Rock the KASBA: Blazingly Fast and Accurate Time Series Clustering

TL;DR

The paper introduces KASBA, a novel time series clustering algorithm that balances speed and accuracy, outperforming existing methods in both metrics through innovative use of elastic distance and stochastic optimization.

Contribution

KASBA is a new scalable time series clustering algorithm combining MSM elastic distance with stochastic gradient descent for improved performance.

Findings

KASBA achieves significantly better clustering accuracy than existing fast algorithms.

KASBA offers orders of magnitude faster run times compared to the most accurate k-means methods.

Extensive experiments validate KASBA's effectiveness on real-world datasets.

Abstract

Time series data has become increasingly prevalent across numerous domains, driving a growing demand for time series machine learning techniques. Among these, time series clustering (TSCL) stands out as one of the most popular machine learning tasks. TSCL serves as a powerful exploratory analysis tool and is also employed as a preprocessing step or subroutine for various tasks, including anomaly detection, segmentation, and classification. The most popular TSCL algorithms are either fast (in terms of run time) but perform poorly on benchmark problems, or perform well on benchmarks but scale poorly. We present a new TSCL algorithm, the $k$-means (K) accelerated (A) Stochastic subgradient (S) Barycentre (B) Average (A) (KASBA) clustering algorithm. KASBA is a $k$-means clustering algorithm that uses the Move-Split-Merge (MSM) elastic distance at all stages of clustering, applies a randomised stochastic subgradient gradient descent to find barycentre centroids, links each stage of clustering to accelerate convergence and exploits the metric property of MSM distance to avoid a large proportion of distance calculations. It is a versatile and scalable clusterer designed for real-world TSCL applications. It allows practitioners to balance run time and clustering performance. We demonstrate through extensive experimentation that KASBA produces significantly better clustering than the faster state of the art clusterers and is offers orders of magnitude improvement in run time over the most performant $k$-means alternatives.