Generalization error of spectral algorithms

arXiv:2403.11696v1 Announce Type: new
Abstract: The asymptotically precise estimation of the generalization of kernel methods has recently received attention due to the parallels between neural networks and their associated kernels. However, prior works derive such estimates for training by kernel ridge regression (KRR), whereas neural networks are typically trained with gradient descent (GD). In the present work, we consider the training of kernels with a family of $\textit{spectral algorithms}$ specified by profile $h(\lambda)$, and including KRR and GD as special …

abstract algorithms arxiv attention cs.lg error gradient however kernel networks neural networks prior regression ridge stat.ml training type