GloballyOptimalGradientDescentforaConvNetwithGaussianInputsAlonBrutzkus1AmirGloberson1Abstractcentattemptstobridgethisgapbetweentheoryandprac-tice.SeveralworksfocusonthegeometricpropertiesofDeeplea...
FasterGreedyMAPInferenceforDeterminantalPointProcessesInsuHan1PrabhanjanKambadur2KyoungsooPark1JinwooShin1Abstractposedetection(Kuleszaetal.,2012),clustering(Kang,2013)andtweettime-linegeneration(Y...
FeUdalNetworksforHierarchicalReinforcementLearningAlexanderSashaVezhnevets1SimonOsindero1TomSchaul1NicolasHeess1MaxJaderberg1DavidSilver1KorayKavukcuoglu1Abstractchallenging,sincetheagenthastolearn...
FastBayesianIntensityEstimationforthePermanentalProcessChristianJ.Walder12AdrianN.Bishop123Abstractin(Lloydetal.,2015;KomSamo&Roberts,2015).TheCoxprocessisastochasticprocesswhichTosatisfynon-negati...
ExactInferenceforIntegerLatent-VariableModelsKevinWinner1DeboraSujono1DanSheldon12Abstractever,thissituationisrareandconsequently,muchresearchtodayisdevotedtogeneral-purposeapproximateinferenceGrap...
End-to-EndLearningforStructuredPredictionEnergyNetworksDavidBelanger1BishanYang2AndrewMcCallum1Abstractminimization(LeCunetal.,2006):StructuredPredictionEnergyNetworks(SPENs)yˆ=argminEx(y),(1)area...
EfficientsoftmaxapproximationforGPUsE´douardGrave1ArmandJoulin1MoustaphaCisse´1DavidGrangier1Herve´Je´gou1Abstractbyobjectivecriteriasuchasperplexity(ppl),whichdirectlymeasurestheabilityofthesy...
DoublyAcceleratedMethodsforFasterCCAandGeneralizedEigendecompositionZeyuanAllen-Zhu1YuanzhiLi2Abstracttraditionof(Wangetal.,2016;Garber&Hazan,2015),weassumewithoutlossofgeneralitythatλi∈[−1,1].W...
DoublyGreedyPrimal-DualCoordinateDescentforSparseEmpiricalRiskMinimizationQiLei1IanE.H.Yen2Chao-yuanWu3InderjitS.Dhillon134PradeepRavikumar2Abstractwhen(z)=max{0,1bz}andg(x)=µ/2kxk22,(1)iiWeconsid...
DistributedandProvablyGoodSeedingsfork-MeansinConstantRoundsOlivierBachem1MarioLucic1AndreasKrause1Abstracttheoreticalguaranteeonthesolutionqualitywhilethesub-sequentrefinementusingLloyd’salgorith...
DissipativityTheoryforNesterov’sAcceleratedMethodBinHu1LaurentLessard1Abstracttories.OnceaLyapunovfunctionisfound,onecanrelatetherateofdecreaseofthisinternalenergytotherateofInthispaper,weadaptthe...
DeeplyAggreVaTeD:DifferentiableImitationLearningforSequentialPredictionWenSun1ArunVenkatraman1GeoffreyJ.Gordon2ByronBoots3J.AndrewBagnell1Abstractoptimizeforalossacquiredonlyaftermanypredictions.Re...
DeltaNetworksforOptimizedRecurrentNetworkComputationDanielNeil1JunHaengLee2TobiDelbruck1Shih-ChiiLiu1AbstractthroughsintheuseofRNNsforprocessingoftemporalse-quences.Applicationssuchasnaturallanguag...
DeepBach:aSteerableModelforBachChoralesGenerationGae¨tanHadjeres12Franc¸oisPachet12FrankNielsen3AbstractMoreover,sincetheaimofreharmonizingamelodyistogivemorepowerornewinsightstoitstext,thelyrics...
DeepIV:AFlexibleApproachforCounterfactualPredictionJasonHartford1GregLewis2KevinLeyton-Brown1MattTaddy2Abstractdatatooptimizethepricesitchargesitscustomers:inthiscase,priceisthetreatmentvariableand...
DeepGenerativeModelsforRelationalDatawithSideInformationChangweiHu1PiyushRai2LawrenceCarin3Abstractofaccomplishingthisisbyembeddingthenodesinala-tentspacevialatentspacemodels(Hoffetal.,2002).Wepres...
CouplingDistributedandSymbolicExecutionforNaturalLanguageQueriesLiliMou1ZhengdongLu2HangLi3ZhiJin1AbstractQuery:Howlongisthegamewiththelargesthostcountrysize?Buildingneuralnetworkstoqueryaknowledge...
CounterfactualData-FusionforOnlineReinforcementLearnersAndrewforney1JudeaPearl1EliasBareinboim2AbstractInthiswork,westudytheconditionsunderwhichdatacol-lectedunderheterogeneousconditions(tobedefine...
CoresetsforVectorSummarizationwithApplicationstoNetworkGraphsDanFeldman1SedatOzer2DanielaRus2Abstractgroups,gatheringplaces,collectiveactivitypatterns,etc.Thereareseveralkeychallengestoachievethese...
ConsistencyAnalysisforBinaryClassificationRevisitedKrzysztofDembczyn´ski1WojciechKotłowski1OluwasanmiKoyejo2NagarajanNatarajan3Abstracttice(Koyejoetal.,2014a;Narasimhanetal.,2014a;Dem-bczyn´skie...