Abstract
We extend the Lagrangian duality theory for convex optimization problems to incorporate approximate solutions. In particular, we generalize well-known relationships between minimizers of a convex optimization problem, maximizers of its Lagrangian dual, saddle points of the Lagrangian, Kuhn–Tucker vectors, and Kuhn–Tucker conditions to incorporate approximate versions. As an application, we show how the theory can be used for convex quadratic programming and then apply the results to support vector machines from learning theory.
Similar content being viewed by others
References
Strodiot, J.-J., Hien Nguyen, V., Huekemes, N.: ε-optimal solutions in nondifferentiable convex programming and some related questions. Math. Program. 25, 307–328 (1983)
Ekeland, I.: On the variational principle. J. Math. Anal. Appl. 47, 324–353 (1974)
Mordukhovich, B.S., Wang, B.: Necessary suboptimality and optimality conditions via variational principles. SIAM J. Control Optim. 41, 623–640 (2002)
Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)
Varaiya, P.P.: Nonlinear programming in Banach space. SIAM J. Appl. Math. 15, 284–293 (1967)
Zălinescu, C.: Convex Analysis in General Vector Spaces. World Scientific, River Edge (2002)
Yokoyama, K., Shiraishi, S.: An ε-optimality condition for convex programming problems without Slater’s constraint qualification. Preprint (2006)
Barbu, V., Precupanu, Th.: Convexity and Optimization in Banach Spaces. D. Reidel Publishing Company, Dordrecht (1986)
Hiriart-Urruty, J.-B., Lemaréchal, C.: Convex Analysis and Minimization Algorithms II. Springer, New York (1996)
Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)
Steinwart, I., Scovel, C.: Fast rates for support vector machines using Gaussian kernels. Ann. Stat. 35(2), 575–607 (2007)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by M. Fukushima.
Rights and permissions
About this article
Cite this article
Scovel, C., Hush, D. & Steinwart, I. Approximate Duality. J Optim Theory Appl 135, 429–443 (2007). https://doi.org/10.1007/s10957-007-9281-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-007-9281-2