Asymptotic Universality for Learning Curves of Support Vector Machines
Manfred Opper, Robert Urbanczik · The MIT Press eBooks · 2002
Using methods of Statistical Physics, we investigate the rôle of model complexity in learning with support vector machines (SVMs). 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 only depend on the target rule but not on the SVM kernel.