun(Tsinghua)·TingyangXu(TencentAILab)·YuRong(TencentAILab)·JunzhouHuang(UniversityofTexasatArlington/TencentAILab)

4、Self-SupervisedMultiModalVersatileNetworks

Jean-BaptisteAlayrac(Deepmind)·AdriaRecasens(DeepMind)·RosaliaSchneider(DeepMind)·ReljaArandjelovi(DeepMind)·JasonRamapuram(UniversityofGeneva)·JeffreyDeFauw(DeepMind)·LucasSmaira(DeepMind)·SanderDieleman(DeepMind)·AndrewZisserman(DeepMind&UniversityofOxford)

5、CoMIR:ContrastiveMultimodalImageRepresentationforRegistration

NicolasPielawski(UppsalaUniversity)·ElisabethWetzer(CentreforImageAnalysis,DepartmentofInformationTechnology,UppsalaUniversity,Sweden)·Johanfverstedt(DepartmentofInformationTechnology,UppsalaUniversity)·JiahaoLu(UppsalaUniversity)·CarolinaWhlby(UppsalaUniversity)·JoakimLindblad(CentreforImageAnalysis,DepartmentofInformationTechnology,UppsalaUniversity,Sweden)·NatasaSladoje(CentreforImageAnalysis,DepartmentofInformationTechnology,UppsalaUniversity,Sweden)

6、EvidentialSparsificationofMultimodalLatentSpacesinConditionalVariationalAutoencoders

MashaItkina(StanfordUniversity)·BorisIvanovic(StanfordUniversity)·RansaluSenanayake(StanfordUniversity)·MykelJKochenderfer(StanfordUniversity)·MarcoPavone(StanfordUniversity)

7、TheHatefulMemesChallenge:DetectingHateSpeechinMultimodalMemes

DouweKiela(FacebookAIResearch)·HamedFirooz(Facebook)·AravindMohan(Facebook)·VedanujGoswami(Facebook)·AmanpreetSingh(Facebook)·PratikRingshia(Facebook)·DavideTestuggine(Facebook

1、MakeOne-ShotVideoObjectSegmentationEfficientAgain

2、AdversarialStyleMiningforOne-ShotUnsupervisedDomainAdaptation

YaweiLuo(ZhejiangUniversity)·PingLiu(UTS)·TaoGuan(HuazhongUniversityofScienceandTechnology)·JunqingYu(HuazhongUniversityofScience&Technology)·YiYang(UTS)

3、BridgingtheGapbetweenSample-basedandOne-shotNeuralArchitectureSearchwithBONAS

4、EfficientNonmyopicBayesianOptimizationviaOne-ShotMulti-StepTrees

ShaliJiang(WashingtonUniversityinSt.Louis)·DanielJiang(Facebook)·MaximilianBalandat(Facebook)·BrianKarrer(Facebook)·JacobGardner(UniversityofPennsylvania)·RomanGarnett(WashingtonUniversityinSt.Louis)

5、CreamoftheCrop:DistillingPrioritizedPathsForOne-ShotNeuralArchitectureSearch

HouwenPeng(MicrosoftResearch)·HaoDu(MicrosoftResearch)·HongyuanYu(MSRA)·QILI(TsinghuaUniveristy)·JingLiao(CityUniversityofHongKong)·JianlongFu(MicrosoftResearch

1、Few-shotImageGenerationviaSelf-Adaptation

YijunLi(AdobeResearch)·RichardZhang(Adobe)·Jingwan(Cynthia)Lu(AdobeResearch)·EliShechtman(AdobeResearch,US)

2、Few-shotVisualReasoningwithMeta-AnalogicalContrastiveLearning

YoungsungKim(SamsungAdvancedInstituteofTechnology)·JinwooShin(KAIST)·EunhoYang(KoreaAdvancedInstituteofScienceandTechnology;AItrics)·SungJuHwang(KAIST,AITRICS)

3、InterventionalFew-ShotLearning

ZhongqiYue(NanyangTechnologicalUniversity)·HanwangZhang(NTU)·QianruSun(SingaporeManagementUniversity)·Xian-ShengHua(DamoAcademy,AlibabaGroup)

4、Self-SupervisedFew-ShotLearningonPointClouds

CharuSharma(IndianInstituteofTechnologyHyderabad)·ManoharKaul(IITH)

5、AdversariallyRobustFew-ShotLearning:AMeta-LearningApproach

6、InformationMaximizationforFew-ShotLearning

MalikBoudiaf(EcoledeTechnologieSuperieure)·ImtiazZiko(Ecoledetechnologiesuperieure(ETS))·JérmeRony(éTSMontréal)·JoseDolz(ETSMontreal)·PabloPiantanida(CentraleSupélec-Mila)·IsmailBenAyed(ETSMontreal)

7、BayesianMeta-LearningfortheFew-ShotSettingviaDeepKernels

8、OOD-MAML:Meta-LearningforFew-ShotOut-of-DistributionDetectionandClassification

9、OneSolutionisNotAllYouNeed:Few-ShotExtrapolationviaStructuredMaxEntRL

SaurabhKumar(StanfordUniversity)·AviralKumar(UCBerkeley)·SergeyLevine(UCBerkeley)·ChelseaFinn(Stanford)

10、RestoringNegativeInformationinFew-ShotObjectDetection

11、NodeClassificationonGraphswithFew-ShotNovelLabelsviaMetaTransformedNetworkEmbedding

12、CrossTransformers:spatially-awarefew-shottransfer

13、LearningtoExtrapolateKnowledge:TransductiveFew-shotOut-of-GraphLinkPrediction

JinheonBaek(KAIST)·DongBokLee(KAIST)·SungJuHwang(KAIST,AITRICS)

14、LanguageModelsareFew-ShotLearners

TomBBrown(GoogleBrain)·BenjaminMann(OpenAI)·NickRyder(OpenAI)·MelanieSubbiah(OpenAI)·JaredDKaplan(JohnsHopkinsUniversity)·PrafullaDhariwal(OpenAI)·ArvindNeelakantan(OpenAI)·PranavShyam(OpenAI)·GirishSastry(OpenAI)·AmandaAskell(OpenAI)·SandhiniAgarwal(OpenAI)·ArielHerbert-Voss(OpenAI)·GretchenMKrueger(OpenAI)·TomHenighan(OpenAI)·RewonChild(OpenAI)·AdityaRamesh(OpenAI)·DanielZiegler(OpenAI)·JeffreyWu(OpenAI)·ClemensWinter(OpenAI)·ChrisHesse(OpenAI)·MarkChen(OpenAI)·EricSigler(OpenAI)·MateuszLitwin(OpenAI)·ScottGray(OpenAI)·BenjaminChess(OpenAI)·JackClark(OpenAI)·ChristopherBerner(OpenAI)·SamMcCandlish(OpenAI)·AlecRadford(OpenAI)·IlyaSutskever(OpenAI)·DarioAmodei(OpenAI)

1、EmergentComplexityandZero-shotTransferviaUnsupervisedEnvironmentDesign

MichaelDennis(UniversityofCaliforniaBerkeley)·NatashaJaques(MIT)·EugeneVinitsky(UCBerkeley)·AlexandreBayen(UCBerkeley)·StuartRussell(UCBerkeley)·AndrewCritch(UCBerkeley)·SergeyLevine(UCBerkeley)

2、DenseFeatureCompositionforZero-ShotLearning

DatHuynh(NortheasternUniversity)·EhsanElhamifar(NortheasternUniversity)

