Task-OptimalExplorationinLinearDynamicalSystemsAndrewWagenmaker1MaxSimchowitz2KevinJamieson1Abstracttaintyabouttheenvironment,anaivestrategymightbetoexploretheenvironmentuntilitisuniformlyunderstoo...
SampleComplexityofRobustLinearClassificationonSeparatedDataRobiBhattacharjee1SomeshJha2KamalikaChaudhuri1Abstractthusaimstofindaclassifierthatmaximizesaccuracyonexamplesthataredistancerormorefromth...
SafeReinforcementLearningwithLinearFunctionApproximationSanaeAmani1ChristosThrampoulidis2LinF.Yang1Abstractactionmayleadtocatastrophicresults.Thus,safetyinRLhasbecomeaseriousissuethatrestrictstheap...
RobustPureExplorationinLinearBanditswithLimitedBudgetAyyaAlieva1AshokCutkosky2AbhimanyuDas3Abstracttheexplorationphaseshouldbesomehowefficient-wewishtomakethebestuseofourlimitedbudgetinordertoWecon...
RobustInferenceforHigh-DimensionalLinearModelsviaResidualRandomizationY.SamuelWang1SiKaiLee1PanosToulis1MladenKolar1Abstractsamplesplittingprocedurestoformvalidp-values.Zhang&Zhang(2014),VandeGeere...
RelativePositionalEncodingforTransformerswithLinearComplexityAntoineLiutkus1OndrˇejC´ıfka2Shih-LunWu345UmutS¸ims¸ekli6Yi-HsuanYang35Gae¨lRichard2AbstractFigure1.Examplesofattentionpatternsobs...
RegularizingtowardsCausalInvariance:LinearModelswithProxiesMichaelOberst1NikolajThams2JonasPeters2DavidSontag1AbstractβxAβyWeproposeamethodforlearningLinearmod-XαYelswhosepredictiveperformanceis...
YouOnlySample(Almost)Once:LinearCostSelf-AttentionViaBernoulliSamplingZhanpengZeng1YunyangXiong1SathyaN.Ravi2ShaileshAcharya3GlennFung3VikasSingh1Abstractlanguageinference(Devlinetal.,2019)andparap...
ProvableMeta-LearningofLinearRepresentationsNileshTripuraneni1ChiJin2MichaelI.Jordan1Abstractrangingfromdeepreinforcementlearning(Baevskietal.,2019)tonaturallanguageprocessing(Ando&Zhang,2005;Meta-...
OnlineA-OptimalDesignandActiveLinearRegressionXavierFontaine1PierrePerrault2MichalValko3VianneyPerchet45Abstractwaytoconstructanestimatoristomakeexperimentsandtogatherdataontheestimand.Inthepolling...
AnalyzingMonotonicLinearInterpolationinNeuralNetworkLossLandscapesJamesLucas12JuhanBae12MichaelR.Zhang12StanislavFort3RichardZemel12RogerGrosse12AbstractFigure1.MonotonicLinearinterpolationforaResN...
OnLinearIdentifiabilityofLearnedRepresentationsGeoffreyRoeder1LukeMetz2DiederikP.Kingma2Abstractetal.,2018;Devlinetal.,2018),andsequentialdecisionmaking(Oordetal.,2018).Identifiabilityisadesirablep...
ObliviousSketching-basedCentralPathMethodforLinearProgrammingZhaoSong1ZhengYu2AbstractConsidersolvingageneralLinearprograminstandardformminAx=b,x≥0cxofsizeA∈Rd×nwithoutredundantInthiswork,weprop...
Near-OptimalRepresentationLearningforLinearBanditsandLinearRLJiachenHu1XiaoyuChen1ChiJin2LihongLi3LiweiWang14AbstractWhilerepresentationlearninghasachievedtremendoussuc-cessinavarietyofapplications...
Near-OptimalLinearRegressionunderDistributionShiftQiLei1WeiHu1JasonD.Lee1Abstractprovidehelpfulmarginaldistributioninformationaboutthetargetdomain.AlthoughthisapproachisintegraltomanyTransferlearni...
LogarithmicRegretforReinforcementLearningwithLinearFunctionApproximationJiafanHe1DongruoZhou1QuanquanGu1AbstractAcommonapproachtocopewithhigh-dimensionalstateandactionspacesistoutilizefunctionappro...
LeveragingSparseLinearLayersforDebuggableDeepNetworksEricWong1ShibaniSanturkar1AleksanderMa˛dry1Abstractmodel’sfailuremodesorevaluatecorrectiveinterventionswithoutin-depthproblem-specificstudies....
LinearTransformersAreSecretlyFastWeightProgrammersImanolSchlag∗1KazukiIrie∗1Ju¨rgenSchmidhuber1Abstractfieldnetwork(Ramsaueretal.,2021;Krotov&Hopfield,2016;Demircigiletal.,2017).Itextendsaformof...
LeveragingGoodRepresentationsinLinearContextualBanditsMatteoPapini†1AndreaTirinzoni1MarcelloRestelli1AlessandroLazaric2MatteoPirotta2Abstractrangeofdomains,includingrecommendationsystems,on-Thelin...
ImprovedConfidenceBoundsfortheLinearLogisticModelandApplicationstoBanditsKwang-SungJun1LalitJain2BlakeMason3HoussamNassif4Abstractafeaturevectorforeacharm.Acommonassumptionisthattherewardisanoisyli...