Similarity Learning for Time Series Classification
It addresses a gap in learning-based improvements for DTW, which is crucial for applications in fields like energy and finance, but the approach appears incremental as it builds on an existing measure.
The paper tackles the problem of improving time series classification by learning similarities based on dynamic time warping (DTW), providing theoretical guarantees with a generalization bound and showing efficiency and sparsity in experiments.
Multivariate time series naturally exist in many fields, like energy, bioinformatics, signal processing, and finance. Most of these applications need to be able to compare these structured data. In this context, dynamic time warping (DTW) is probably the most common comparison measure. However, not much research effort has been put into improving it by learning. In this paper, we propose a novel method for learning similarities based on DTW, in order to improve time series classification. Making use of the uniform stability framework, we provide the first theoretical guarantees in the form of a generalization bound for linear classification. The experimental study shows that the proposed approach is efficient, while yielding sparse classifiers.