ReinforcementLearninginConfigurableContinuousEnvironmentsAlbertoMariaMetelli1EmanueleGhelfi1MarcelloRestelli1AbstractasaConfigurableMarkovDecisionProcess(Conf-MDP,Metellietal.,2018).Asintraditional...
RecurrentKalmanNetworks:FactorizedinferenceinHigh-DimensionalDeepFeatureSpacesPhilippBecker123HaritPandya4GregorGebhardt1ChengZhao5JamesTaylor6GerhardNeumann423Abstract1.introductioninordertointegr...
QuantifyingGeneralizationinReinforcementLearningKarlCobbe1OlegKlimov1ChrisHesse1TaehoonKim1JohnSchulman1Abstract(Nicholetal.,2018),weseektobetterquantifyanagent’sabilitytogeneralize.inthispaper,we...
PhasetransitioninPCAwithmissingdata:Reducedsignal-to-noiseratio,notsamplesize!NielsBruunIpsen1LarsKaiHansen1Abstract(1999)andthisformulationallowsforestimatingprincipalcomponentsinthepresenceofmiss...
PACLearnabilityofNodeFunctionsinNetworkedDynamicalSystemsAbhijinAdiga1ChrisJ.Kuhlman1MadhavV.Marathe12S.S.Ravi13AnilK.Vullikanti12Abstract(Beietal.,2016;Kleinbergetal.,2017;Adigaetal.,2018).Weconsi...
PACIdentificationofManyGoodArmsinStochasticMulti-ArmedBanditsArghyaRoyChaudhuri1ShivaramKalyanakrishnan1Abstractdecision,whichproducesareal-valuedreward.Therewardisdrawni.i.d.fromadistributioncorre...
OvercomingMean-FieldApproximationsinRecurrentGaussianProcessModelsAlessandroDavideIalongo12MarkvanderWilk3JamesHensman3CarlEdwardRasmussen1Abstractthedistributionoftheoutcome(vonNeumannetal.,1944)....
Open-endedLearninginSymmetricZero-sumGamesDavidBalduzzi1MartaGarnelo1YoramBachrach1WojciechM.Czarnecki1JulienPerolat1MaxJaderberg1ThoreGraepel1Abstractofwhattesttotake,orwhatobjectivetooptimize,isn...
OnlineConvexOptimizationinAdversarialMarkovDecisionProcessesAvivRosenberg1YishayMansour12AbstractWeproposeanovelalgorithmfortheadversarialMDPmodelwherethetransitionfunctionisunknowntotheWeconsidero...
OnThePowerofCurriculumLearninginTrainingDeepNetworksGuyHacohen12DaphnaWeinshall1Abstracttypicallyreflectstheircomplexity.Thestudentisthengrad-uallyintroducedtotheseconceptsbyincreasingcomplexity,Tr...
OntheGeneralizationGapinReparameterizableReinforcementLearningHuanWang1StephanZheng1CaimingXiong1RichardSocher1Abstract2018a).Amodelthatperformswellinthetrainingenvi-ronment,mayormaynotperformwellw...
OnSparseLinearRegressionintheLocalDifferentialPrivacyModelDiWang1JinhuiXu1Abstractsciences(Marascuilo&Serlin,1988),genomicsresearch(Bu˘žková,2013)andsignalrecovery(Bühlmann&Vaninthispaper,westu...
OnConnectedSublevelSetsinDeepLearningQuynhNguyen1Abstractcontinuouspathfromanystartingpointinparameterspaceonwhichthelossisnon-increasingandgetsarbitrarilycloseThispapershowsthateverysublevelsetoft...
NaturalAnalystsinAdaptiveDataAnalysisTijanaZrnic1MoritzHardt1Abstract1.introductionAdaptivedataanalysisisfrequentlycriticizedforModerndataanalysisisusuallyadaptiveinthesensethatitspessimisticgenera...
MeasurementsofThree-LevelHierarchicalStructureintheOutliersintheSpectrumofDeepnetHessiansVardanPapyan1Abstract(f(xi,c;θ),yc)∈R+isthecross-entropylossbetweenthesoftmaxoff(xi,c;θ)andtheone-hotvect...
Matrix-FreePreconditioninginOnlineLearningAshokCutkosky1TamasSarlos1AbstractOurgoalistoobtainadaptiveregretboundssothatRT(w˚)maybemuchsmallerineasierproblemswhilestillmaintain-Weprovideanonlinecon...
LeveragingLow-RankRelationsBetweenSurrogateTasksinStructuredPredictionGiuliaLuise1DimitrisStamos1MassimilianoPontil12CarloCiliberto13AbstractAmongthemostwell-establishedstrategiesforstructuredpredi...
LexicographicandDepth-SensitiveMarginsinHomogeneousandNon-HomogeneousDeepModelsMorShpigelNacson1SuriyaGunasekar2JasonD.Lee3NathanSrebro2DanielSoudry1Abstractimaofthetraininglossindeedhaveveryhighte...
LearningtoRouteinSimilarityGraphsDmitryBaranchuk12DmitryPersiyanov3AntonSinitsin14ArtemBabenko14AbstractThecurrentapproachesforefficientNNSmostlybelongtothreeseparatelinesofresearch.Thefirstfamilyo...
LearningtoExploitLong-termRelationalDependenciesinKnowledgeGraphsLingbingGuo1ZequnSun1WeiHu1Abstractsamereal-worldobject;and(ii)KGcompletion,a.k.a.linkprediction,whichaimstocompletethemissingfactsi...