Nonsmooth analysis and subgradient methods for averaging in dynamic time warping spaces

- Stochastic subgradient method outperforms state-of-the-art algorithm DTW Barycenter Averaging (DBA) for non-small sample sizes.
- Necessary and sufficient conditions of optimality for the sample mean problem in DTW spaces.
- Finite convergence of DBA to necessary conditions of optimality.

Time series averaging in dynamic time warping (DTW) spaces has been successfully applied to improve pattern recognition systems. This article proposes and analyzes subgradient methods for the problem of finding a sample mean in DTW spaces. The class of subgradient methods generalizes existing sample mean algorithms such as DTW Barycenter Averaging (DBA). We show that DBA is a majorize-minimize algorithm that converges to necessary conditions of optimality after finitely many iterations. Empirical results show that for increasing sample sizes the proposed stochastic subgradient (SSG) algorithm is more stable and finds better solutions in shorter time than the DBA algorithm on average. Therefore, SSG is useful in online settings and for non-small sample sizes. The theoretical and empirical results open new paths for devising sample mean algorithms: nonsmooth optimization methods and modified variants of pairwise averaging methods.