3、AttributePrototypeNetworkforZero-ShotLearning

WenjiaXu(UniversityofChineseAcademyofSciences)·YongqinXian(MaxPlanckInstituteInformatics)·JiuniuWang(CityUniversityofHongKong)·BerntSchiele(MaxPlanckInstituteforInformatics)·ZeynepAkata(UniversityofTübingen)

4、Uncertainty-AwareLearningforZero-ShotSemanticSegmentation

PingHu(BostonUniversity)·StanSclaroff(BostonUniversity)·KateSaenko(BostonUniversity&MIT-IBMWatsonAILab,IBMResearch)

5、ConsistentStructuralRelationLearningforZero-ShotSegmentation

PeikeLi(UniversityofTechnologySydney)·YunchaoWei(UTS)·YiYang(UTS)

6、ModelingTaskEffectsonMeaningRepresentationintheBrainviaZero-ShotMEGPrediction

MariyaToneva(CarnegieMellonUniversity)·OtiliaStretcu(CarnegieMellonUniversity)·BarnabasPoczos(CarnegieMellonUniversity)·LeilaWehbe(CarnegieMellonUniversity)·TomMitchell(CarnegieMellonUniversity)

1、SubgraphNeuralNetworks

EmilyAlsentzer(MIT)·SamuelFinlayson(HarvardMedicalSchool)·MichelleLi(HarvardMedicalSchool)·MarinkaZitnik(HarvardUniversity)

2、CanGraphNeuralNetworksCountSubstructures

ZhengdaoChen(NewYorkUniversity)·LeiChen(NewYorkUniversity)·SoledadVillar(NewYorkUniversity)·JoanBruna(NYU)

3、FactorGraphNeuralNetworks

ZhenZhang(UniversityofAdelaide)·FanWu(NanjingUniversity)·WeeSunLee(NationalUniversityofSingapore)

4、ImplicitGraphNeuralNetworks

FangdaGu(UCBerkeley)·HengChang(TsinghuaUniversity)·WenwuZhu(TsinghuaUniversity)·SomayehSojoudi(UniversityofCalifornia,Berkeley)·LaurentElGhaoui(UCBerkeley)

5、ReliableGraphNeuralNetworksviaRobustLocationEstimation

SimonGeisler(TechnicalUniversityofMunich)·DanielZügner(TechnicalUniversityofMunich)·StephanGünnemann(TechnicalUniversityofMunich)

6、AttributionforGraphNeuralNetworks

BenjaminSanchez-Lengeling(GoogleResearch)·JenniferWei(GoogleResearch)·BrianLee(GoogleInc.)·EmilyReif(Google)·PeterWang(ColumbiaUniversity)·WesleyWeiQian(UniversityofIllinoisatUrbana-Champaign)·KevinMcCloskey(Google)·LucyColwell(Google)·AlexanderWiltschko(GoogleBrain)

7、SpectralTemporalGraphNeuralNetworkforMultivariateTime-seriesForecasting

DefuCao(PekingUniversity)·YujingWang(MSRA)·JuanyongDuan(Microsoft)·CeZhang(ETHZurich)·XiaZhu(Microsoft)·CongruiHuang(Microsoft)·YunhaiTong(PekingUniversity)·BixiongXu(Microsoft)·JingBai(Microsoft)·JieTong(Microsoft)·QiZhang(Microsoft)

8、GNNGuard:DefendingGraphNeuralNetworksagainstAdversarialAttacks

XiangZhang(HarvardUniversity)·MarinkaZitnik(HarvardUniversity)

9、TowardsScale-InvariantGraph-relatedProblemSolvingbyIterativeHomogeneousGNNs

HaoTang(ShanghaiJiaoTongUniversity)·ZhiaoHuang(UniversityofCaliforniaSanDiego)·JiayuanGu(UniversityofCalifornia,SanDiego)·Bao-LiangLu(ShanghaiJiaoTongUniversity)·HaoSu(UCSD)

10、DistanceEncoding--DesignProvablyMorePowerfulGNNsforStructuralRepresentationLearning

PanLi(StanfordUniversity-PurdueUniversity)·YanbangWang(StanfordUniversity)·HongweiWang(StanfordUniversity)·JureLeskovec(StanfordUniversityandPinterest)

11、Rethinkingpoolingingraphneuralnetworks

DiegoMesquita(AaltoUniversity)·AmauriSouza(IFCE)·SamuelKaski(AaltoUniversityandUniversityofManchester)

12、DesignSpaceforGraphNeuralNetworks

JiaxuanYou(StanfordUniversity)·ZhitaoYing(StanfordUniversity)·JureLeskovec(StanfordUniversityandPinterest)

13、BanditSamplersforTrainingGraphNeuralNetworks

ZiqiLiu(AntFinancial)·ZhengweiWu(AntFinancial)·ZhiqiangZhang(AntFinancialServicesGroup)·JunZhou(AntFinancial)·ShuangYang(AntFinancial)·LeSong(AntFinancialServicesGroup)·YuanQi(AntFinancialServicesGroup)

14、Pre-TrainingGraphNeuralNetworks:AContrastiveLearningFrameworkwithAugmentations

15、BeyondHomophilyinGraphNeuralNetworks:CurrentLimitationsandEffectiveDesigns

JiongZhu(UniversityofMichigan)·YujunYan(UniversityofMichigan)·LingxiaoZhao(CarnegieMellonUniversity)·MarkHeimann(UniversityofMichigan)·LemanAkoglu(CMU)·DanaiKoutra(UMichigan)

16、ScalableGraphNeuralNetworksviaBidirectionalPropagation

MingChen(RenminUniversityofChina)·ZheweiWei(RenminUniversityofChina)·BolinDing("DataAnalyticsandIntelligenceLab,AlibabaGroup")·YaliangLi(AlibabaGroup)·YeYuan(BeijingInstituteofTechnology)·XiaoyongDu(RenminUniversityofChina)·Ji-RongWen(RenminUniversityofChina)

17、TowardsDeeperGraphNeuralNetworkswithDifferentiableGroupNormalization

KaixiongZhou(TexasA&MUniversity)·XiaoHuang(TheHongKongPolytechnicUniversity)·YueningLi(TexasA&MUniversity)·DaochenZha(TexasA&MUniversity)·RuiChen(SamsungResearchAmerica)·XiaHu(TexasA&MUniversity)

18、StronglyIncrementalConstituencyParsingwithGraphNeuralNetworks

KaiyuYang(PrincetonUniversity)·JiaDeng(PrincetonUniversity)

19、GraphonNeuralNetworksandtheTransferabilityofGraphNeuralNetworks

LuanaRuiz(UniversityofPennsylvania)·LuizChamon(UniversityofPennsylvania)·AlejandroRibeiro(UniversityofPennsylvania)

20、AdversarialAttackonGraphNeuralNetworkswithLimitedNodeAccess

JiaqiMa(UniversityofMichigan)·ShuangruiDing(UniversityofMichigan)·QiaozhuMei(UniversityofMichigan)

21、PathIntegralBasedConvolutionandPoolingforGraphNeuralNetworks

ZhengMa(PrincetonUniversity)·JunyuXuan(UniversityofTechnologySydney)·YuGuangWang(UniversityofNewSouthWales;MPIMiS)·MingLi(ZhejiangNormalUniversity)·PietroLiò(UniversityofCambridge)

22、Howhardistodistinguishgraphswithgraphneuralnetworks

AndreasLoukas(EPFL)

