Smooth monotone stochastic variational inequalities and saddle point problems: A survey
Aleksandr Beznosikov
Moscow Institute of Physics and Technology, RussiaBoris Polyak
Moscow University of Physics and Engineering, RussiaEduard Gorbunov
Moscow Institute of Physics and Technology, RussiaDmitry Kovalev
King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaAlexander Gasnikov
Moscow Institute of Physics and Technology, Russia
Abstract
This paper is a survey of methods for solving smooth, (strongly) monotone stochastic variational inequalities. To begin with, we present the deterministic foundation from which the stochastic methods eventually evolved. Then we review methods for the general stochastic formulation, and look at the finite-sum setup. The last parts of the paper are devoted to various recent (not necessarily stochastic) advances in algorithms for variational inequalities.
Cite this article
Aleksandr Beznosikov, Boris Polyak, Eduard Gorbunov, Dmitry Kovalev, Alexander Gasnikov, Smooth monotone stochastic variational inequalities and saddle point problems: A survey. Eur. Math. Soc. Mag. 127 (2023), pp. 15–28
DOI 10.4171/MAG/112