We adapt the quasi-monotone method from Nesterov, Shikhman (2015) for composite convex minimization in the stochastic setting. For the proposed numerical scheme we derive the optimal convergence rate in terms of the last iterate, rather than on average as it is standard for subgradient methods. The theoretical guarantee for individual convergence of the regularized quasi-monotone method is confirmed by numerical experiments on l_1-regularized robust linear regression.
Article
View Regularized quasi-monotone method for stochastic optimization