Abstract
Support vector machines (SV machines, SVMs) are solved conventionally by converting the convex primal problem into a dual problem with the aid of a Lagrangian function, during whose process the non-negative Lagrangian multipliers are mandatory. Consequently, in the typical C-SVMs, the optimal solutions are given by stationary saddle points. Nonetheless, there may still exist solutions beyond the stationary saddle points. This paper explores these new points violating Karush-Kuhn-Tucker (KKT) condition.
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
Bertsekas, D.P.: Convex Optimization Theory. Athena Scientific (2009)
Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press (2004)
Burges, C.J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining Knowl. Disc. 2, 121–167 (1998)
Chen, R.-C., Huang, M.-R., Chung, R.-G., Hsu, C.-J.: Allocation of Short-Term Jobs to Unemployed Citizens And the Global Economic Downturn Using Genetic Algorithm. Expert Systems with Applications 38, 7535–7543 (2011)
Liang, X., Chen, R., Guo, X.: Pruning Support Vector Machines Without Altering Performances. IEEE Trans. Neural Netw. 19, 1792–1803 (2008)
Mankiw, N.G.: Mcroeconomics, 6th edn. Worth Publishers (2006)
Vapnik, V.N.: Statistical Learning Theory. Wiley-Interscience (1998)
Varian, H.R.: Intermediate Microeconomics: A Modern Approach, 7th edn. Norton and Company (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liang, X. (2011). Solving Support Vector Machines beyond Dual Programming. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7063. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24958-7_59
Download citation
DOI: https://doi.org/10.1007/978-3-642-24958-7_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24957-0
Online ISBN: 978-3-642-24958-7
eBook Packages: Computer ScienceComputer Science (R0)