23、ParameterizedExplainerforGraphNeuralNetwork

DongshengLuo(ThePennsylvaniaStateUniversity)·WeiCheng(NECLabsAmerica)·DongkuanXu(ThePennsylvaniaStateUniversity)·WenchaoYu(UCLA)·BoZong(NECLabs)·HaifengChen(NECLabsAmerica)·XiangZhang(ThePennsylvaniaStateUniversity)

24、Buildingpowerfulandequivariantgraphneuralnetworkswithmessage-passing

ClémentVignac(EPFL)·AndreasLoukas(EPFL)·PascalFrossard(EPFL)

25、RandomWalkGraphNeuralNetworks

GiannisNikolentzos(AthensUniversityofEconomicsandBusiness)·MichalisVazirgiannis(écolePolytechnique)

26、LearningtoExecuteProgramswithInstructionPointerAttentionGraphNeuralNetworks

27、PGM-Explainer:ProbabilisticGraphicalModelExplanationsforGraphNeuralNetworks

MinhNVu(UniversityofFlorida)·MyT.Thai(UniversityofFlorida)

28、OptimizationandGeneralizationAnalysisofTransductionthroughGradientBoostingandApplicationtoMulti-scaleGraphNeuralNetworks

KentaOono(TheUniversityofTokyo,PreferredNetworksInc.)·TaijiSuzuki(TheUniversityofTokyo/RIKEN-AIP)

1、Cross-scaleInternalGraphConvolutionNetworkforImageSuper-Resolution

ShangchenZhou(NanyangTechnologicalUniversity)·JiaweiZhang(SensetimeResearch)·WangmengZuo(HarbinInstituteofTechnology)·ChenChangeLoy(NanyangTechnologicalUniversity)

2、CertifiedRobustnessofGraphConvolutionNetworksforGraphClassificationunderTopologicalAttacks

HongweiJin(UniversityofIllinoisatChicago)·ZhanShi(UniversityofIllinoisatChicago)·VenkataJayaShankarAshishPeruri(UniversityofIllinoisatChicago)·XinhuaZhang(UIC)

HaraldSteck(Netflix)

2、SwappingAutoencoderforDeepImageManipulation

TaesungPark(UCBerkeley)·Jun-YanZhu(Adobe,CMU)·OliverWang(AdobeResearch)·JingwanLu(AdobeResearch)·EliShechtman(AdobeResearch,US)·AlexeiEfros(UCBerkeley)·RichardZhang(Adobe)

3、HierarchicalQuantizedAutoencoders

WillWilliams(Speechmatics)·SamRinger(Speechmatics)·TomAsh(Speechmatics)·DavidMacLeod(Speechmatics)·JamieDougherty(Speechmatics)·JohnHughes(Speechmatics)

4、ImplicitRank-MinimizingAutoencoder

LiJing(FacebookAIResearch)·JureZbontar(Facebook)·yannlecun(Facebook)

5、DirichletGraphVariationalAutoencoder

JiaLi(TheChineseUniversityofHongKong)·JianweiYu(CUHK)·JiajinLi(TheChineseUniversityofHongKong)·HongleiZhang(GeorgiaInstituteofTechnology)·KangfeiZhao(TheChineseUniversityofHongKong)·YuRong(TencentAILab)·HongCheng(TheChineseUniversityofHongKong)·JunzhouHuang(UniversityofTexasatArlington/TencentAILab)

6、Regularizedlinearautoencodersrecovertheprincipalcomponents,eventually

XuchanBao(UniversityofToronto)·JamesLucas(UniversityofToronto)·SushantSachdeva(UniversityofToronto)·RogerGrosse(UniversityofToronto)

7、FullyConvolutionalMeshAutoencoderusingEfficientSpatiallyVaryingKernels

YiZhou(UniversityofSouthernCalifornia)·ChengleiWu(Facebook)·ZimoLi(UniversityofSouthernCalifornia)·ChenCao(SnapInc.)·YutingYe(FacebookRealityLabs)·JasonSaragih(Facebook)·HaoLi(Pinscreen/UniversityofSouthernCalifornia/USCICT)·YaserSheikh(FacebookRealityLabs)

8、TheAutoencodingVariationalAutoencoder

TaylanCemgil(DeepMind)·SumedhGhaisas(DeepMind)·KrishnamurthyDvijotham(DeepMind)·SvenGowal(DeepMind)·PushmeetKohli(DeepMind)

9、RecursiveInferenceforVariationalAutoencoders

MinyoungKim(SamsungAICenter)·VladimirPavlovic(RutgersUniversity)

10、NVAE:ADeepHierarchicalVariationalAutoencoder

ArashVahdat(NVIDIA)·JanKautz(NVIDIA)

11、EvidentialSparsificationofMultimodalLatentSpacesinConditionalVariationalAutoencoders

1、AdaptiveGradientQuantizationforData-ParallelSGD

FartashFaghri(UniversityofToronto)·ImanTabrizian(UniversityofToronto)·IliaMarkov(ISTAustria)·DanAlistarh(ISTAustria&NeuralMagicInc.)·DanielRoy(UnivofToronto&Vector)·AliRamezani-Kebrya(VectorInstitute)

2、RobustQuantization:OneModeltoRuleThemAll

MoranShkolnik(Intel)·BrianChmiel(Intel)·RonBanner(Intel-ArtificialIntelligenceProductsGroup(AIPG))·GilShomron(Technion-IsraelInstituteofTechnology)·YuryNahshan(Intel-ArtificialIntelligenceProductsGroup(AIPG))·AlexBronstein(Technion)·UriWeiser(Technion-IsraelInstituteofTechnology)

3、Position-basedScaledGradientforModelQuantizationandSparseTraining

JanghoKim(SeoulNationalUniversity)·KiYoonYoo(SeoulNationalUniversity)·NojunKwak(SeoulNationalUniversity)

4、AMQ:AutomaticMixed-precisionQuantizationBasedonHessianTrace

ZhenDong(UCBerkeley)·ZheweiYao(UCBerkeley)·DaiyaanArfeen(UCBerkeley)·AmirGholami(UniversityofCalifornia,Berkeley)·MichaelMahoney(UCBerkeley)·KurtKeutzer(EECS,UCBerkeley)

5、FleXOR:TrainableFractionalQuantization

DongsooLee(SamsungResearch)·SeJungKwon(SamsungResearch)·ByeongwookKim(SamsungResearch)·YongkweonJeon(SamsungResearch)·BaeseongPark(samsungresearch)·JeonginYun(SamsungResearch)

6、ClosingtheDequantizationGap:PixelCNNasaSingle-LayerFlow

DidrikNielsen(DTUCompute)·OleWinther(DTUandKU)

7、BayesianBits:UnifyingQuantizationandPruning

MartvanBaalen(Qualcomm)·ChristosLouizos(QualcommAIResearch)·MarkusNagel(Qualcomm)·RanaAliAmjad(Qualcomm)·YingWang(Qualcomm)·TijmenBlankevoort(Qualcomm)·MaxWelling(UniversityofAmsterdam/QualcommAIResearch)

1、PruningFilterinFilter

FanxuMeng(HarbinInstituteofTechnology,Shenzhen)·HaoCheng(Tencent)·KeLi(Tencent)·HuixiangLuo(Tencent)·XiaoweiGuo(TencentYoutuLab)·GuangmingLu(HarbinInstituteofTechnology,Shenzhen)·XingSun(Tencent)

2、Pruningneuralnetworkswithoutanydatabyconservingsynapticflow

HidenoriTanaka(NTTResearch,PHILab/StanfordUniversity)·DanielKunin(StanfordUniversity)·DanielYamins(StanfordUniversity)·SuryaGanguli(Stanford)

