The one-sided mean kernel: a positive definite kernel for time series

Nicolas Chrysanthos (1) , Pierre Beauseroy (1) , Hichem Snoussi (1) , Edith Grall-Maës (1) , Fabrice Ferrand (2)

1 LM2S - Laboratoire Modélisation et Sûreté des Systèmes
2 SAGEM Défense Sécurité [Massy]

We propose in this paper a new kernel for time series on structured data in the dynamic time warping family. We demonstrate using the theory of infinitely divisible kernels that this kernel is positive definite, that it is a radial basis kernel and that it reduces to a product kernel when comparing two sequences of the same length. Finally we compare this kernel with the global alignment kernel in a classification task using support vector machines.

Domains: Machine Learning [cs.LG]

Nicolas Chrysanthos, Pierre Beauseroy, Hichem Snoussi, Edith Grall-Maës, Fabrice Ferrand. The one-sided mean kernel: a positive definite kernel for time series. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2014, Apr 2014, Bruges, Belgium. ⟨hal-02518557⟩