English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  An algebraic characterization of the optimum of regularized kernel methods

Dinuzzo, F., & De Nicolao, G. (2009). An algebraic characterization of the optimum of regularized kernel methods. Machine Learning, 74(3), 315-345. doi:10.1007/s10994-008-5095-1.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Dinuzzo, F1, Author              
De Nicolao, G, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: The representer theorem for kernel methods states that the solution of the associated variational problem can be expressed as the linear combination of a finite number of kernel functions. However, for non-smooth loss functions, the analytic characterization of the coefficients poses nontrivial problems. Standard approaches resort to constrained optimization reformulations which, in general, lack a closed-form solution. Herein, by a proper change of variable, it is shown that, for any convex loss function, the coefficients satisfy a system of algebraic equations in a fixed-point form, which may be directly obtained from the primal formulation. The algebraic characterization is specialized to regression and classification methods and the fixed-point equations are explicitly characterized for many loss functions of practical interest. The consequences of the main result are then investigated along two directions. First, the existence of an unconstrained smooth reformulation of the original non-smooth problem is proven. Second, in the context of SURE (Stein’s Unbiased Risk Estimation), a general formula for the degrees of freedom of kernel regression methods is derived.

Details

show
hide
Language(s):
 Dates: 2009-03
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/s10994-008-5095-1
BibTex Citekey: DinuzzoD2009
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Machine Learning
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Dordrecht : Springer
Pages: - Volume / Issue: 74 (3) Sequence Number: - Start / End Page: 315 - 345 Identifier: ISSN: 0885-6125
CoNE: https://pure.mpg.de/cone/journals/resource/08856125