3、NetworkPruningviaGreedyOptimization:FastRateandEfficientAlgorithms

MaoYe(TheUniversityofTexasatAustin)·LemengWu(UTAustin)·QiangLiu(UTAustin)

4、HYDRA:PruningAdversariallyRobustNeuralNetworks

VikashSehwag(PrincetonUniversity)·ShiqiWang(Columbia)·PrateekMittal(PrincetonUniversity)·SumanJana(ColumbiaUniversity)

5、LogarithmicPruningisAllYouNeed

LaurentOrseau(DeepMind)·MarcusHutter(DeepMind)·OmarRivasplata(DeepMind&UCL)

6、BayesianBits:UnifyingQuantizationandPruning

7、Sanity-CheckingPruningMethods:RandomTicketscanWintheJackpot

JingtongSu(PekingUniversity)·YihangChen(PekingUniversity)·TianleCai(PekingUniversity)·TianhaoWu(PekingUniversity)·RuiqiGao(PekingUniversity)·LiweiWang(PekingUniversity)·JasonLee(PrincetonUniversity)

8、ScientificControlforReliableNeuralNetworkPruning

9、Neuron-levelStructuredPruningusingPolarizationRegularizer

TaoZhuang(AlibabaGroup)·ZhixuanZhang(BeijingUniversityofPostsandTelecommunications)·YuhengHuang(BeijingUniv.ofPostsandTelecommunications)·XiaoyiZeng(AlibabaGroup)·KaiShuang(StateKeyLaboratoryofNetworkingandSwitchingTechnology,BeijingUniversityofPostsandTelecommunications,Beijing,China.)·XiangLi(AlibabaGroup)

10、DirectionalPruningofDeepNeuralNetworks

Shih-KangChao(UniversityofMissouri)·ZhanyuWang(PurdueUniversity)·YueXing(PurdueUniversity)·GuangCheng(PurdueUniversity)

11、StorageEfficientandDynamicFlexibleRuntimeChannelPruningviaDeepReinforcementLearning

12、MovementPruning:AdaptiveSparsitybyFine-Tuning

VictorSanh(HuggingFace)·ThomasWolf(HuggingFace)·AlexanderRush(CornellUniversity)

13、TheGeneralization-StabilityTradeoffInNeuralNetworkPruning

BrianBartoldson(FloridaStateUniversity)·AriMorcos(FacebookAIResearch)·AdrianBarbu(FloridaStateUniversity,USA)·GordonErlebacher(FloridaStateUniversity)

14、BayesianBits:UnifyingQuantizationandPruning

1、UniversallyQuantizedNeuralCompression

EirikurAgustsson(Google)·LucasTheis(Twitter)

ChongYu(NVIDIA)·ChongYu(Intel)

2、High-FidelityGenerativeImageCompression

FabianMentzer(ETHZurich)·GeorgeDToderici(Google)·MichaelTschannen(GoogleBrain)·EirikurAgustsson(Google)

3、MuSCLE:MultiSweepCompressionofLiDARusingDeepEntropyModels

SouravBiswas(UniversityofWaterloo)·JerryLiu(UberATG)·KelvinWong(UniversityofToronto)·ShenlongWang(UniversityofToronto)·RaquelUrtasun(UberATG)

4、ImprovingInferenceforNeuralImageCompression

YiboYang(UniversityofCalifornia,Irivine)·RobertBamler(UniversityofCaliforniaatIrvine)·StephanMandt(UniversityofCalifornia,Irivine)

5、PracticalLow-RankCommunicationCompressioninDecentralizedDeepLearning

ThijsVogels(EPFL)·SaiPraneethKarimireddy(EPFL)·MartinJaggi(EPFL)

6、AttributionPreservationinNetworkCompressionforReliableNetworkInterpretation

GeondoPark(KoreaAdvancedInstituteofScienceandTechnology)·JuneYongYang(KoreaAdvancedInstituteofScienceandTechnology)·SungJuHwang(KAIST,AITRICS)·EunhoYang(KoreaAdvancedInstituteofScienceandTechnology;AItrics)

7、Self-SupervisedGenerativeAdversarialCompression

8、ScaleCom:ScalableSparsifiedGradientCompressionforCommunication-EfficientDistributedTraining

Chia-YuChen(IBMresearch)·JiaminNi(IBM)·SongtaoLu(IBM)·XiaodongCui(IBMT.J.WatsonResearchCenter)·Pin-YuChen(IBMResearchAI)·XiaoSun(IBMThomasJ.WatsonResearchCenter)·NaigangWang(IBMT.J.WatsonResearchCenter)·SwagathVenkataramani(IBMResearch)·Vijayalakshmi(Viji)Srinivasan(IBMTJWatson)·WeiZhang(IBMT.J.WatsonResearchCenter)·KailashGopalakrishnan(IBMResearch)

9、MiniLM:DeepSelf-AttentionDistillationforTask-AgnosticCompressionofPre-TrainedTransformers

WoodFisher:EfficientSecond-OrderApproximationforNeuralNetworkCompression

SidakPalSingh(EPFL)·DanAlistarh(ISTAustria&NeuralMagicInc.)

1、ISTA-NAS:EfficientandConsistentNeuralArchitectureSearchbySparseCoding

YiboYang(PekingUniversity)·HongyangLi(PekingUniversity)·ShanYou(SenseTime)·FeiWang(SenseTime)·ChenQian(SenseTime)·ZhouchenLin(PekingUniversity)

2、BRP-NAS:Prediction-basedNASusingGCNs

ThomasChau(SamsungAICenterCambridge)·LukaszDudziak(SamsungAICenterCambridge)·MohamedAbdelfattah(SamsungAICentreCambridge)·RoysonLee(SamsungAICenterCambridge)·HyejiKim(SamsungAICenterCambridge)·NicholasLane(SamsungAICenterCambridge&UniversityofOxford)

4、CryptoNAS:PrivateInferenceonaReLUBudget

ZahraGhodsi(NewYorkUniversity)·AkshajKumarVeldanda(NewYorkUniversity)·BrandonReagen(NewYorkUniversity)·SiddharthGarg(NYU)

5、ISTA-NAS:EfficientandConsistentNeuralArchitectureSearchbySparseCoding

6、BRP-NAS:Prediction-basedNASusingGCNs

7、DifferentiableNeuralArchitectureSearchinEquivalentSpacewithExplorationEnhancement

MiaoZhang(UTS&BIT)·HuiqiLi(BeijingInstituteofTechnology)·ShiruiPan(MonashUniversity)·XiaojunChang(MonashUniversity)·ZongyuanGe(MonashUniversity)·StevenSu(UniversityofTechnologySydney)

8、HierarchicalNeuralArchitectureSearchforDeepStereoMatching

XuelianCheng(MonashUniversity)·YiranZhong(AustralianNationalUniversity)·MehrtashTHarandi(MonashUniversity)·YuchaoDai(NorthwesternPolytechnicalUniversity)·XiaojunChang(MonashUniversity)·HongdongLi(AustralianNationalUniversity)·TomDrummond(MonashUniversity)·ZongyuanGe(MonashUniversity)

9、AStudyonEncodingsforNeuralArchitectureSearch

ColinWhite(RealityEngines.AI)·WillieNeiswanger(CarnegieMellonUniversity)·SamNolen(RealityEngines.AI)·YashSavani(RealityEngines.AI)

