Risk Bounds for Regularized Least-Squares Algorithm with Operator-Value Kernels
Abstract
We show that recent results in [3] on risk bounds for regularized least-squares on reproducing kernel Hilbert spaces can be straight-forwardly extended to the vector-valued regression setting. We first briefly introduce central concepts on operator-valued kernels, then we show how risk bounds can be expressed in terms of a generalization of effective dimension.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 16, 2005
- Accession Number
- ADA466779
Entities
People
- Andrea Caponnetto
- Ernesto De Vito
Organizations
- Massachusetts Institute of Technology