SpectralSmoothingUnveilsPhaseTransitionsinHierarchicalVariationalAutoencodersAdeelPervez1EfstratiosGavves1Abstracttivemodelp(xz)andtheapproximateposteriorq(zx)areGaussiandistributionsoptimizedinuni...
SparseBERT:RethinkingtheImportanceAnalysisinSelf-attentionHanShi1JiahuiGao2XiaozheRen3HangXu3XiaodanLiang4ZhenguoLi3JamesT.Kwok1AbstractincludetheBERT(Devlinetal.,2019),whichachievesstate-of-the-ar...
SoftthenHard:RethinkingtheQuantizationinNeuralImageCompressionZongyuGuo1ZhizhengZhang1RunsenFeng1ZhiboChen1AbstractQuantizationisoneofthekeychallengesforneuralimagecompression.Sincethegradientofqua...
SharingLessisMore:LifelongLearninginDeepNetworkswithSelectiveLayerTransferSeungwonLee1SimaBehpour2EricEaton1Abstract&Hospedales,2017;Leeetal.,2019;Liuetal.,2019b;Bulatetal.,2020),suchassharingthelo...
ScalableOptimalTransportinHighDimensionsforGraphDistances,EmbeddingAlignment,andMoreJohannesKlicpera1MartenLienen1StephanGünnemann1Abstractcostw.r.t.somepointwisecostfunction(e.g.theEuclideandista...
SampleEfficientReinforcementLearninginContinuousStateSpaces:APerspectiveBeyondLinearityDhruvMalik1AldoPacchiano2VishwakSrinivasan1YuanzhiLi1Abstractsuchabenchmark(Bellemareetal.,2013).Agentstrained...
Run-Sort-ReRun:EscapingBatchSizeLimitationsinSlicedWassersteinGenerativeModelsJose´Lezama1WeiChen2QiangQiu2Abstract2017;Lietal.,2017;Mrouehetal.,2017;Heuseletal.,2017;Deshpandeetal.,2018).However,...
RobustPureExplorationinLinearBanditswithLimitedBudgetAyyaAlieva1AshokCutkosky2AbhimanyuDas3Abstracttheexplorationphaseshouldbesomehowefficient-wewishtomakethebestuseofourlimitedbudgetinordertoWecon...
ReservePriceOptimizationforFirstPriceAuctionsinDisplayAdvertisingZheFeng1SébastienLahaie2JonSchneider2JinchaoYe2Abstracttimizationinfirst-price(i.e.,pay-your-bid)auctions,mo-tivatedbythefactthatal...
RobustAsymmetricLearninginPOMDPsAndrewWarrington1J.WilderLavington23AdamS´cibior23MarkSchmidt24FrankWood235Abstracttheworld,tocompletethetask.Atrainee,observingonlyimages,canthenlearntomimictheact...
RiskBoundsandRademacherComplexityinBatchReinforcementLearningYaqiDuan1ChiJin2ZhiyuanLi3Abstractalgorithmsincludingsupportvectormachines(Cortes&Vapnik,1995;Suykens&Vandewalle,1999),boosting(Fre-This...
RewardIdentificationininverseReinforcementLearningKunoKim1KirankumarShiragur1ShivamGarg1StefanoErmon1AbstractMDPstobuildcomputationalmodels(Niv,2009)ofreal-world,rationaldecisionmakerssuchasinvesto...
Revenue-incentiveTradeoffsinDynamicReservePricingYuanDeng1Se´bastienLahaie1VahabMirrokni1SongZuo1Abstract1981).Anaturalideatocircumventthisdifficultyinpracticeistolearnareservepricefromtheadvertis...
ResourceAllocationinMulti-armedBanditExploration:OvercomingSublinearScalingwithAdaptiveParallelismBrijenThananjeyan1KirthevasanKandasamy1IonStoica1MichaelI.Jordan1KenGoldberg1JosephE.Gonzalez1Abstr...
RepresentationalaspectsofdepthandconditioninginnormalizingflowsFredericKoehler1VirajMehta2AndrejRisteski3Abstract1.introductionNormalizingflowsareamongthemostpopularDeepgenerativemodelsareoneofthel...
REPAinT:KnowledgeTransferinDeepReinforcementLearningYunzheTao1SahikaGenc1JonathanChung1TaoSun1SunilMallya1Abstractimproveperformanceonothertasks.AcceleratinglearningprocessesforcomplextasksTransfer...
QuantifyingIgnoranceinindividual-LevelCausal-EffectEstimatesunderHiddenConfoundingAndrewJesson1So¨renMindermann1YarinGal1UriShalit2Abstractfordiscoveringpopulation-levelcausaleffectsofsuchtreat-me...
QuantifyingAvailabilityandDiscoveryinRecommenderSystemsviaStochasticReachabilityMihaelaCurmei1SarahDean1BenjaminRecht1Abstractwhichhavebeenimplicatedinunintendedconsequenceslikepolarizationorradica...
QuantifyingandReducingBiasinMaximumLikelihoodEstimationofStructuredAnomaliesUthsavChitra1KimberlyDing1JasperC.H.Lee2BenjaminJ.Raphael1Abstract1.introductionAnomalyestimation,ortheproblemoffindingAn...
PureExplorationandRegretMinimizationinMatchingBanditsFloreSentenac1JialinYi2Cle´mentCalauze`nes3VianneyPerchet4MilanVojnovic´2Abstractonlineadvertising,wheretheprobabilitythatauserclicksonanaddep...