PretrainedGeneralizedAutoregressiveModelwithAdaptiveProbabilisticLabelClustersforExtremeMulti-labelTextClassificationHuiYe1ZhiyuChen1Da-HanWang2BrianD.Davison1Abstracttextfeaturesisbag-of-words(BOW...
PreferenceModelingwithContext-DependentSalientFeaturesAmandaBower1LauraBalzano2Abstractmodelsaddressthisissuewithmodelingnoise,ignoringitssystematicnature.Weobserve,asothershavebeforeusWeconsiderth...
PredictiveSamplingwithForecastingAutoregressiveModelsAukeWiggers1EmielHoogeboom23AbstractFigure1.Overviewofpredictivesampling.Asequence-so-farofARMsamplesx0,...,xi−1isextendedwithforecastsAutoregr...
PredictingChoicewithSet-DependentAggregationNirRosenfeld1KojinOshiba1YaronSinger1Abstractofitemss={x(1),...,x(n)},x(i)∈X=Rd,calledthechoiceset,withs∈S⊆2X.Fromthealternativesins,theProvidingusers...
PEGASUS:Pre-trainingwithExtractedGap-sentencesforAbstractiveSummarizationJingqingZhang1YaoZhao2MohammadSaleh2PeterJ.Liu2AbstractRecentworkpre-trainingTransformerswithFigure1:ThebasearchitectureofPE...
AnInvestigationofWhyOverparameterizationExacerbatesSpuriousCorrelationsShioriSagawa1AditiRaghunathan1PangWeiKoh1PercyLiang1AbstractUnderparameterizedOverparameterizedWestudywhyoverparameterization...
OptimizingDynamicStructureswithBayesianGenerativeSearchMinhHoang1CarlKingsford2Abstractspaceofarchitecturesencompassesneuralnetworkdesignchoicessuchasthenumberofhiddenlayers,dimensionKernelselectio...
OptimizingBlack-boxMetricswithAdaptiveSurrogatesQijiaJiang1OlaoluwaAdigun2HarikrishnaNarasimhan3MahdiMilaniFard3MayaGupta3Abstractinformationbeusedtoinfluencethetrainingloss?Similarexamplesalsoaris...
OptimisticPolicyOptimizationwithBanditFeedbackYonathanEfroni1LiorShani1AvivRosenberg2ShieMannor1AbstractDuetotheirpopularity,thereisarichliteraturethatpro-videsdifferenttypesoftheoreticalguarantees...
OnlinePricingwithOfflineData:PhaseTransitionandInverseSquareLawJinzhiBu1DavidSimchi-Levi1YunzongXu1Abstractofflinehistoricaldataset(basedonhistoricalactions)atthetimethatthelearnerstartsanonlinelea...
OnlineMetricAlgorithmswithUntrustedPredictionsAntoniosAntoniadis1ChristianCoester2asdatacenters(Iranietal.,2003;Linetal.,2013),andareMarekElia´sˇ3AdamPolak4BertrandSimon5alsorelatedtotheexpertspr...
OnlineMulti-KernelLearningwithGraph-StructuredFeedbackPouyaMGhari1YanningShen1Abstractwhilethedata-drivenmulti-kernellearning(MKL)approachismorepowerful,asitlearnstheoptimalkernelfromadic-Multi-ker...
OnlineLearningwithDependentStochasticFeedbackGraphsCorinnaCortes1GiuliaDeSalvo1ClaudioGentile1MehryarMohri1NingshanZhang2AbstractofonlinelearningintroducedbyMannor&Shamir(2011),wherelossobservabili...
OnlineLearningwithImperfectHintsAdityaBhaskara1AshokCutkosky23RaviKumar2ManishPurohit2Abstracthencedesirable.Theframeworkofonlineconvexoptimiza-tionisquitepowerful,general,andhasbeenextensivelyWeco...
OnlineLearnedContinualCompressionwithAdaptiveQuantizationModulesLucasCaccia123EugeneBelilovsky42MassimoCaccia425JoellePineau123Abstractetal.,2017;Balle´etal.,2016;Johnstonetal.,2018).Yetitsapplica...
OnThompsonSamplingwithLangevinAlgorithmsEricMazumdar1AldoPacchiano1Yi-AnMa23PeterL.Bartlett14MichaelI.Jordan14Abstractexploitationtradeoffs(Aueretal.,2002;LattimoreandSzepesva´ri,2020),whereinanal...
OnthePowerofCompressedSensingwithGenerativeModelsAkshayKamath1SushrutKarmalkar1EricPrice1Abstractofthecompressedrepresentationofxthantoitsambientdimensionn.Thegoalofcompressedsensingistolearnastruc...
OnLeveragingPretrainedGANsforGenerationwithLimitedDataMiaoyunZhao1YulaiCong1LawrenceCarin1AbstractAlthoughmanypowerfulGANmodelspretrainedonlarge-scaledatasetshavebeenreleased,feweffortshavebeenRece...
OnDifferentiallyPrivateStochasticConvexOptimizationwithHeavy-tailedDataDiWang12HanshenXiao3SriniDevadas3JinhuiXu1Abstractarethemostfundamentalproblemsinsupervisedlearningandstatistics.Theyfindnumer...
Off-PolicyActor-CriticwithSharedExperienceReplaySimonSchmitt1MatteoHessel1KarenSimonyan1AbstractTable1.Comparisonofmodel-freestate-of-the-artagentson57Atarigamesinthestandardregime:Herenoexperience...