  


Mirrorprox sliding methods for solving a class of monotone variational inequalities
Guanghui Lan(george.lanisye.gatech.edu) Abstract: In this paper we propose new algorithms for solving a class of structured monotone variational inequality (VI) problems over compact feasible sets. By identifying the gradient components existing in the operator of VI, we show that it is possible to skip computations of the gradients from time to time, while still maintaining the optimal iteration complexity for solving these VI problems. Specifically, for deterministic VI problems involving the sum of the gradient of a smooth convex function $\nabla G$ and a monotone operator $H$, we propose a new algorithm, called the mirrorprox sliding method, which is able to compute an $\varepsilon$approximate weak solution with at most $O((L/\varepsilon)^{1/2})$ evaluations of $\nabla G$ and $O((L/\varepsilon)^{1/2}+M/\varepsilon)$ evaluations of $H$, where $L$ and $M$ are Lipschitz constants of $\nabla G$ and $H$, respectively. Moreover, for the case when the operator $H$ can only be accessed through its stochastic estimators, we propose a stochastic mirrorprox sliding method that can compute a stochastic $\varepsilon$approximate weak solution with at most $O((L/\varepsilon)^{1/2})$ evaluations of $\nabla G$ and $O((L/\varepsilon)^{1/2}+M/\varepsilon + \sigma^2/\varepsilon^2)$ samples of $H$, where $\sigma$ is the variance of the stochastic samples of $H$. Keywords: Category 1: Complementarity and Variational Inequalities Category 2: Nonlinear Optimization Category 3: Stochastic Programming Citation: Download: [PDF] Entry Submitted: 11/01/2021 Modify/Update this entry  
Visitors  Authors  More about us  Links  
Subscribe, Unsubscribe Digest Archive Search, Browse the Repository

Submit Update Policies 
Coordinator's Board Classification Scheme Credits Give us feedback 
Optimization Journals, Sites, Societies  