Network Modeling of Asynchronous Change-Points in Multivariate Time Series

TL;DR

This paper presents a Bayesian approach for detecting asynchronous change-points in multivariate time series, modeling lead-lag dependencies via a latent graph, and demonstrating improved performance and interpretability in seismology and neurology data.

Contribution

It introduces a novel hierarchical Bayesian model with a latent graph for asynchronous change-point detection, incorporating a new inference method for complex multivariate data.

Findings

Outperforms existing methods in simulated dependent change-point scenarios

Recovers interpretable network structures in real datasets

Effective in fields like seismology and neurology

Abstract

This article introduces a novel Bayesian method for asynchronous change-point detection in multivariate time series. This method allows for change-points to occur earlier in some (leading) series followed, after a short delay, by change-points in some other (lagging) series. Such dynamic dependence structure is common in fields such as seismology and neurology where a latent event such as an earthquake or seizure causes certain sensors to register change-points before others. We model these lead-lag dependencies via a latent directed graph and provide a hierarchical prior for learning the graph's structure and parameters. Posterior inference is made tractable by modifying particle MCMC methods designed for univariate change-point problems. We apply our method to both simulated and real datasets from the fields of seismology and neurology. In the simulated data, we find that our method outperforms competing methods in settings where the change-point locations are dependent across series. In the real data applications we show that our model can also uncover interpretable network structure.