Universal Learning Curves of Support Vector Machines
- 7 May 2001
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 86 (19) , 4410-4413
- https://doi.org/10.1103/physrevlett.86.4410
Abstract
Using methods of statistical physics, we investigate the role of model complexity in learning with support vector machines (SVMs), which are an important alternative to neural networks. We show the advantages of using SVMs with kernels of infinite complexity on noisy target rules, which, in contrast to common theoretical beliefs, are found to achieve optimal generalization error although the training error does not converge to the generalization error. Moreover, we find a universal asymptotics of the learning curves which depend only on the target rule but not on the SVM kernel.Keywords
This publication has 4 references indexed in Scilit:
- Generalization properties of finite-size polynomial support vector machinesPhysical Review E, 2000
- Support Vector MachinesPublished by Cambridge University Press (CUP) ,2000
- Statistical Mechanics of Support Vector NetworksPhysical Review Letters, 1999
- The Nature of Statistical Learning TheoryPublished by Springer Nature ,1995