English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Learning with Non-Positive Kernels

Ong, C., Mary X, Canu, S., & Smola, A. (2004). Learning with Non-Positive Kernels. Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), 81-81.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Ong, CS1, Author           
Mary X, Canu, S, Author
Smola, AJ, Author
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Content

show
hide
Free keywords: -
 Abstract: n this paper we show that many kernel methods can be adapted to deal with indefinite kernels, that is, kernels which are not positive semidefinite. They do not satisfy Mercer‘s condition and they induce associated functional spaces called Reproducing Kernel Kreicaron;n Spaces (RKKS), a generalization of Reproducing Kernel Hilbert Spaces (RKHS).Machine learning in RKKS shares many "nice" properties of learning in RKHS, such as orthogonality and projection. However, since the kernels are indefinite, we can no longer minimize the loss, instead we stabilize it. We show a general representer theorem for constrained stabilization and prove generalization bounds by computing the Rademacher averages of the kernel class. We list several examples of indefinite kernels and investigate regularization methods to solve spline interpolation. Some preliminary experiments with indefinite kernels for spline smoothing are reported for truncated spectral factorization, Landweber-Fridman iterations, and MR-II.

Details

show
hide
Language(s):
 Dates: 2004-07
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Degree: -

Event

show
hide
Title: Twenty-First International Conference on Machine Learning
Place of Event: Banff, Alberta, Canada
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004)
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: New York, NY, USA : ACM Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 81 - 81 Identifier: -