RegularizedOnlineAllocationProblems:FairnessandBeyondSantiagoBalseiro12HaihaoLu32VahabMirrokni2Abstractapublishertypicallysignscontractswithmanyadvertisersagreeingtodeliverafixednumberofimpressions...
Multi-AgentTrainingBeyondZero-SumwithCorrelatedEquilibriumMeta-SolversLukeMarris12PaulMuller13MarcLanctot1KarlTuyls1ThoreGraepel12AbstractAvisetal.,2010;Harsanyi&Selten,1988).2Two-player,constant-s...
GlobalOptimalityBeyondTwoLayers:TrainingDeepReLUNetworksviaConvexProgramsTolgaErgen1MertPilanci1AbstractOutputUnderstandingthefundamentalmechanismbe-Inputhindthesuccessofdeepneuralnetworksisoneofth...
Beyondlog2(T)RegretforDecentralizedBanditsinMatchingMarketsSoumyaBasu1KarthikAbinavSankararaman2AbishekSankararaman3Abstractbanditsisdedicatedtounderstandingalgorithmicprinciplesintheinterplayofcom...
BeyondVarianceReduction:UnderstandingtheTrueImpactofBaselinesonPolicyOptimizationWesleyChung1ValentinThomas2MarlosC.Machado345NicolasLeRoux612Abstract&Cesa-Bianchi,2012).Whiletheformermeasureisofte...
BeyondtheParetoEfficientFrontier:ConstraintActiveSearchforMultiobjectiveExperimentalDesignGustavoMalkomes1BolongCheng1EricHansLee1MichaelMcCourt1AbstractInrecentyears,activelearninghasgainedpopular...
ComposableSketchesforFunctionsofFrequencies:BeyondtheWorstCaseEdithCohen12OfirGeri34RasmusPagh156Abstractdatawithsmallcomputationalresources(time,communi-cation,andspace).Suchsketchessupportprocess...
BeyondUCB:OptimalandEfficientContextualBanditswithRegressionOraclesDylanJ.Foster1AlexanderRakhlin1Abstractible,generalpurposealgorithmsthatworkforarbitrary,user-specifiedclassesofpoliciesandcomewit...
BeyondSignalPropagation:IsFeatureDiversityNecessaryinDeepNeuralNetworkInitialization?YanivBlumenfeld1DarGilboa2DanielSoudry1Abstractadetailedanalysisoftheirdynamicsandgeneralizationproperties.Unlik...
BeyondSyntheticNoise:DeepLearningonControlledNoisyLabelsLuJiang1DiHuang2MasonLiu3WeilongYang1AbstractHowever,duetothelackofsuitabledatasets,previousworkhasonlyexaminedDNNsoncontrolledsyntheticlabel...
SubmodularMaximizationBeyondNon-negativity:Guarantees,FastAlgorithms,andApplicationsChristopherHarshaw1MoranFeldman2JustinWard3AminKarbasi4Abstract1.IntroductionItisgenerallybelievedthatsubmodularf...
ExtrapolatingBeyondSuboptimalDemonstrationsviaInverseReinforcementLearningfromObservationsDanielS.Brown1WonjoonGoo1PrabhatNagarajan2ScottNiekum1AbstractFigure1.T-REXtakesasequenceofrankeddemonstrat...
BeyondBackprop:OnlineAlternatingMinimizationwithAuxiliaryVariablesAnnaChoromanska1BenjaminCowen1SadhanaKumaravel2RonnyLuss2MattiaRigotti2IrinaRish2BrianKingsbury2PaoloDiAchille2ViatcheslavGurev2Rav...
BeyondtheChineseRestaurantandPitman-Yorprocesses:StatisticalModelswithdoublepower-lawbehaviorFadhelAyed1JuhoLee12Franc¸oisCaron1Abstractbyapower-lawdistribution,anobservationattributedtoZipf(1935)...
BeyondAdaptiveSubmodularity:ApproximationGuaranteesofGreedyPolicywithAdaptiveSubmodularityRatioKaitoFujii1ShinsakuSakaue2Abstractrecommendation(Gabillonetal.,2013),andtouch-basedlocalizationinrobot...
PathwiseDerivativesBeyondtheReparameterizationTrickMartinJankowiak1FritzObermeyer1AbstractWerevisittheclassofgradientestimatorspopularizedin(Kingma&Welling,2013;Rezendeetal.,2014;Titsias&Weobservet...
InterpretabilityBeyondFeatureAttribution:QuantitativeTestingwithConceptActivationVectors(TCAV)BeenKimMartinWattenbergJustinGilmerCarrieCaiJamesWexlerFernandaViegasRorySayresAbstractcoefficientweigh...
BeyondFiniteLayerNeuralNetworks:BridgingDeepArchitecturesandNumericalDifferentialEquationsYipingLu1AoxiaoZhong2QuanzhengLi234BinDong564Abstractswhilemaintainingasimilarperformance.Thiscanbeexplaine...
BeyondtheOne-StepGreedyApproachinReinforcementLearningYonathanEfroni1GalDalal1BrunoScherrer2ShieMannor1Abstractsuggestedthatgreedyapproachesw.r.t.multiplestepsper-formbetterthanw.r.t.1-step.Notable...
Beyond1/2-ApproximationforSubmodularMaximizationonMassiveDataStreamsAshkanNorouzi-Fard1JakubTarnawski1SlobodanMitrovic´1AmirZandieh1AidasadatMousavifar1OlaSvensson1Abstractstreams,sensordata,socia...