Abstract
We make a connection between classical polytopes called zonotopes and Support Vector Machine (SVM) classifiers. We combine this connection with the ellipsoid method to give some new theoretical results on training SVMs. We also describe some special properties of C-SVMs for C → ∞.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
K.P. Bennett and E.J. Bredensteiner. Duality and geometry in SVM classifiers. Proc. 17th Int. Conf. Machine Learning, Pat Langley, ed., Morgan Kaufmann, 2000, 57–64.
M. Bern, D. Eppstein, L. Guibas, J. Hershberger, S. Suri, and J. Wolter. The centroid of points with approximate weights. 3rd European Symposium on Algorithms, Corfu, 1995. Springer Verlag LNCS 979, 1995, 460–472.
C.J.C. Burges. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, Vol. 2, No. 2, 1998, 121–167. http://svm.research.bell-labs.com/SVMrefs.html
C. Cortes and V. Vapnik. Support vector networks. Machine Learning, 1995, 273–297.
D.J. Crisp and C.J.C. Burges. A geometric interpretation of i-SVM classifiers. Advances in Neural Information Processing Systems 12. S.A. Solla, T.K. Leen, and K.-R. Müller, eds. MIT Press, 1999. http://svm.research.bell-labs.com/SVMrefs.html
N. Cristianini and J. Shawe-Taylor. Support Vector Machines. Cambridge U. Press, 2000.
H. Edelsbrunner. Algorithms in Combinatorial Geometry, Springer Verlag, 1987.
B. Gärtner. A subexponential algorithm for abstract optimization problems. SI AM J. Computing 24 (1995), 1018–1035.
S.S. Keerthi, S.K. Shevade, C. Bhattacharyya, and K.R.K. Murthy. A fast iterative nearest point algorithm for support vector machine classifier design. IEEE Trans. Neural Networks 11 (2000), 124–136. http://guppy.mpe.nus.edu.sg/~mpessk/
M.K. Kozlov, S.P. Tarasov, L.G. Khachiyan. Polynomial solvability of convex quadratic programming. Soviet Math. Doklady 20 (1979) 1108–1111.
J. Matoušek, M. Sharir, and E. Welzl. A subexponential bound for linear programming. Tech. Report B 92-17, Freie Univ. Berlin, Fachb. Mathematik, 1992
J.C. Platt. Fast training of support vector machines using sequential minimal optimization. Chapter 12 of Advances in Kernel Methods: Support Vector Learning, B. Schölkopf, C. Burges, and A. Smola, eds. MIT Press, 1998, 185–208. http://www.research.microsoft.com/~jplatt
B. Schölkopf, A.J. Smola, R. Williamson, and P. Bartlett. New support vector algorithms. Neural Computatation Vol. 12, No. 5, 2000, 1207–1245. NeuroCOLT2 Technical Report NC2-TR-1998-031. 1998. http://svm.first.gmd.de/papers/tr-31-1998.ps.gz
B. Schölkopf, S. Mika, C.J.C. Burges, P. Knirsch, K.-R. Müller, G. Rätsch, and A.J. Smola. Input space vs. feature space in kernel-based methods. IEEE Trans, on Neural Networks 10 (1999) 1000–1017. http://svm.research.bell-labs.com/SVMrefs.html
A. Schrijver. Theory of Linear and Integer Programming John Wiley & Sons, 1986.
M.J. Todd. Mathematical Programming. Chapter 39 of Handbook of Discrete and Computational Geometry, J.E. Goodman and J. O’Rourke, eds., CRC Press, 1997.
G. Tóth. Point sets with many k-sets. Proc. 16th Annual ACM Symp. Computational Geometry, 2000, 37–42.
V. Vapnik. Statistical Learning Theory. Wiley, 1998.
R.T. Zivaljević and S.T. Vrećica. The colored Tverberg’s problem and complexes of injective functions. J. Comb. Theory, Series A, 61 (1992) 309–318.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bern, M., Eppstein, D. (2001). Optimization over Zonotopes and Training Support Vector Machines. In: Dehne, F., Sack, JR., Tamassia, R. (eds) Algorithms and Data Structures. WADS 2001. Lecture Notes in Computer Science, vol 2125. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44634-6_11
Download citation
DOI: https://doi.org/10.1007/3-540-44634-6_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42423-9
Online ISBN: 978-3-540-44634-7
eBook Packages: Springer Book Archive