Abstract
We prove new theorems which describe a necessary and sufficient condition for linear (strong and non-strong) separability and inseparability of the sets in a finite-dimensional Euclidean space. We propose a universal measure for the thickness of the geometric margin (both the strong separation margin (separator) and the margin of unseparated points (pseudo-separator)) formed between the parallel generalized supporting hyperplanes of the two sets which are separated. The introduced measure allows comparing results of linear separation obtained by different techniques for both linearly separable and inseparable sets. An optimization program whose formulation provides a maximum thickness of the separator for the separable sets is considered. When the sets are inseparable, the same solver is guaranteed to construct a pseudo-separator with a minimum thickness. We estimate the distance between the convex and closed sets. We construct a cone of generalized support vectors for hyperplanes, each one of which linearly separates the considered sets. The interconnection of the problem of different types of linear separation of sets with some related problems is studied.
Similar content being viewed by others
References
Dem’yanov, V.F.: Mathematical diagnostics via nonsmooth analysis. Optim. Methods Softw. 20(2–3), 191–212 (2005)
Mangasarian, O.L.: Linear and nonlinear separation of patterns by linear programming. Oper. Res. 13(3), 444–452 (1965)
Bennett, K.P., Mangasarian, O.L.: Robust linear programming discrimination of two linearly inseparable sets. Optim. Methods Softw. 1, 23–34 (1992)
Mangasarian, O.I.: Generalized Support Vector Machines. Advances in Large Margin Classifiers. MIT Press, Cambridge (2000)
Gabidullina, Z.R.: On the issue of linear separability of convex polyhedra. In: “Mathematical Programming and Applications” Abstracts for Presentation at the XIV Russian Conference. UrO RAN, Yekaterinburg (2011)
Gabidullina, Z.R.: A linear separability criterion for convex polyhedra. In: Book of abstracts of 25-th IFIP TC 7 Conference on System Modeling and Optimization, Berlin (2011)
Gabidullina, Z.R.: A theorem on strict separability of convex polyhedra and its applications in optimization. J. Optim. Theory Appl. 148(3), 550–570 (2011)
Giannessi, F.: Constrained Optimization and Image Space Analysis. Volume 1. Separation of Sets and Optimality Conditions. Springer, New York (2005)
Vasil’ev, F.P.: Numerical Methods for Solving Extremum Problems. Nauka, Moscow (1980)
Dem’yanov, V.F., Vasil’ev, L.V.: Nondifferentiable Optimization. Nauka, Moscow (1981) (Engl. transl., Dem’yanov, V.F., Vasil’ev, L.V., Sasagawa, T., Nondifferentiable Optimization. Springer, Berlin (1985))
Dem’yanov, V.F., Malozemov, V.N.: Introduction to Minimax. Nauka, Moscow (1972) (Engl. transl., Dover Publications (1990))
Ioffe, A.D., Tichomirov, B.M.: Theory of Extremal Problems. Nauka, Moscow (1974) (Engl. transl., Theory of Extremal Problems. Studies in Mathematics and Its Applications. Elsevier Science Ltd. (1979))
Pshenichnii, B.N.: Convex Analysis and Extremal Problems. Nauka, Moscow (1980)
Levitin, E.S., Polyak, B.T.: Costrained minimization methods. Ž. Vyčisl. Mat. Mat. Fiz. 6(5), 787–823 (1966)
Elster, K.H., Reinhart, R., Schauble, M., Donath, G.: Einführung in die Nichtlineare Optimierung. Teubner, Leipzig (1977) (Russ. transl., Introduction in Nonlinear Programming, Nauka, Moscow (1985))
Sukharev, A.G., Timokhov, A.V., Fedorov, V.V.: A Cource in Optimization Methods. Nauka, Moscow (1986)
Konnov, I.V.: Application of the method of conjugate gradients to minimization of quasiconvex functionals. Issled. Prikl. Mat. 12, 46–58 (1984)
Gavurin, M.K., Malozemov, V.N.: Extremum Problems with Linear Constraints. Publishing House of LGU, Leningrad (1984)
Michel, M., Vaida, S.: Mathematical Programming. Theory and Algorithms. Wiley, New York (1986) (Russ. transl., Nauka, Moscow (1990))
Gabidullina, Z.R.: A theorem on separability of a convex polyhedron from zero point of the space and its applications in optimization. Russ. Math. 12(12), 21–26 (2006) (Engl. transl., Russ. Math. (Iz. VUZ) 50, 18–23 (2006))
Acknowledgements
The author thanks Prof. G. Di Pillo for his helpful comments on a previous version of the paper. The valuable remarks of the anonymous referees are gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Gianni Di Pillo.
Rights and permissions
About this article
Cite this article
Gabidullina, Z.R. A Linear Separability Criterion for Sets of Euclidean Space. J Optim Theory Appl 158, 145–171 (2013). https://doi.org/10.1007/s10957-012-0155-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-012-0155-x