10、CreamoftheCrop:DistillingPrioritizedPathsForOne-ShotNeuralArchitectureSearch

HouwenPeng(MicrosoftResearch)·HaoDu(MicrosoftResearch)·HongyuanYu(MSRA)·QILI(TsinghuaUniveristy)·JingLiao(CityUniversityofHongKong)·JianlongFu(MicrosoftResearch)

11、CLEARER:Multi-ScaleNeuralArchitectureSearchforImageRestoration

YuanbiaoGou(CollegeofComputerScience,SichuanUniversity)·BoyunLi(CollegeofComputerScience,SichuanUniversity)·ZitaoLiu(TALAILab)·SongfanYang(TALAILab)·XiPeng(InstituteforInfocomm,ResearchAgencyforScience,TechnologyandResearch(A*STAR)Singapore)

12、DoesUnsupervisedArchitectureRepresentationLearningHelpNeuralArchitectureSearch

ShenYan(MichiganStateUniversity)·YuZheng(MichiganStateUniversity)·WeiAo(MichiganStateUniversity)·XiaoZeng(MichiganStateUniversity)·MiZhang(MichiganStateUniversity)

1、BayesianOptimizationoverStringSpaces

HenryMoss(LancasterUniversity)·DavidLeslie(LancasterUniversityandPROWLER.io)·DanielBeck(UniversityofMelbourne)·JavierGonzalez(Amazon.com)·PaulRayson(LancasterUniversity)

2、BayesianOptimizationofRiskMeasures

SaitCakmak(GeorgiaInstituteofTechnology)·RaulAstudilloMarban(CornellUniversity)·PeterFrazier(Cornell/Uber)·EnluZhou(GeorgiaInstituteofTechnology)

3、BayesianOptimizationforIterativeLearning

VuNguyen(UniversityofOxford)·SebastianSchulze(UniversityofOxford)·MichaelAOsborne(UOxford)

4、ModularBayesianOptimizationwithBoTorch:AnEfficientDifferentiableMonte-CarloApproach

MaximilianBalandat(Facebook)·BrianKarrer(Facebook)·DanielJiang(Facebook)·SamuelDaulton(Facebook)·BenLetham(Facebook)·AndrewGordonWilson(NewYorkUniversity)·EytanBakshy(Facebook)

5、DifferentiableExpectedHypervolumeImprovementforParallelMulti-ObjectiveBayesianOptimization

SamuelDaulton(Facebook)·MaximilianBalandat(Facebook)·EytanBakshy(Facebook)

6、FederatedBayesianOptimizationviaThompsonSampling

ZhongxiangDai(NationalUniversityofSingapore)·BryanKianHsiangLow(NationalUniversityofSingapore)·PatrickJaillet(MIT)

7、Multi-FidelityBayesianOptimizationviaDeepNeuralNetworks

ShiboLi(UniversityofUtah)·WeiXing(UniversityofUtah)·RobertKirby(UniversityofUtah)·ShandianZhe(UniversityofUtah)

8、Diversity-GuidedMulti-ObjectiveBayesianOptimizationWithBatchEvaluations

MinaKonakovicLukovic(MassachusettsInstituteofTechnology)·YunshengTian(MassachusettsInstituteofTechnology)·WojciechMatusik(MIT)

9、FastMatrixSquareRootswithApplicationstoGaussianProcessesandBayesianOptimization

GeoffPleiss(ColumbiaUniversity)·MartinJankowiak(UberAILabs)·DavidEriksson(Facebook)·AnilDamle(CornellUniversity)·JacobGardner(UniversityofPennsylvania)

10、Re-ExaminingLinearEmbeddingsforHigh-DimensionalBayesianOptimization

BenLetham(Facebook)·RobertoCalandra(FacebookAIResearch)·AksharaRai(Facebook)·EytanBakshy(Facebook)

11、EfficientNonmyopicBayesianOptimizationviaOne-ShotMulti-StepTrees

12、EfficientExplorationofRewardFunctionsinInverseReinforcementLearningviaBayesianOptimization

13、High-DimensionalBayesianOptimizationviaNestedRiemannianManifolds

NoémieJaquier(KarlsruheInstituteofTechnology)·LeonelRozo(BoschCenterforArtificialIntelligence)

14、High-DimensionalContextualPolicySearchwithUnknownContextRewardsusingBayesianOptimization

QingFeng(Facebook)·BenLetham(Facebook)·HongziMao(MIT)·EytanBakshy(Facebook)

15、BayesianRobustOptimizationforImitationLearning

DanielBrown(TheUniversityofTexasatAustin)·ScottNiekum(UTAustin)·MarekPetrik(UniversityofNewHampshire)

1、Convexoptimizationbasedongloballowersecond-ordermodels

NikitaDoikov(CatholicUniversityofLouvain)·YuriiNesterov(CatholicUniversityofLouvain(UCL))

2、Aconvexoptimizationformulationformultivariateregression

YunzhangZhu(OhioStateUniversity)

3、OptimalQueryComplexityofSecureStochasticConvexOptimization

WeiTang(WashingtonUniversityinSt.Louis)·Chien-JuHo(WashingtonUniversityinSt.Louis)·YangLiu(UCSantaCruz)

4、Generalizationerrorinhigh-dimensionalperceptrons:ApproachingBayeserrorwithconvexoptimization

BenjaminAubin(IphtSaclay)·FlorentKrzakala(ENSParis,SorbonnesUniversité&EPFL)·YueLu(HarvardUniversity)·LenkaZdeborová(UniversityParis-Saclay&EPFL)

5、CanImplicitBiasExplainGeneralizationStochasticConvexOptimizationasaCaseStudy

AssafDauber(Tel-AvivUniversity)·MeirFeder(Tel-AvivUniversity)·TomerKoren(Google)·RoiLivni(TelAvivUniversity)

6、Leveragingpredictionsinsmoothedonlineconvexoptimizationviagradient-basedalgorithms

YingyingLi(HarvardUniversity)·NaLi(HarvardUniversity)

7、Anefficientnonconvexreformulationofstagewiseconvexoptimizationproblems

SrinadhBhojanapalli(GoogleAI)·RudyBunel(Deepmind)·KrishnamurthyDvijotham(DeepMind)·OliverHinder(UniversityofPittsburgh)

8、Understandingspikingnetworksthroughconvexoptimization

AllanMancoo(ChampalimaudCentrefortheUnknown)·SanderKeemink(ChampalimaudCentrefortheUnknown)·ChristianKMachens(ChampalimaudCentrefortheUnknown)

9、MinimaxRegretofSwitching-ConstrainedOnlineConvexOptimization:NoPhaseTransition

LinChen(UniversityofCalifornia,Berkeley)·QianYu(UniversityofSouthernCalifornia)·HannahLawrence(FlatironInstitute)·AminKarbasi(Yale)

10、OnlineConvexOptimizationOverErdos-RenyiRandomNetworks

JinlongLei(TongjiUniversity)·PengYi(TongjiUniversity)·YiguangHong(AcademyofMathematicsandSystemsScience,ChineseAcademyofSciences)·JieChen(BeijingInstituteofTechnology)·GuodongShi(UniversityofSydney)

1、SecondOrderOptimalityinDecentralizedNon-ConvexOptimizationviaPerturbedGradientTracking

IsidorosTziotis(UTAustin)·ConstantineCaramanis(UTAustin)·AryanMokhtari(UTAustin)

2、ImprovedAnalysisofClippingAlgorithmsforNon-convexOptimization

BohangZhang(PekingUniversity)·JikaiJin(PekingUniversity)·CongFang(PekingUniversity)·LiweiWang(PekingUniversity)

