TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces - Université Clermont Auvergne Access content directly
Conference Papers Year : 2019

TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces

Abstract

The proposed work aims at proposing a alternative kernel decomposition in the context of kernel machines with indefinite kernels. The original paper of KSVM (SVM in Kre˘ ın spaces) uses the eigen-decomposition, our proposition avoids this decompostion. We explain how it can help in designing an algorithm that won't require to compute the full kernel matrix. Finally we illustrate the good behavior of the proposed method compared to KSVM.
Fichier principal
Vignette du fichier
trikSVMreduced.pdf (801.59 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02049004 , version 1 (26-02-2019)

Identifiers

Cite

Gaëlle Loosli. TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces. ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2019, Bruges, Belgium. ⟨hal-02049004⟩
99 View
59 Download

Altmetric

Share

Gmail Facebook X LinkedIn More