Lepskii Principle in Supervised Learning
From MaRDI portal
Abstract: In the setting of supervised learning using reproducing kernel methods, we propose a data-dependent regularization parameter selection rule that is adaptive to the unknown regularity of the target function and is optimal both for the least-square (prediction) error and for the reproducing kernel Hilbert space (reconstruction) norm error. It is based on a modified Lepskii balancing principle using a varying family of norms.
This page was built for publication: Lepskii Principle in Supervised Learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6319385)
