Search papers, labs, and topics across Lattice.
This paper introduces Elastic Time Warping (ETW), an algorithm for matching time series in metric spaces using a Hellinger kernel as the stretching penalty. ETW optimizes time series alignment by minimizing the Hellinger distance between warped versions of the series. The algorithm achieves a cubic computational complexity, making it potentially more efficient than existing methods for certain applications.
Time series alignment just got faster: Elastic Time Warping offers a cubic complexity alternative for matching time series with Hellinger-based stretching penalties.
We consider a matching problem for time series with values in an arbitrary metric space, with the stretching penalty given by the Hellinger kernel. To optimize this matching, we introduce the Elastic Time Warping algorithm with a cubic computational complexity.
