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.

Open PDF

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

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Computer Science
  • Contracts
  • Estimators
  • European Communities
  • Hilbert Space
  • Inverse Problems
  • Learning
  • Military Research
  • Notation
  • Probability
  • Probability Distributions
  • Random Variables
  • Standards
  • Supervised Machine Learning
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)
  • Linear Algebra

Technology Areas

  • Space