Gold, Carl and Sollich, Peter (2005) Fast Bayesian Support Vector Machine Parameter Tuning with the Nystrom Method. In: 2005 Proceedings of the International Joint Conference on Neural Networks (IJCNN). IEEE International Joint Conference on Neural Networks (IJCNN). IEEE , Piscataway, NJ, pp. 2820-2825. ISBN 0-7803-9048-2 http://resolver.caltech.edu/CaltechAUTHORS:20110817-102358825
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20110817-102358825
We experiment with speeding up a Bayesian method for tuning the hyperparameters of a support vector machine (SVM) classifier. The Bayesian approach gives the gradients of the evidence as averages over the posterior, which can be approximated using hybrid Monte Carlo simulation (HMC). By using the Nystrom approximation to the SVM kernel, our method significantly reduces the dimensionality of the space to be simulated in the HMC. We show that this speeds up the running time of the HMC simulation from O(n^2) (with a large prefactor) to effectively O(n), where n is the number of training samples. We conclude that the Nystrom approximation has an almost insignificant effect on the performance of the algorithm when compared to the full Bayesian method, and gives excellent performance in comparison with other approaches to hyperparameter tuning.
|Item Type:||Book Section|
|Additional Information:||© 2005 IEEE. Issue Date: 31 July-4 Aug. 2005. Date of Current Version: 27 December 2005.|
|Other Numbering System:|
|Official Citation:||Gold, C.; Sollich, P.; , "Fast Bayesian support vector machine parameter tuning with the Nystrom method," Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on , vol.5, no., pp. 2820- 2825 vol. 5, 31 July-4 Aug. 2005 doi: 10.1109/IJCNN.2005.1556372 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1556372&isnumber=33093|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Ruth Sustaita|
|Deposited On:||17 Aug 2011 17:44|
|Last Modified:||17 Aug 2011 17:44|
Repository Staff Only: item control page