The extragradient method for finding saddle points and other problems

By G. M. Korpelevich. 1976

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

Citations in the corpus

Stochastic Hamiltonian Gradient Methods for Smooth Games (2020, background): “The deterministic version of the problem has been studied in a number of classic (Korpelevich, 1976; Nemirovski, 2004) and recent results (Mescheder et al.”
A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games (2019, methodology): “The extragradient method was introduced by Korpelevich (1976) in the context of variational inequalities.”
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks (2019, methodology): “For the MoG dataset we tried both the extragradient method (Korpelevich, 1976; Gidel et al., 2019) and the standard gradient descent.”
A Variational Inequality Perspective on Generative Adversarial Networks (2018, methodology): “This concept is anterior to the extragradient method since Korpelevich (1976) mentions that the idea of extrapolated “prices” to give “stability” had been already formulated by Polyak (1963, Chap.”
Revisiting Stochastic Extragradient (2019, methodology): “The extragradient method was first proposed by (Korpelevich, 1977).”
Two inertial subgradient extragradient algorithms for variational inequalities with fixed-point constraints (2020, methodology): “At present, Korpelevich’s extragradient method and its variants have been widely investigated; see, e.g.[2–9].”
Optimization of supply chain networks with inclusion of labor: Applications to COVID-19 pandemic disruptions (2021, methodology): “Computational Procedure and Numerical Examples Since the supply chain network optimization model with labor, under its realizations in the case of both elastic demands and fixed demands, and under all three labor capacity scenarios, admits a variational inequality formulation, the modified projectio”
Error bounds and convergence analysis of feasible descent methods: a general approach (1993, methodology): “The extragradient method is an iterative method proposed by Korpelevich for solving monotone variational inequality problems [ 25 ] (also see [24, 46] for extensions).”
An Efficient Primal-Dual Hybrid Gradient Algorithm For Total Variation Image Restoration (2008, methodology): “To overcome the drawbacks of the projection methods defined in (48) and (49), Korpelevich [12] first proposed a modified method called extragradient algorithm.”
A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach (2019, methodology): “EG is a classical method which was introduced in Korpelevich (1976).”
A Variational Inequality Perspective on Generative Adversarial Nets (2018, methodology): “The two standard methods studied in the (VIP) literature are the gradient method (Bruck, 1977) and the extragradient method (Korpelevich, 1976).”