Time warping with Hellinger elasticity

TL;DR

This paper introduces a novel elastic time warping algorithm for matching time series in arbitrary metric spaces, utilizing Hellinger kernel-based stretching penalties to improve alignment accuracy.

Contribution

The paper presents a new elastic time warping method that efficiently handles time series matching with Hellinger kernel penalties, with cubic computational complexity.

Findings

Effective matching of time series in arbitrary metric spaces.

Introduction of a cubic complexity elastic time warping algorithm.

Utilization of Hellinger kernel for stretching penalties.

Abstract

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.