Kernel learning as minimization of the single validation estimate - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Conference Papers Year : 2014

Kernel learning as minimization of the single validation estimate

Abstract

In order to prevent overfitting in traditional support vector kernel learning, we propose to learn a kernel (jointly with the cost parameter C) by minimizing the single validation estimate with a sequential linear filter algorithm. Additionally, we introduce a simple heuristic in order to improve risk estimation, which randomly swaps several points between the validation and the training sets. Contrarily to previous works, which use several validation sets to improve risk estimation, our strategy does not increase the number of optimization variables. This is easily done thanks to Karasuyama and Takeuchi's multiple incremental decremental support vector learning algorithm. A synthetic signal classification problem underlines the effectiveness of our method. The main parameters of the learned kernel are the finite impulse responses of a filter bank.
Fichier principal
Vignette du fichier
article_MaximeSangnier_IEEE2014_.pdf (355.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

cea-01830640 , version 1 (09-05-2022)

Identifiers

Cite

Maxime Sangnier, Jérôme Gauthier, A. Rakotomamonjy. Kernel learning as minimization of the single validation estimate. 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Sep 2014, Reims, France. pp.6958855, ⟨10.1109/MLSP.2014.6958855⟩. ⟨cea-01830640⟩
98 View
27 Download

Altmetric

Share

Gmail Facebook X LinkedIn More