StatisticallyPreconditionedAcceleratedGradientMethodforDistributedOptimizationHadrienHendrikx1LinXiao2Se´bastienBubeck2FrancisBach1LaurentMassoulie´1Abstractleaveψmainlyfornon-smoothregularizati...
Shampoo:PreconditionedStochasticTensorOptimizationVineetGupta1TomerKoren1YoramSinger21AbstractNocedal,1980)thatcanbeusedwheneversecond-orderinformationisunavailableortooexpensivetocompute.Precondit...