Last Iterate Convergence of AdaGrad-Norm for Convex Non-Smooth Optimization

Margarita Preobrazhenskaia, Makar Sidorov, Igor Preobrazhenskii +1

We study the convergence of the last iterate (i.e., the $(N+1)$-th iterate) of the AdaGrad method. Although AdaGrad -- an adaptive subgradient method -- underpins a wide class of a…