LearningtoCollaborateinMarkovDecisionProcessesGoranRadanovic1RatiDevidze2DavidC.Parkes1AdishSingla2AbstractWeexpectthatusefulcollaborationwillcomeaboutthroughAIagentsthatcanadapttothebehaviorofuser...
Learningtobidinrevenue-maximizingauctionsThomasNedelec12NoureddineElKaroui31VianneyPerchet21Abstractmaximizingauctions.Thisisanewargumentsupport-ingtheWilsondoctrine(Wilson,1987)claimingthatdata-We...
LearningandDataSelectioninBigDatasetsHosseinS.Ghadikolaei1HadiGhauch12CarloFischione1MikaelSkoglund1Abstractmodel.Studyingitsbehavioraroundthosecriticalsampleshelpsustobetterunderstandtheunknownmod...
Kernel-BasedReinforcementLearninginRobustMarkovDecisionProcessesShiauHongLim1ArnaudAutef2AbstractThisclassincludeskernelaveraging,k-nearest-neighbor,weightedk-nearestneighbor,Bezierpatches,linearin...
information-TheoreticConsiderationsinBatchReinforcementLearningJinglinChen1NanJiang1AbstractwhentheyworkiscentraltoourunderstandingofRL.Ex-istingworksthatanalyzeerrorpropagationandfinitesam-Value-f...
inferringHeterogeneousCausalEffectsinPresenceofSpatialConfoundingMuhammadOsama1DaveZachariah1ThomasB.Scho¨n1Abstract1.5cWeaddresstheproblemofinferringthecausal1effectofanexposureonanoutcomeacrosss...
ImputingMissingEventsinContinuous-TimeEventStreamsHongyuanMei1GuanghuiQin2JasonEisner1Abstract•Medicalrecords.Somepatientsrecorddetailedsymp-toms,self-administeredmedications,diet,andsleep.Eventsi...
HumorinWordEmbeddings:CockamamieGobbledegookforNincompoopsWARNinG:Thispapercontainswordsthatpeopleratedhumorousincludingmanythatareoffensiveinnature.LimorGultchin1GenevievePatterson2NancyBaym3Natha...
Grid-WiseControlforMulti-AgentReinforcementLearninginVideoGameAILeiHan1PengSun1YaliDu23JiechaoXiong1QingWang1XinghaiSun1HanLiu4TongZhang5Abstractetal.,2016),etc.Amongthese,RLingameAIresearchattract...
GlobalConvergenceofBlockCoordinateDescentinDeepLearningJinshanZeng12TimTsz-KitLau3Shao-BoLin4YuanYao2AbstractinGogames(Silveretal.,2016).DeeplearninghasarousedextensiveattentiondueThepracticaloptim...
GeometryandSymmetryinShort-and-SparseDeconvolutionHan-WenKuo12YuqianZhang3YensonLau12JohnWright124AbstractMotivatedbytheseandrelatedproblemsinimagingandWestudytheShort-and-Sparse(SaS)deconvo-scient...
Garbagein,RewardOut:BootstrappingExplorationinMulti-ArmedBanditsBranislavKveton1CsabaSzepesva´ri23SharanVaswani4ZhengWen5MohammadGhavamzadeh6TorLattimore2Abstract2013b)isageneralizationofamulti-ar...
Garbagein,RewardOut:BootstrappingExplorationinMulti-ArmedBanditsBranislavKveton1CsabaSzepesva´ri23SharanVaswani4ZhengWen5MohammadGhavamzadeh6TorLattimore2Abstract2013b)isageneralizationofamulti-ar...
FlatMetricMinimizationwithApplicationsinGenerativeModelingThomasMo¨llenhoff1DanielCremers1Abstractfromlefttorightwevarythelatentcodez1(time)WetakethenovelperspectivetoviewdatanotFigure1.Discoverin...
FaultToleranceinIterative-ConvergentMachineLearningAurickQiao12BryonAragam3BingjingZhang1EricP.Xing123AbstractMachinelearning(ML)trainingalgorithmsoftenpossessaninherentself-correctingbehaviordueto...
FastDirectSearchinanOptimallyCompressedContinuousTargetSpaceforEfficientMulti-LabelActiveLearningWeishiShi1QiYu1Abstractretrievalandorganization.UsersfromQ&Awebsites,suchasstackoverflowandQuora,are...
ExploitingWorkerCorrelationforLabelAggregationinCrowdsourcingYuanLi1BenjaminI.P.Rubinstein1TrevorCohn1Abstractequalvotestowardsconsensus.Numerousprobabilisticmodelshaveemergedthatparameteriseworker...
EstimatinginformationFlowinDeepNeuralNetworksZivGoldfeld12EwoutvandenBerg23KristjanGreenewald23IgorMelnyk23NamNguyen23BrianKingsbury23YuryPolyanskiy12Abstractetal.,2018;Achille&Soatto,2018).Mutuali...
EigenDamage:StructuredPruningintheKronecker-FactoredEigenbasisChaoqiWang12RogerGrosse12SanjaFidler123GuodongZhang12AbstractOriginalWeightspaceinput(32x32x512)Reducingthetesttimeresourcerequirements...
DynamicWeightsinMulti-ObjectiveDeepReinforcementLearningAxelAbels12DiederikM.Roijers3TomLenaerts12AnnNowe´2DenisSteckelmacher2Abstractasalinearscalarizationwithweightsperobjectivethatareknowninadv...