Skip navigation
Skip navigation

Learning with Non-Positive Kernels

Ong, Cheng Song; Mary, Xavier; Canu, Stephane; Smola, Alexander

Description

In 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 Kreǐn Spaces (RKKS), a generalization of Reproducing Kernel Hubert 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,...[Show more]

CollectionsANU Research Publications
Date published: 2004
Type: Conference paper
URI: http://hdl.handle.net/1885/85979
Source: Proceedings of 21st International Conference on Machine Learning (ICML-2004)

Download

File Description SizeFormat Image
01_Ong_Learning_with_Non-Positive_2004.pdf1.46 MBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator