CanStochasticZeroth-OrderFrank-WolfeMethodConvergeFasterforNon-ConvexProblems?HongchangGao1HengHuang12Abstractwhere⌦⇢Rddenotesaclosedconvexfeasibleset,eachcomponentfunctionfiissmoothandnon-convex...
Plug-and-PlayMethodsProvablyConvergewithProperlyTrainedDenoisersErnestK.Ryu1JialinLiu1SichengWang2XiaohanChen2ZhangyangWang2WotaoYin1Abstractmeasurementsoftheimage,isencodedinf(x).Sof(x)issmallifxa...
First-OrderAlgorithmsConvergeFasterthanO(1/k)onConvexProblemsChing-peiLee1StephenJ.Wright1Abstract(3)reliesonshowingthatItiswellknownthatbothgradientdescentandkstochasticcoordinatedescentachieveagl...
AlternatingMinimizationsConvergetoSecond-OrderOptimalSolutionsQiuweiLi1ZhihuiZhu2GongguoTang1AbstractinlandscapeanalysisshowthatmanypopularnonconvexoptimizationproblemsenjoyanicelandscapewhereallTh...