TY - GEN
T1 - Revisiting Stochastic Extragradient
AU - Mishchenko, Konstantin
AU - Kovalev, Dmitry
AU - Shulgin, Egor
AU - Richtarik, Peter
AU - Malitsky, Yura
N1 - KAUST Repository Item: Exported on 2021-09-02
PY - 2020
Y1 - 2020
N2 - We fix a fundamental issue in the stochastic extragradient method by providing a new sampling strategy that is motivated by approximating implicit updates. Since the existing stochastic extragradient algorithm, called Mirror-Prox, of (Juditsky et al., 2011)
diverges on a simple bilinear problem when the domain is not bounded, we prove guarantees for solving variational inequality that
go beyond existing settings. Furthermore, we illustrate numerically that the proposed variant converges faster than many other methods on bilinear saddle-point problems. We also discuss how extragradient can be applied to training Generative Adversarial Networks (GANs) and how it compares to other methods. Our experiments on GANs demonstrate that the introduced approach may make the training faster in terms of data passes, while its higher iteration complexity makes the advantage smaller.
AB - We fix a fundamental issue in the stochastic extragradient method by providing a new sampling strategy that is motivated by approximating implicit updates. Since the existing stochastic extragradient algorithm, called Mirror-Prox, of (Juditsky et al., 2011)
diverges on a simple bilinear problem when the domain is not bounded, we prove guarantees for solving variational inequality that
go beyond existing settings. Furthermore, we illustrate numerically that the proposed variant converges faster than many other methods on bilinear saddle-point problems. We also discuss how extragradient can be applied to training Generative Adversarial Networks (GANs) and how it compares to other methods. Our experiments on GANs demonstrate that the introduced approach may make the training faster in terms of data passes, while its higher iteration complexity makes the advantage smaller.
UR - http://hdl.handle.net/10754/670895
UR - http://proceedings.mlr.press/v108/mishchenko20a/mishchenko20a.pdf
M3 - Conference contribution
SP - 4573
EP - 4581
BT - Proceedings of the 23rdInternational Conference on Artificial Intelligence and Statistics (AISTATS) 2020, Palermo, Italy.
ER -