中文
相关论文

相关论文: Convergence of Extragradient SVRG for Variational …

200 篇论文

In this paper we study the smooth convex-concave saddle point problem. Specifically, we analyze the last iterate convergence properties of the Extragradient (EG) algorithm. It is well known that the ergodic (averaged) iterates of EG…

机器学习 · 计算机科学 2020-07-08 Noah Golowich , Sarath Pattathil , Constantinos Daskalakis , Asuman Ozdaglar

The extragradient (EG), introduced by G. M. Korpelevich in 1976, is a well-known method to approximate solutions of saddle-point problems and their extensions such as variational inequalities and monotone inclusions. Over the years,…

最优化与控制 · 数学 2023-03-31 Quoc Tran-Dinh

Extragradient method (EG) (Korpelevich, 1976) is one of the most popular methods for solving saddle point and variational inequalities problems (VIP). Despite its long history and significant attention in the optimization community, there…

最优化与控制 · 数学 2022-02-23 Eduard Gorbunov , Nicolas Loizou , Gauthier Gidel

Variational inequalities have recently attracted considerable interest in machine learning as a flexible paradigm for models that go beyond ordinary loss function minimization (such as generative adversarial networks and related deep…

最优化与控制 · 数学 2020-02-12 Yu-Guan Hsieh , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

We study nonconvex finite-sum problems and analyze stochastic variance reduced gradient (SVRG) methods for them. SVRG and related methods have recently surged into prominence for convex optimization given their edge over stochastic gradient…

最优化与控制 · 数学 2016-04-06 Sashank J. Reddi , Ahmed Hefny , Suvrit Sra , Barnabas Poczos , Alex Smola

The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving finite-sum min-max optimization and variational inequality problems (VIPs) appearing in various machine learning tasks. However, existing…

最优化与控制 · 数学 2024-10-11 Konstantinos Emmanouilidis , René Vidal , Nicolas Loizou

Single-call stochastic extragradient methods, like stochastic past extragradient (SPEG) and stochastic optimistic gradient (SOG), have gained a lot of interest in recent years and are one of the most efficient algorithms for solving…

最优化与控制 · 数学 2023-11-14 Sayantan Choudhury , Eduard Gorbunov , Nicolas Loizou

Last-iterate convergence has received extensive study in two player zero-sum games starting from bilinear, convex-concave up to settings that satisfy the MVI condition. Typical methods that exhibit last-iterate convergence for the…

计算机科学与博弈论 · 计算机科学 2023-10-05 Yi Feng , Hu Fu , Qun Hu , Ping Li , Ioannis Panageas , Bo Peng , Xiao Wang

Stochastic variance reduced gradient (SVRG) is a popular variance reduction technique for accelerating stochastic gradient descent (SGD). We provide a first analysis of the method for solving a class of linear inverse problems in the lens…

数值分析 · 数学 2022-01-19 Bangti Jin , Zehui Zhou , Jun Zou

We study the stochastic bilinear minimax optimization problem, presenting an analysis of the same-sample Stochastic ExtraGradient (SEG) method with constant step size, and presenting variations of the method that yield favorable…

最优化与控制 · 数学 2022-04-11 Chris Junchi Li , Yaodong Yu , Nicolas Loizou , Gauthier Gidel , Yi Ma , Nicolas Le Roux , Michael I. Jordan

The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving min-max optimization and variational inequalities problems (VIP) appearing in various machine learning tasks. However, several important questions…

最优化与控制 · 数学 2022-02-23 Eduard Gorbunov , Hugo Berard , Gauthier Gidel , Nicolas Loizou

In this paper we apply the stochastic variance reduced gradient (SVRG) method, which is a popular variance reduction method in optimization for accelerating the stochastic gradient method, to solve large scale linear ill-posed systems in…

数值分析 · 数学 2024-03-20 Qinian Jin , Liuhong Chen

Stochastic variance reduced gradient (SVRG) is an accelerated version of stochastic gradient descent based on variance reduction, and is promising for solving large-scale inverse problems. In this work, we analyze SVRG and a regularized…

数值分析 · 数学 2026-03-18 Bangti Jin , Zehui Zhou

We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $\min_{\mathbf{x}}\max_{\mathbf{y}}~F(\mathbf{x}) + H(\mathbf{x},\mathbf{y}) - G(\mathbf{y})$, where one has access to stochastic first-order oracles for $F$,…

最优化与控制 · 数学 2022-08-15 Simon S. Du , Gauthier Gidel , Michael I. Jordan , Chris Junchi Li

Riemannian convex optimization and minimax optimization have recently drawn considerable attention. Their appeal lies in their capacity to adeptly manage the non-convexity of the objective function as well as constraints inherent in the…

最优化与控制 · 数学 2024-06-04 Zihao Hu , Guanghui Wang , Xi Wang , Andre Wibisono , Jacob Abernethy , Molei Tao

Monotone variational inequalities (VIs) provide a unifying framework for convex minimization, equilibrium computation, and convex-concave saddle-point problems. Extragradient-type methods are among the most effective first-order algorithms…

最优化与控制 · 数学 2026-04-16 Lingqing Shen , Fatma Kılınç-Karzan

The monotone variational inequality is a central problem in mathematical programming that unifies and generalizes many important settings such as smooth convex optimization, two-player zero-sum games, convex-concave saddle point problems,…

最优化与控制 · 数学 2022-05-17 Yang Cai , Argyris Oikonomou , Weiqiang Zheng

In this paper, we present a unified analysis of methods for such a wide class of problems as variational inequalities, which includes minimization problems and saddle point problems. We develop our analysis on the modified Extra-Gradient…

Last-iterate behaviors of learning algorithms in repeated two-player zero-sum games have been extensively studied due to their wide applications in machine learning and related tasks. Typical algorithms that exhibit the last-iterate…

机器学习 · 计算机科学 2024-06-18 Yi Feng , Ping Li , Ioannis Panageas , Xiao Wang

We consider differentiable games where the goal is to find a Nash equilibrium. The machine learning community has recently started using variants of the gradient method (GD). Prime examples are extragradient (EG), the optimistic gradient…

机器学习 · 计算机科学 2020-07-08 Waïss Azizian , Ioannis Mitliagkas , Simon Lacoste-Julien , Gauthier Gidel
‹ 上一页 1 2 3 10 下一页 ›