Fast Rates for Regularized Least-Squares Algorithm

Abstract

We develop a theoretical analysis of generalization performances of regularized least-squares on reproducing kernel Hilbert spaces for supervised learning. we show that the concept of effective dimension of an integral operator plays a central role in the definition of a criterion for the choice of the regularization parameter as a function of the number of samples. In fact a minimax analysis is performed which shows asymptotic optimality of the above mentioned criterion.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 2005
Accession Number
ADA454989

Entities

People

  • Andrea Caponnetto
  • Ernesto De Vito

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Convergence
  • Eigenvalues
  • Equations
  • Estimators
  • Hilbert Space
  • Inequalities
  • Integrals
  • Inverse Problems
  • Learning
  • Notation
  • Probability
  • Probability Distributions
  • Random Variables
  • Standards
  • Two Dimensional

Readers

  • Calculus or Mathematical Analysis
  • Operations Research
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • Space