Dual approaches to the strongly convex simple function minimization problem under affine restrictions
Optimization and Control
2017-06-23 v9
Abstract
We consider strongly convex optimization problems with affine-type restrictions. We build dual problem and solve dual problem by Fast Gradient Method. We use primal-dual structure of this method to construct the solution of the primal problem. The paper contain a lot of different tricks that allows to generalize mentioned above results for almost all methods we would like to choose to solve the dual problem.
Cite
@article{arxiv.1602.01686,
title = {Dual approaches to the strongly convex simple function minimization problem under affine restrictions},
author = {Anton Anikin and Alexander Gasnikov and Pavel Dvurechensky and Alexander Turin and Alexey Chernov},
journal= {arXiv preprint arXiv:1602.01686},
year = {2017}
}
Comments
16 pages, in Russian