3、OnlineNon-ConvexOptimizationwithInexactModels

AmélieHéliou(CriteoAILab)·MatthieuMartin(Criteo)·PanayotisMertikopoulos(CNRS(FrenchNationalCenterforScientificResearch))·ThibaudJRahier(INRIA)

4、BreakingReversibilityAcceleratesLangevinDynamicsforNon-ConvexOptimization

XuefengGAO(TheChineseUniversityofHongKong)·MertGurbuzbalaban(Rutgers)·LingjiongZhu(FloridaStateUniversity)

5、FindingSecond-OrderStationaryPointsEfficientlyinSmoothNonconvexLinearlyConstrainedOptimizationProblems

SongtaoLu(IBMResearch)·MeisamRazaviyayn(UniversityofSouthernCalifornia)·BoYang(UniversityofMinnesota)·KejunHuang(UniversityofFlorida)·MingyiHong(UniversityofMinnesota)

1、POMO:PolicyOptimizationwithMultipleOptimaforReinforcementLearning

2、Model-basedPolicyOptimizationwithUnsupervisedModelAdaptation

JianShen(ShanghaiJiaoTongUniversity)·HanZhao(CarnegieMellonUniversity)·WeinanZhang(ShanghaiJiaoTongUniversity)·YongYu(ShanghaiJiaoTongUnviersity)

3、DynamicRegretofPolicyOptimizationinNon-stationaryEnvironments

YingjieFei(CornellUniversity)·ZhuoranYang(Princeton)·ZhaoranWang(NorthwesternUniversity)·QiaominXie(CornellUniversity)

4、MOPO:Model-basedOfflinePolicyOptimization

TianheYu(StanfordUniversity)·GarrettW.Thomas(StanfordUniversity)·LantaoYu(StanfordUniversity)·StefanoErmon(Stanford)·JamesZou(StanfordUniversity)·SergeyLevine(UCBerkeley)·ChelseaFinn(Stanford)·TengyuMa(StanfordUniversity)

5、AdversarialSoftAdvantageFitting:ImitationLearningwithoutPolicyOptimization

PaulBarde(QuebecAIinstitute-UbisoftLaForge)·JulienRoy(Mila)·WonseokJeon(MILA,McGillUniversity)·JoellePineau(McGillUniversity)·ChrisPal(MILA,PolytechniqueMontréal,ElementAI)·DerekNowrouzezahrai(McGillUniversity)

6、MinimaxConfidenceIntervalforOff-PolicyEvaluationandPolicyOptimization

NanJiang(UniversityofIllinoisatUrbana-Champaign)·JiaweiHuang(UniversityofIllinoisatUrbana-Champaign)

7、HowtoLearnaUsefulCriticModel-basedAction-Gradient-EstimatorPolicyOptimization

1、Black-BoxOptimizationwithLocalGenerativeSurrogates

SergeyShirobokov(ImperialCollegeLondon)·VladislavBelavin(NationalResearchUniversityHigherSchoolofEconomics)·MichaelKagan(SLAC/Stanford)·AndreiUstyuzhanin(NationalResearchUniversityHigherSchoolofEconomics)·AtilimGunesBaydin(UniversityofOxford)

2、ScalableBlack-boxOptimizationbyLearnableSearchSpacePartition

LinnanWang(BrownUniversity)·RodrigoFonseca(BrownUniversity)·YuandongTian(FacebookAIResearch)

3、Improvingmodelcalibrationwithaccuracyversusuncertaintyoptimization

RanganathKrishnan(IntelLabs)·OmeshTickoo(Intel)

4、StochasticOptimizationforPerformativePrediction

CelestineMendler-Dünner(UCBerkeley)·JuanPerdomo(UniversityofCalifornia,Berkeley)·TijanaZrnic(UCBerkeley)·MoritzHardt(UniversityofCalifornia,Berkeley)

5、UnfoldingtheAlternatingOptimizationforBlindSuperResolution

zhengxiongluo(中国科学院自动化所)·YanHuang(CRIPAC,CASIA)·ShangLi(CASIA)·LiangWang(NLPR,China)·TieniuTan(ChineseAcademyofSciences)

6、Dual-FreeStochasticDecentralizedOptimizationwithVarianceReduction

HadrienHendrikx(INRIA-PSL)·FrancisBach(INRIA-EcoleNormaleSuperieure)·LaurentMassoulié(Inria)

7、Black-BoxCertificationwithRandomizedSmoothing:AFunctionalOptimizationBasedFramework

DinghuaiZhang(PekingUniversity)·MaoYe(TheUniversityofTexasatAustin)·ChengyueGong(PekingUniversity)·ZhanxingZhu(PekingUniversity)·QiangLiu(UTAustin)

8、ProjectionRobustWassersteinDistanceandRiemannianOptimization

TianyiLin(UCBerkeley)·ChenyouFan(TheChineseUniversityofHongKong,Shenzhen)·NhatHo(UniversityofTexasatAustin)·MarcoCuturi(GoogleBrain&CREST-ENSAE)·MichaelJordan(UCBerkeley)

9、ProvablyEfficientOnlineHyperparameterOptimizationwithPopulation-BasedBandits

JackParker-Holder(UniversityofOxford)·VuNguyen(UniversityofOxford)·StephenJRoberts(UniversityofOxford)

10、CoresetsviaBilevelOptimizationforContinualLearningandStreaming

ZalánBorsos(ETHZurich)·MojmirMutny(ETHZurich)·AndreasKrause(ETHZurich)

11、SemialgebraicOptimizationforLipschitzConstantsofReLUNetworks

TongChen(LAAS-CNRS)·JeanBLasserre(lasserre@laas.fr)·VictorMagron(LAAS-CNRS)·EdouardPauwels(IRIT)

StochasticVarianceReducedAcceleratedDualAveragingforFinite-SumOptimization

ChaobingSong(TsinghuaUniversity)·YongJiang(Tsinghua)·YiMa(UCBerkeley)

12、InferenceStageOptimizationforCross-scenario3DHumanPoseEstimation

JianfengZhang(NUS)·XuechengNie(NUS)·JiashiFeng(NationalUniversityofSingapore)

13、RobustOptimizationforFairnesswithNoisyProtectedGroups

SerenaWang(Google)·WenshuoGuo(UCBerkeley)·HarikrishnaNarasimhan(GoogleResearch)·AndrewCotter(Google)·MayaGupta(Google)·MichaelJordan(UCBerkeley)

13、FedSplit:analgorithmicframeworkforfastfederatedoptimization

ReesePathak(UniversityofCalifornia,Berkeley)·MartinWainwright(UCBerkeley)

14、Robust,AccurateStochasticOptimizationforVariationalInference

AkashKumarDhaka(AaltoUniversity)·AlejandroCatalina(AaltoUniversity)·MichaelAndersen(AaltoUniversity)·MnsMagnusson(AaltoUniversity)·JonathanHuggins(BostonUniversity)·AkiVehtari(AaltoUniversity)

15、FirstOrderConstrainedOptimizationinPolicySpace

YimingZhang(NewYorkUniversity)·QuanVuong(UniversityofCalifornia,SanDiego)·KeithRoss(NYUShanghai)

16、ReinforcedMolecularOptimizationwithNeighborhood-ControlledGrammars

ChenchengXu(TsinghuaUniversity)·QiaoLiu(TsinghuaUniversity)·MinlieHuang(TsinghuaUniversity)·TaoJiang(UniversityofCalifornia-Riverside)

