On the O(1/t) convergence rate of the projection and contraction methods for variational inequalities with Lipschitz continuous monotone operators
- 467 Downloads
Nemirovski’s analysis (SIAM J. Optim. 15:229–251, 2005) indicates that the extragradient method has the O(1/t) convergence rate for variational inequalities with Lipschitz continuous monotone operators. For the same problems, in the last decades, a class of Fejér monotone projection and contraction methods is developed. Until now, only convergence results are available to these projection and contraction methods, though the numerical experiments indicate that they always outperform the extragradient method. The reason is that the former benefits from the ‘optimal’ step size in the contraction sense. In this paper, we prove the convergence rate under a unified conceptual framework, which includes the projection and contraction methods as special cases and thus perfects the theory of the existing projection and contraction methods. Preliminary numerical results demonstrate that the projection and contraction methods converge twice faster than the extragradient method.
KeywordsVariational inequality Projection and contraction method Convergence rate
The authors thank X.-L. Fu, M. Li, M. Tao and X.-M. Yuan for the discussion and valuable suggestions.
- 3.Facchinei, F., Pang, J.S.: Finite-Dimensional Variational Inequalities and Complementarity Problems, Vols. I and II. Springer Series in Operations Research. Springer, New York (2003) Google Scholar
- 11.Howard, A.G.: Large margin, transformation learning. PhD Thesis, Graduate School of Arts and Science, Columbia University (2009) Google Scholar
- 14.Lacoste-Julien, S.: Discriminative machine learning with structure. PhD Thesis, Computer Science, University of California, Berkeley (2009) Google Scholar
- 16.Pan, Y.: A game theoretical approach to constrained OSNR optimization problems in optical network. PhD Thesis, Electrical and Computer Engineering, University of Toronto (2009) Google Scholar
- 18.Sha, F.: Large margin training of acoustic models for speech recognition. PhD Thesis, Computer and Information Science, University of Pennsylvania (2007) Google Scholar
- 23.Taskar, B., Lacoste-Julien, S., Jordan, M.I.: Structured prediction via extragradient method. In: Weiss, Y., Schoelkopf, B., Platt, J. (eds.) Advances in Neural Information Processing Systems (NIPS), vol. 18 (2006) Google Scholar
- 24.Tseng, P.: On accelerated proximal gradient methods for convex-concave optimization. Department of Mathematics, University of Washington, Seattle, WA 98195, USA (2008) Google Scholar