Dual Extrapolation and its Applications for Solving Variational Inequalities and Related Problems'
暂无分享,去创建一个
In this paper we suggest new dual methods for solving variational inequalities with monotone operators. We show that with an appropriate step-size strategy, our method is optimal both for Lipschitz continuous operators (O( 1 ² ) iterations), and for the operators with bounded variations (O( 1 ²2 ) iterations). Our technique can be applied for solving nonsmooth convex minimization problems with known structure. In this case the worst-case complexity bound is O( 1 ² ) iterations.
[1] Arkadi S. Nemirovsky,et al. Information-based complexity of linear operator equations , 1992, J. Complex..
[2] Yurii Nesterov,et al. Homogeneous Analytic Center Cutting Plane Methods for Convex Problems and Variational Inequalities , 1999, SIAM J. Optim..
[3] Yurii Nesterov,et al. Excessive Gap Technique in Nonsmooth Convex Minimization , 2005, SIAM J. Optim..
[4] Yurii Nesterov,et al. Smooth minimization of non-smooth functions , 2005, Math. Program..