WhatMakesforEnd-to-EndObjectDetection?PeizeSun1YiJiang2EnzeXie1WenqiShao3ZehuanYuan2ChanghuWang2PingLuo1AbstractFigure1.End-to-endobjectdetection.Non-end-to-endobjectdetectorsrequireNMStoremoveredu...
Weight-CovarianceAlignmentforAdversariallyRobustNeuralNetworksPanagiotisEustratiadis1HenryGouk1DaLi12TimothyHospedales12Abstract2013).Inordertotacklethisproblem,manyadversarialdefensealgorithmshave...
Voice2Series:ReprogrammingAcousticModelsforTimeSeriesClassificationChao-HanHuckYang1Yun-YunTsai2Pin-YuChen3AbstracttargetreprogrammedsourceoutputtargetoutputLearningtoclassifytimeserieswithlimitedd...
WassersteinDistributionalNormalizationforRobustDistributionalCertificationofNoisyLabeledDataSungWooPark1JunseokKwon1AbstractWhilethereareseveralmethodsthatcandealwithnoisy-labeleddata,recentmethods...
VectorQuantizedModelsforPlanningSherjilOzair12YazheLi1AliRazavi1IoannisAntonoglou1AäronvandenOord1OriolVinyals1AbstractDota2(OpenAIetal.,2019)andStarCraftII(Vinyalsetal.,2019),orrobotics(OpenAIeta...
VariationalEmpowermentasRepresentationLearningforGoal-BasedReinforcementLearningJongwookChoi†1ArchitSharma†2HonglakLee13SergeyLevine45ShixiangShaneGu4Abstract1IntroductionLearningtoreachgoalstate...
VariationalAuto-RegressiveGaussianProcessesforContinualLearningSanyamKapoor1TheofanisKaraletsos2ThangD.Bui3Abstract(a)VAR-GP(ours)Throughsequentialconstructionofposteriorson(b)VCL(withcoresetsize10...
VarianceReducedTrainingwithStratifiedSamplingforforecastingModelsYuchengLu12YoungsukPark2LifanChen2YuyangWang2ChristopherDeSa1DeanFoster34Abstract2004)arethefolkloremethodsformodelingthedynamicsofa...
UnsupervisedLearningofVisual3DKeypointsforControlBoyuanChen1PieterAbbeel1DeepakPathak2AbstractFigure1.Weproposeanend-to-endframeworkforunsupervisedlearningof3Dkeypointsfrommulti-viewimages.Thesekey...
UneVEn:UniversalValueExplorationforMulti-AgentReinforcementLearningTarunGupta1AnujMahajan1BeiPeng1WendelinBo¨hmer2ShimonWhiteson1Abstractfactorization,thejointactionvaluefunctioncanbedecen-trallym...
UnICORNN:ArecurrentmodelforlearningverylongtimedependenciesT.KonstantinRusch1SiddharthaMishra1AbstractsuchasinLSTMs(Hochreiter&Schmidhuber,1997)andGRUs(Choetal.,2014),wheretheadditivestructureofThe...
UncertaintyWeightedActor-CriticforOfflineReinforcementLearningYueWu12ShuangfeiZhai1NitishSrivastava1JoshuaSusskind1JianZhang1RuslanSalakhutdinov2HanlinGoh1Abstractleveragingpriorexperience(Langeeta...
TreeswithAttentionforSetPredictionTasksRoyHirsch1RanGilad-Bachrach2AbstractTree-basedmodels,suchasDecisionTree(DT),Randomforest(RF)andGradientBoostingDecisionTree(GBT)Inmanymachinelearningapplicati...
TrajectoryDiversityforZero-ShotCoordinationAndreiLupu1BrandonCui2HengyuanHu2JakobFoerster2AbstractFigure1:Thecorridorcoordinationtaskadmitsthreeopti-malSPpolicies,onlyoneofwhichissuitableforZSC.Wes...
TrainingDataSubsetSelectionforRegressionWithControlledGeneralizationErrorDurgaSivasubramanian1RishabhIyer2GaneshRamakrishnan1AbirDe1Abstractreliabilityofthelearnedmodel.Therefore,thesuccessofsevera...
TowardsPracticalMeanBoundsforSmallSamplesMyPhan1PhilipS.Thomas1ErikLearned-Miller1Abstractrefertotwoseparatesettings,theone-endedsupportsetting,inwhichthedistributionisknowntofallintheintervalHisto...
TheoryofSpectralMethodforUnionofSubspaces-BasedRandomGeometryGraphGenLi1YuantaoGu1AbstracttaskinprocessingdatapointsinUoSistoclusterthesedatapoints,whichisknownasSubspaceClustering(SC).Appli-Spectr...
ThePowerofAdaptivityforStochasticSubmodularCoverRohanGhuge1AnupamGupta2ViswanathNagarajan1Abstractsoleimanetal.,2015;Batenietal.,2018):herearetwoexamplesfromsensordeploymentandmedicaldiagnosis.Inth...
TheImplicitRegularizationforAdaptiveOptimizationAlgorithmsonHomogeneousNeuralNetworksBohanWang1QiMeng1WeiChen1Tie-YanLiu1Abstractprocessing(Youngetal.,2018).Inpractice,deepneuralnetworks(DNN)learne...
TheEarthMover’sPinballLoss:QuantilesforHistogram-ValuedRegressionFlorianList1AbstractFigure1.ComicofourmethodforDeepLearning-basedhistogramregression:aneuralnetwork(NN)fθwithweightsθistrainedAlt...