17、AdvancesinBlack-BoxVI:NormalizingFlows,ImportanceWeighting,andOptimization

AbhinavAgrawal(UMassAmherst)·DanielSheldon(UniversityofMassachusettsAmherst)·JustinDomke(UniversityofMassachusetts,Amherst)

18、ImprovedAlgorithmsforConvex-ConcaveMinimaxOptimization

YuanhaoWang(TsinghuaUniversity)·JianLi(TsinghuaUniversity)

19、BiasedStochasticGradientDescentforConditionalStochasticOptimization

YifanHu(UniversityofIllinoisatUrbana-Champaign)·SiqiZhang(UniversityofIllinoisatUrbana-Champaign)·XinChen(UniversityofIllinoisatUrbana-Champaign)·NiaoHe(UIUC)

20、ModelingandOptimizationTrade-offinMeta-learning

21、OnlineOptimizationwithMemoryandCompetitiveControl

GuanyaShi(Caltech)·YihengLin(CaliforniaInstituteofTechnology)·Soon-JoChung(Caltech)·YisongYue(Caltech)·AdamWierman(CaliforniaInstituteofTechnology)

22、AutomaticallyLearningCompactQuality-awareSurrogatesforOptimizationProblems

KaiWang(HarvardUniversity)·BryanWilder(HarvardUniversity)·AndrewPerrault(HarvardUniversity)·MilindTambe(HarvardUniversity/Google)

23、Bayesianfilteringunifiesadaptiveandnon-adaptiveneuralnetworkoptimizationmethods

LaurenceAitchison(UniversityofCambridge)

24、ModelInversionNetworksforModel-BasedOptimization

AviralKumar(UCBerkeley)·SergeyLevine(UCBerkeley)

25、NeuralArchitectureGeneratorOptimization

RobinRu(OxfordUniversity)·PedroMEsperana(Huawei)·FabioMariaCarlucci(SapienzaUniversityofRome)

26、Sample-EfficientOptimizationintheLatentSpaceofDeepGenerativeModelsviaWeightedRetraining

AustinTripp(UniversityofCambridge)·ErikDaxberger(UniversityofCambridge)·JoséMiguelHernández-Lobato(UniversityofCambridge)

27、GuidingDeepMolecularOptimizationwithGeneticExploration

Sung-SooAhn(KAIST)·JunsuKim(KAIST)·HankookLee(KoreaAdvancedInstituteofScienceandTechnology)·JinwooShin(KAIST)

28、RelativegradientoptimizationoftheJacobianterminunsuperviseddeeplearning

LuigiGresele(MPIforIntelligentSystems,Tübingen)·GiancarloFissore(Inria)·AdriánJavaloy(SaarlandUniversity)·BernhardSchlkopf(MPIforIntelligentSystems)·AapoHyvarinen(UniversityofHelsinki)

29、FullyDynamicAlgorithmforConstrainedSubmodularOptimization

SilvioLattanzi(GoogleResearch)·SlobodanMitrovi(MIT)·AshkanNorouzi-Fard(GoogleResearch)·JakubTarnawski(MicrosoftResearch)·MortezaZadimoghaddam(GoogleResearch)

30、ConicDescentanditsApplicationtoMemory-efficientOptimizationoverPositiveSemidefiniteMatrices

JohnDuchi(Stanford)·OliverHinder(UniversityofPittsburgh)·AndrewNaber(StanfordUniversity)·YinyuYe(Standord)

31、CooperativeMulti-PlayerBanditOptimization

IlaiBistritz(Stanford)·NicholasBambos(StanfordUniversity)

32、ExploitingHigherOrderSmoothnessinDerivative-freeOptimizationandContinuousBandits

AryaAkhavan(ENSAE-IIT)·MassimilianoPontil(IIT&UCL)·AlexandreTsybakov(CREST,ENSAE)

33、ContextualReservePriceOptimizationinAuctionsviaMixedIntegerProgramming

JoeyHuchette(RiceUniversity)·HaihaoLu(UniversityofChicago)·HosseinEsfandiari(GoogleResearch)·VahabMirrokni(GoogleResearchNYC)

34、AdaptiveImportanceSamplingforFinite-SumOptimizationandSamplingwithDecreasingStep-Sizes

AyoubElHanchi(McGillUniversity)·DavidStephens(McGillUniversity)

35、StochasticOptimizationwithHeavy-TailedNoiseviaAcceleratedGradientClipping

EduardGorbunov(MoscowInstituteofPhysicsandTechnology)·MarinaDanilova(ICSRAS)·AlexanderGasnikov(MIPT&HSE)

36、OptimizationandGeneralizationofShallowNeuralNetworkswithQuadraticActivationFunctions

StefanoSaraoMannelli(InstitutdePhysiqueThéorique)·EricVanden-Eijnden(NewYorkUniversity)·LenkaZdeborová(UniversityParis-Saclay&EPFL)

37、AccelerationwithaBallOptimizationOracle

YairCarmon(StanfordUniversity)·ArunJambulapati(StanfordUniversity)·QijiaJiang(StanfordUniversity)·YujiaJin(StanfordUniversity)·YinTatLee(UW)·AaronSidford(Stanford)·KevinTian(StanfordUniversity

38、Large-ScaleMethodsforDistributionallyRobustOptimization

DanielLevy(StanfordUniversity)·YairCarmon(StanfordUniversity)·JohnDuchi(Stanford)·AaronSidford(Stanford)

39、DAGswithNoFears:ACloserLookatContinuousOptimizationforLearningBayesianNetworks

DennisWei(IBMResearch)·TianGao(IBMResearchAI)·yueyu(LehighUniversity)

40、OnlineLinearOptimizationwithManyHints

AdityaBhaskara(UniversityofUtah)·AshokCutkosky(GoogleResearch)·RaviKumar(Google)·ManishPurohit(Google)

41、TacklingtheObjectiveInconsistencyProbleminHeterogeneousFederatedOptimization

JianyuWang(CarnegieMellonUniversity)·QinghuaLiu(PrincetonUniversity)·HaoLiang(CarnegieMellonUniversity)·GauriJoshi(CarnegieMellonUniversity)·H.VincentPoor(PrincetonUniversity)

42、DebiasingDistributedSecondOrderOptimizationwithSurrogateSketchingandScaledRegularization

MichalDerezinski(UCBerkeley)·BurakBartan(StanfordUniversity)·MertPilanci(Stanford)·MichaelWMahoney(UCBerkeley)

43、ACatalystFrameworkforMinimaxOptimization

JunchiYang(UniversityofIllinois)·SiqiZhang(UniversityofIllinoisatUrbana-Champaign)·NegarKiyavash(écolePolytechniqueFédéraledeLausanne)·NiaoHe(UIUC)

44、ANovelApproachforConstrainedOptimizationinGraphicalModels

SaraRouhani(UniversityofTexasatDallas)·TahrimaRahman(UTDallas)·VibhavGogate(UTDallas)

45、NetworkPruningviaGreedyOptimization:FastRateandEfficientAlgorithms

EffectiveDimensionAdaptiveSketchingMethodsforFasterRegularizedLeast-SquaresOptimization

JonathanLacotte(StanfordUniversity)·MertPilanci(Stanford)

46、ReconcilingModernDeepLearningwithTraditionalOptimizationAnalyses:TheIntrinsicLearningRate

ZhiyuanLi(PrincetonUniversity)·KaifengLyu(TsinghuaUniversity)·SanjeevArora(PrincetonUniversity)

