ProximalCausalLearningwithKernels:Two-StageEstimationandMomentRestrictionAfsanehMastouri1YuchenZhu1LimorGultchin23AnnaKorba4RicardoSilva1MattJ.Kusner1ArthurGretton†1KrikamolMuandet†5AbstractGoalA...
OnProximalPolicyOptimization’sHeavy-tailedGradientsSaurabhGarg1JoshuaZhanson2EmilioParisotto1AdarshPrasad1J.ZicoKolter2ZacharyC.Lipton1SivaramanBalakrishnan3RuslanSalakhutdinov1PradeepRavikumar1Ab...
OnCharacterizingGANConvergenceThroughProximalDualityGapSahilSidheekh1AroofAimen1NarayananC.Krishnan1Abstractmostpopularandsuccessfulofinnovationsforlearningdatadistributions.AGANformulatesthegenera...
GuidedExplorationwithProximalPolicyOptimizationusingaSingleDemonstrationGabrieleLibardi1SebastianDittert1GianniDeFabritiis12AbstractLearningfromdemonstrationsallowstodirectlybypassthisproblembutito...
Tuning-freePlug-and-PlayProximalAlgorithmforInverseImagingProblemsKaixuanWei1AngelicaAviles-Rivero2JingweiLiang3YingFu1Carola-BibianeSchnlieb3HuaHuang1Abstracty∈RMisfundamentalincomputationalimagi...
InertialBlockProximalMethodsForNon-ConvexNon-SmoothOptimizationLeThiKhanhHien1NicolasGillis1PanagiotisPatrinos2Abstractbutpossiblynon-smoothnon-convexfunction,andr(x)=Weproposeinertialversionsofblo...
HybridStochastic-DeterministicMinibatchProximalGradient:Less-Than-Single-PassOptimizationwithNearlyOptimalGeneralizationPanZhou1Xiao-TongYuan2Abstract1.IntroductionStochasticvariance-reducedgradien...
EfficientProximalMappingofthe1-path-normofShallowNetworksFabianLatore1PaulRolland1NadavHallak1VolkanCevher1AbstracttheLipschitzconstantofthenetworkfunctiontoquantizerobustness,andregularizationtoen...
AndersonAccelerationofProximalGradientMethodsVienV.Mai1MikaelJohansson1Abstractrameters;slightlyover-orunder-estimatingthestrongcon-vexityconstantcanhaveasevereeffectontheoverallper-Andersonacceler...
ABlockCoordinateDescentProximalMethodforSimultaneousFilteringandParameterEstimationRaminRaziperchikolaei12HarishS.Bhat34Abstractblockcoordinatedescent(BCD)(Xu&Yin,2013;Zhang&Brand,2017),andProximal...
StochasticProximalAlgorithmsforAUCMaximizationMichaelNatoleJr.1YimingYing1SiweiLyu2Abstractformeasuringtheperformanceinthesetasks.Inpartic-ular,minimizationoftheranklossinbipartiterankingisStochast...
Prox-PDA:TheProximalPrimal-DualAlgorithmforFastDistributedNonconvexOptimizationandLearningOverNetworksMingyiHong1DavoodHajinezhad1Ming-MinZhao2Abstract2016);3)nonconvexutilityfunctionsusedinapplica...
ConvergenceAnalysisofProximalGradientwithMomentumforNonconvexOptimizationQunweiLi1YiZhou1YingbinLiang1PramodK.Varshney1AbstractAlgorithm1APGInthiswork,weinvestigatetheacceleratedprox-Input:y1=x1=x0...