Regularized quasi-monotone method for stochastic optimization
Optimization and Control
2021-07-09 v1
Abstract
We adapt the quasi-monotone method from [2] 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 l1-regularized robust linear regression.
Cite
@article{arxiv.2107.03779,
title = {Regularized quasi-monotone method for stochastic optimization},
author = {Vyacheslav Kungurtsev and Vladimir Shikhman},
journal= {arXiv preprint arXiv:2107.03779},
year = {2021}
}