47、GaussianProcessBanditOptimizationoftheThermodynamicVariationalObjective

VuNguyen(UniversityofOxford)·VadenMasrani(UniversityofBritishColumbia)·RobBrekelmans(UniversityofSouthernCalifornia)·MichaelAOsborne(UOxford)·FrankWood(UniversityofBritishColumbia)

48、OptimalEpochStochasticGradientDescentAscentMethodsforMin-MaxOptimization

YanYan(theUniversityofIowa)·YiXu(AlibabaGroupU.S.Inc.)·QihangLin(UniversityofIowa)·WeiLiu(TencentAILab)·TianbaoYang(TheUniversityofIowa)

49、ErdosGoesNeural:anUnsupervisedLearningFrameworkforCombinatorialOptimizationonGraphs

50、StochasticOptimizationwithLaggardDataPipelines

NamanAgarwal(Google)·RohanAnil(Google)·TomerKoren(Google)·KunalTalwar(Google)·CyrilZhang(PrincetonUniversity)

51、AFeasibleLevelProximalPointMethodforNonconvexSparseConstrainedOptimization

DigvijayBoob(GeorgiaInstituteofTechnology)·QiDeng(ShanghaiUniversityofFinanceandEconomics)·GuanghuiLan(GeorgiaTech)·YilinWang(ShanghaiUniversityofFinanceandEconomics)

52、ConformalSymplecticandRelativisticOptimization

GuilhermeStarvaggiFranca(UniversityofCalifornia,Berkeley)·JeremiasSulam(JohnsHopkinsUniversity)·DanielRobinson(JohnsHopkinsUniversity)·ReneVidal(JohnsHopkinsUniversity,USA)

53、DirectPolicyGradients:DirectOptimizationofPoliciesinDiscreteActionSpaces

GuyLorberbom(Technion)·ChrisJ.Maddison(UniversityofToronto)·NicolasHeess(GoogleDeepMind)·TamirHazan(Technion)·DanielTarlow(GoogleBrain)

54、ASimpleandEfficientSmoothingMethodforAcceleratedOptimizationandLocalExploration

55、Delta-STN:EfficientBilevelOptimizationofNeuralNetworksusingStructuredResponseJacobians

JuhanBae(UniversityofToronto)·RogerGrosse(UniversityofToronto)

56、FinerMetagenomicReconstructionviaBiodiversityOptimization

SimonFoucart(TexasA&M)·DavidKoslicki(PennsylvaniaStateUniversity)

57、OptimalandPracticalAlgorithmsforSmoothandStronglyConvexDecentralizedOptimization

DmitryKoralev(KAUST)·AdilSALIM(KAUST)·PeterRichtarik(KAUST)

1、InterpretableandPersonalizedApprenticeshipScheduling:LearningInterpretableSchedulingPoliciesfromHeterogeneousUserDemonstrations

RohanPaleja(GeorgiaInstituteofTechnology)·AndrewSilva(GeorgiaInstituteofTechnology)·LetianChen(GeorgiaInstituteofTechnology)·MatthewGombolay(GeorgiaInstituteofTechnology)

2、InterpretableSequenceLearningforCovid-19Forecasting

SercanArik(Google)·Chun-LiangLi(Google)·MartinNikoltchev(Google)·RajarishiSinha(Google)·ArkadyEpshteyn(Google)·JinsungYoon(Google)·LongLe(Google)·VikasMenon(Google)·ShashankSingh(Google)·YashSonthalia(Google)·HootanNakhost(Google)·LeyouZhang(Google)·ElliKanal(Google)·TomasPfister(Google)

3、IncorporatingInterpretableOutputConstraintsinBayesianNeuralNetworks

WanqianYang(HarvardUniversity)·LarsLorch(Harvard)·MoritzGraule(HarvardUniversity)·HimabinduLakkaraju(Harvard)·FinaleDoshi-Velez(Harvard)

4、ICAM:InterpretableClassificationviaDisentangledRepresentationsandFeatureAttributionMapping

5、HowdoesthisinteractionaffectmeInterpretableattributionforfeatureinteractions

MichaelTsang(UniversityofSouthernCalifornia)·SirishaRambhatla(UniversityofSouthernCalifornia)·YanLiu(UniversityofSouthernCalifornia)

6、LearningoutsidetheBlack-Box:Thepursuitofinterpretablemodels

JonathanCrabbe(UniversityofCambridge)·YaoZhang(UniversityofCambridge)·WilliamZame(UCLA)·MihaelavanderSchaar(UniversityofCambridge)

7、GANSpace:DiscoveringInterpretableGANControls

8、Interpretablemulti-timescalemodelsforpredictingfMRIresponsestocontinuousnaturalspeech

ShaileeJain(TheUniversityofTexasatAustin)·VyVo(IntelCorporation)·ShivangiMahto(TheUniversityofTexasatAustin)·AmandaLeBel(TheUniversityofTexasatAustin)·JavierTurek(IntelLabs)·AlexanderHuth(TheUniversityofTexasatAustin)

9、Learningidentifiableandinterpretablelatentmodelsofhigh-dimensionalneuralactivityusingpi-VAE

DingZhou(ColumbiaUniversity)·Xue-XinWei(UniversityofPennsylvania)

10、TowardsInterpretableNaturalLanguageUnderstandingwithExplanationsasLatentVariables

WangchunshuZhou(BeihangUniversity)·JinyiHu(TsinghuaUniversity)·HanlinZhang(SouthChinaUniversityofTechnology)·XiaodanLiang(SunYat-senUniversity)·MaosongSun(TsinghuaUniversity)·ChenyanXiong(MicrosoftResearchAI)·JianTang(Mila)

1、Decisions,CounterfactualExplanationsandStrategicBehavior

StratisTsirtsis(MPI-SWS)·ManuelGomezRodriguez(MaxPlanckInstituteforSoftwareSystems)

2、ModelAgnosticMultilevelExplanations

KarthikeyanNatesanRamamurthy(IBMResearch)·BhanukiranVinzamuri(IBMResearch)·YunfengZhang(IBMResearch)·AmitDhurandhar(IBMResearch)

3、PGM-Explainer:ProbabilisticGraphicalModelExplanationsforGraphNeuralNetworks

4、OnCompleteness-awareConcept-BasedExplanationsinDeepNeuralNetworks

Chih-KuanYeh(CarnegieMellonUniversity)·BeenKim(Google)·SercanArik(Google)·Chun-LiangLi(Google)·TomasPfister(Google)·PradeepRavikumar(CarnegieMellonUniversity)

5、DebuggingTestsforModelExplanations

JuliusAdebayo(MIT)·MichaelMuelly(StanfordUniversity)·IlariaLiccardi(MIT)·BeenKim(Google)

6、HowCanIExplainThistoYouAnEmpiricalStudyofDeepNeuralNetworkExplanationMethods

JeyaVikranthJeyakumar(UniversityofCalifornia,LosAngeles)·JosephNoor(UniversityofCalifornia,LosAngeles)·Yu-HsiCheng(UCLA)·LuisGarcia(UniversityofCalifornia,LosAngeles)·ManiSrivastava(UCLA)

7、TowardsInterpretableNaturalLanguageUnderstandingwithExplanationsasLatentVariables

8、Generativecausalexplanationsofblack-boxclassifiers

9、CompositionalExplanationsofNeurons

JesseMu(StanfordUniversity)·JacobAndreas(MIT)

10、LearningGlobalTransparentModelsconsistentwithLocalContrastiveExplanations

TejaswiniPedapati(IBMResearch)·AvinashBalakrishnan(IBM)·KarthikeyanShanmugam(IBMResearch,NY)·AmitDhurandhar(IBMResearch)