Smoothp-WassersteinDistance:Structure,EmpiricalApproximation,andStatisticalApplicationsSloanNietert1ZivGoldfeld2KengoKato3AbstractapplicationsinstatisticsandML,rangingfromgenerativemodeling(Arjovsk...
SinglePassEntrywise-TransformedLowRankApproximationYifeiJiang1YiLi2YimingSun2JiaxinWang3DavidP.Woodruff4Abstract1.IntroductionInapplicationssuchasnaturallanguageprocess-Therearenumerousapplications...
SafeReinforcementLearningwithLinearFunctionApproximationSanaeAmani1ChristosThrampoulidis2LinF.Yang1Abstractactionmayleadtocatastrophicresults.Thus,safetyinRLhasbecomeaseriousissuethatrestrictstheap...
Risk-SensitiveReinforcementLearningwithFunctionApproximation:ADebiasingApproachYingjieFei1ZhuoranYang2ZhaoranWang1Abstractrisk-seekingobjectiveandβ<0inducesarisk-averseone.ItcanalsobeseenthatVβte...
MultidimensionalScaling:ApproximationandComplexityErikDemaine1AdamHesterberg2FredericKoehler3JaysonLynch4JohnUrschel3Abstractbeenrecognizedasafundamentaltoolfordataanalysisacrossabroadrangeofdiscip...
Fixed-ParameterandApproximationAlgorithmsforPCAwithOutliersYogeshDahiya1FedorFomin2FahadPanolan3KirillSimonov2AbstractYoung,1936),PCAisefficientlysolvableviaSingularValueDecomposition(SVD).PCAisuse...
BesovFunctionApproximationandBinaryClassificationonLow-DimensionalManifoldsUsingConvolutionalResidualNetworksHaoLiu1MinshuoChen2TuoZhao2WenjingLiao3AbstractThesuccessofdeeplearningclearlydemonstrat...
BatchValue-functionApproximationwithOnlyRealizabilityTengyangXie1NanJiang1Abstractthissubproblem,wecreateapiecewiseconstantfunctionclassofstatisticalcomplexityO(1/2)thatcanexpressbothWemakeprogress...
Average-RewardOff-PolicyPolicyEvaluationwithFunctionApproximationShangtongZhang1YiWan2RichardS.Sutton2ShimonWhiteson1Abstractwhichaimtogenerateapolicythatmaximizestherewardratebyiterativelyimprovin...
ApproximationTheoryofConvolutionalArchitecturesforTimeSeriesModellingHaotianJiang1ZhongLi2QianxiaoLi13AbstractTherecentworkofLietal.(2021)formulatedthetempo-ralmodellingtaskintoafunctionalanalysisp...
ApproximationTheoryBasedMethodsforRKHSBanditsShoTakemori1MasahiroSato1AbstracttheadversarialRKHSbanditproblem,wherealearnerinter-actswithasequenceofanyfunctionsfromtheRKHSwithTheRKHSbanditproblem(a...
OptimalApproximationforunconstrainednon-submodularminimizationMarwaElHalabi1StefanieJegelka1Abstractclassofsuchfunctionsareα-weaklyDR-submodularfunc-tions,introducedin(Lehmannetal.,2006).Theparame...
Minimax-OptimalOff-PolicyEvaluationwithLinearFunctionApproximationYaqiDuan1ZeyuJia2MengdiWang34Abstractvalue)tobeearnedbyanewpolicybasedonloggedhistory.Thispaperstudiesthestatisticaltheoryofoff-Int...
k-means++:FewMoreStepsYieldConstantApproximationDavinChoo1ChristophGrunau1JulianPortmann1Va´clavRozhonˇ1AbstractApproximationalgorithmsexist(Jain&Vazirani,2001;Kanungoetal.,2004).Forconstantdimen...
Input-SparsityLowRankApproximationinSchattenNormYiLi1DavidP.Woodruff2Abstractlarvaluedecomposition(SVD)ofA,whichisanexpensiveoperation.Wegivethefirstinput-sparsitytimealgorithmsfortherank-klowranka...
GeneralizationGuaranteesforSparseKernelApproximationwithEntropicOptimalFeaturesLiangDing1RuiTuo1ShahinShahrampour1AbstractSupportVectorMachines(SVM)).Despitetheirsuccess,kernelmethodssufferfromInth...
Black-BoxVariationalInferenceasDistilledLangevinDynamicsMatthewHoffman1Yi-AnMa12AbstractrithmsareMarkovchainMonteCarlo(MCMC)andvaria-tionalinference(VI).VIchoosesafamilyoftractabledis-Variationalin...
ApproximationGuaranteesofLocalSearchAlgorithmsviaLocalizabilityofSetFunctionsKaitoFujii1Abstractproblemoffindingan(approximately)optimalsetfromallfeasiblesets.VariousmachinelearningtaskshavebeenThi...
ApproximationCapabilitiesofNeuralODEsandInvertibleResidualNetworksHanZhang1XiGao1JacobUnterman1TomArodz1Abstractsequence.Then,wecanrepresentthesequencethroughxt+1−xt=fΘ(xt,t),whereΘconsistsoftra...
SortingOutLipschitzFunctionApproximationCemAnil12JamesLucas12RogerGrosse12AbstractExistingapproachestoenforceLipschitzconstraintsfallintotwocategories:regularizationandarchitecturalcon-Trainingneur...