RIO-CPD: A Riemannian Geometric Method for Correlation-aware Online Change Point Detection

Chengyuan Deng, Zhengzhang Chen, Xujiang Zhao, Haoyu Wang, Junxiang Wang, Haifeng Chen, Jie Gao

Track: Extended abstract

Keywords: Change point detection, Riemannian geometry, Online Learning

TL;DR: We propose a framework for correlation-aware online change point detection rooted in Riemannian geometry

Abstract: The objective of change point detection is to identify abrupt changes at potentially multiple points within a data sequence. This task is particularly challenging in the online setting where various types of changes can occur, including shifts in both the marginal and joint distributions of the data. This paper tackles these challenges by sequentially tracking correlation matrices on their Riemannian geometry, where the geodesic distances accurately capture the development of correlations. We propose Rio-CPD, a non-parametric correlation-aware online change point detection framework that combines the Riemannian geometry of the manifold of symmetric positive definite matrices and the cumulative sum statistic (CUSUM) for detecting change points. Rio-CPD enhances CUSUM by computing the geodesic distance from present observations to the Fr\'echet mean of previous observations. With careful choice of metrics equipped to the Riemannian geometry, Rio-CPD is simple and computationally efficient. Experimental results on both synthetic and real-world datasets demonstrate that Rio-CPD outperforms existing methods in detection accuracy and efficiency.

Submission Number: 64