Trainsimultaneously,generalizebetter:StabilityofGradient-BasedminimaxlearnersFarzanFarnia1AsumanOzdaglar1Abstract2014)andadversarialtraining(Madryetal.,2017)haveachievedgreatsuccessoverawidearrayof...
SMG:AShufflingGradient-BasedMethodwithMomentumTrangH.Tran1LamM.Nguyen2QuocTran-Dinh3Abstractlearning,including,butnotlimitedto,logisticregression,multi-kernellearning,conditionalrandomfields,andneu...
Continuous-timeLowerBoundsforGradient-BasedAlgorithmsMichaelMuehlebach1MichaelI.Jordan1Abstractindependentlowerboundsthenresultfromanunboundedincreaseintheproblemdimension.Thisestablishes,forThisar...
ProvableGuaranteesforGradient-BasedMeta-LearningMikhailKhodak1Maria-FlorinaBalcan1AmeetTalwalkar12Abstractwithexamples(xi,yi)∈X×Yforanunseentask,thepopularMAMLalgorithm(Finnetal.,2017)outputsWest...
GameTheoreticOptimizationviaGradient-BasedNikaido-IsodaFunctionArvindU.Raghunathan1AnoopCherian1DeveshK.Jha1Abstract(NE).WedenotebySNEthesetofallNEpoints,i.e.,SNE={x(1)holds}.Intheabsenceofconvexit...
Gradient-BasedMeta-LearningwithLearnedLayerwiseMetricandSubspaceYoonhoLee1SeungjinChoi1Abstractoperatesontheleveloftasks,gatheringinformationfromseveralinstancesoftask-specificlearners.Atask-speci...
FastGradient-BasedMethodswithExponentialRate:AHybridControlFrameworkArmanSharifiKolarijani1PeymanMohajerinEsfahani1Tama´sKeciczky1Abstracttheanalysisanddesignofoptimizationalgorithms.Con-sideranit...
ForwardandReverseGradient-BasedHyperparameterOptimizationLucaFranceschi12MicheleDonini1PaoloFrasconi3MassimilianoPontil12Abstractresponsefunction,Bayesianoptimizationapproachespro-videanaturalframe...
FailuresofGradient-BasedDeepLearningShaiShalev-Shwartz1OhadShamir2ShakedShammah1Abstractbothparties:fromapractitioner’sperspective,emphasizingthedifficultiesprovidespracticalinsightstothetheoreti-...