A Wasserstein Subsequence Kernel for Time Series
Christian Bock, Matteo Togninalli, Elisabetta Ghisu, Thomas Gumbsch, Bastian Rieck, Karsten Borgwardt · 2019
Kernel methods are a powerful approach for learning on structured data. However, as we show in this paper, simple but common instances of the popular R-convolution kernel framework can be meaningless when assessing the similarity of two time series through their subsequences. We therefore propose a meaningful approach based on optimal transport theory that simultaneously captures local and global characteristics of time series. Moreover, we demonstrate that our method achieves competitive classification accuracy in comparison to state-of-the art methods across a wide variety of data sets.