| |
Abstract:
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.
|
