Abstract
A parallel support vector machine based on randomized sampling technique is proposed in this paper. We modeled a new LP-type problem so that it works for general linear-nonseparable SVM training problems unlike the previous work [2]. A unique priority based sampling mechanism is used so that we can prove an average convergence rate that is so far the fastest bounded convergence rate to the best of our knowledge. The numerical results on synthesized data and a real geometric database show that our algorithm has good scalability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Adler, I., Shamir, R.: A randomized scheme for speeding up algorithms for linear and convex programming with high constraints-to-variable ratio. Mathematical Programming (1993)
Balcazar, J., Dai, Y., Tanaka, J., Watanabe, O.: Provably fast training algorithm for support vector machines. In: Proceedings of First IEEE International Conference on Data Mining, ICDM 2001 (2001)
Balcazar, J., Dai, Y., Watanabe, O.: Provably fast support vector regression using random sampling. In: Proceedings of SIAM Workshop on Discrete Mathematics and Data Mining (April 2001)
Blackard, J.A., Dean, D.J.: Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover type from cartographic variables. Computer and Electronics in Agriculture 24 (1999)
Blake, C.L., Merz, C.J.: UCI repository of machine learning databases (1998)
Clarkson, K.L.: Las vegas algorithms for linear and integer programming when the dimension is small. In: Proceeding of 29th IEEE Symposium on Foundations of Computer Science, FOCS 1988 (1988)
Collobert, R., Bengio, S., Bengio, Y.: A parallel mixture of svms for very large scale problems. In: Neural Information Processing Systems, pp. 633–640 (2001)
Eitrich, T., Lang, B.: Shared memory parallel support vector machine learning. Technical report, ZAM Publications on Parallel Applications (2005)
Gartner, B., Welzl, E.: A simple sampling lemma: Analysis and applications in geometric optimization. In: Proceeding of the 16th Annual ACM Symposium on Computational Geometry, SCG (2000)
Graf, H.P., Cosatto, E., Bottou, L., Dourdanovic, I., Vapnik, V.: Parallel support vector machine: The cascade svm. Advances in Neural Information Processing Systems (2005)
Joachims, T.: Making large-scale svm learning practical. Advances in Kernel Methods - Support Vector Learning, 169–184 (1998)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lu, Y., Roychowdhury, V. (2006). Parallel Randomized Support Vector Machine. In: Ng, WK., Kitsuregawa, M., Li, J., Chang, K. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2006. Lecture Notes in Computer Science(), vol 3918. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11731139_25
Download citation
DOI: https://doi.org/10.1007/11731139_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33206-0
Online ISBN: 978-3-540-33207-7
eBook Packages: Computer ScienceComputer Science (R0)