AnIterative,Sketching-basedFrameworkforRidgeRegressionAgnivaChowdhury1JiasenYAng1PetrosDrineas2Abstractsion.First,whendn,i.e.,thenumberofpredictorvari-ablesdgreatlyexceedsthenumberofobservationsn,...
AnEstimationAndAnalysisFrameworkfortheRaschModelAndrewS.LAn1MungChiAng2ChristophStuder3Abstractresponsetheory(IRT)model(Lord,1980),isgivenbyTheRaschmodeliswidelyusedforitemre-p(Yu,i=1)=Φ(au−di),(...
AnInference-BasedPolicyGradientMethodforLearningOptionsMatthewJ.A.Smith1HerkeVAnHoof2JoellePineau1Abstractatvariouslevelsofabstraction,itispossibletoinfer,learnAndplAnmuchmoreefficiently.Further,ab...
AnEfficient,GeneralizedBellmAnUpdateForCooperativeInverseReinforcementLearningDhruvMalik1MalayAndiPalAniappAn1JaimeF.Fisac1DylAnHadfield-Menell1StuartRussell1AncaD.DragAn1AbstractFigure1.ACIRLgame....
AnAlternativeView:WhenDoesSGDEscapeLocalMinima?RobertKleinberg1YuAnzhiLi2YAngYuAn1Abstractmoreiterationstoconverge,butfewergradientevaluationsperiteration.Therefore,forthestAndardempiricalriskmin-S...
AnAlgorithmicFrameworkofVariableMetricOver-RelaxedHybridProximalExtra-GradientMethodLiShen1PengSun1YitongWAng1WeiLiu1TongZhAng1AbstracttimizationAndconvex-concavesaddle-pointoptimization,encompasse...
AnEfficientSemismoothNewtonBasedAlgorithmforConvexClusteringYAnchengYuAn1DefengSun2Kim-ChuAnToh3AbstractwhichisnotavailableinmAnyrealapplications.There-fore,inrealapplications,k-meAnsistypicallytri...
ActiveTesting:AnEfficientAndRobustFrameworkforEstimatingAccuracy.PhucNguyen1DevaRamAnAn2CharlessFowlkes1AbstractnoisyvettedSampleOracledatabaseSelectionMuchrecentworkonvisualrecognitionaimstoSystem...
WorldofBits:AnOpen-DomainPlatformforWeb-BasedAgentsTiAnlin(Tim)Shi12AndrejKarpathy2Linxi(Jim)FAn1JonathAnHernAndez2PercyLiAng1AbstractFigure1.AgentsintheWorldofBitsperceivethescreenpixels,theDOM(wi...
iSurvive:AnInterpretable,Event-timePredictionModelformHealthWalterH.Dempsey1AlexAnderMoreno2ChristyK.Scott3MichaelL.Dennis3DavidH.Gustafson4SusAnA.Murphy1JamesM.Rehg2Abstractmeasurements;And(3)Para...
InputSwitchedAffineNetworks:AnRNNArchitectureDesignedforInterpretabilityJakobN.Foerster1JustinGilmer2JaschaSohl-Dickstein3JAnChorowski4DavidSussillo3AbstractquiringinterpretableMLincludeself-drivin...
AnInfiniteHiddenMarkovModelWithSimilarity-BiasedTrAnsitionsColinReimerDawson1ChaofAnHuAng1ClaytonT.Morrison2Abstractinga“stick”offoftheremainingweightaccordingtoaBeta(1,γ)distribution.Theparamet...
AnEfficient,Sparsity-Preserving,OnlineAlgorithmforLow-RAnkApproximationDavidAnderson1MingGu1AbstractAdditionally,arecenttrendinmachinelearningistoin-cludeAnapproximationofsecondorderinformationforL...
AnAlternativeSoftmaxOperatorforReinforcementLearningKavoshAsadi1MichaelL.LittmAn1AbstractAnidealsoftmaxoperatorisaparameterizedsetofoperatorsthat:Asoftmaxoperatorappliedtoasetofvaluesactssomewhatli...
AnAnalyticalFormulaofPopulationGradientfortwo-layeredReLUnetworkAnditsApplicationsinConvergenceAndCriticalPointAnalysisYuAndongTiAn1AbstractAndwhysimplemethodslikegradientdescentcAnsolvethecomplica...
AnAdaptiveTestofIndependencewithAnalyticKernelEmbeddingsWittawatJitkrittum1ZoltánSzabó2ArthurGretton1AbstractAbasicnonlineardependencemeasureistheHilbert-SchmidtIndependenceCriterion(HSIC),whichi...