StatisticallyPreconditionedAcceleratedGradientMethodforDistributedOptimizationHadrienHendrikx1LinXiao2Se´bastienBubeck2FrancisBach1LaurentMassoulie´1Abstractleaveψmainlyfornon-smoothregularizati...
StatisticallyEfficientOff-PolicyPolicyGradientsNathanKallus1MasatoshiUehara2AbstractTable1.Comparisonofoff-policypolicygradientestimators.Here,f=Θ(g)means0<liminff/g≤limsupf/g<∞(nottoPolicygradi...
OptimalityImpliesKernelSumClassifiersareStatisticallyEfficientRaphaelA.Meyer1JeanHonorio1AbstractweconsiderbinaryclassificationwithKernelSupportVec-torMachines(SVM),whicharecomputedbysolvingaWeprop...