Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection
This work addresses the challenge of real-time changepoint detection and model selection in spatio-temporal data, which is incremental as it builds upon existing Bayesian methods.
The paper tackles the problem of detecting changepoints in non-stationary spatio-temporal processes by extending Bayesian On-line Changepoint Detection to include on-line model selection and using spatially structured Vector Autoregressions, resulting in an algorithm that is two orders of magnitude faster than competitors and outperforms state-of-the-art methods for multivariate data.
Bayesian On-line Changepoint Detection is extended to on-line model selection and non-stationary spatio-temporal processes. We propose spatially structured Vector Autoregressions (VARs) for modelling the process between changepoints (CPs) and give an upper bound on the approximation error of such models. The resulting algorithm performs prediction, model selection and CP detection on-line. Its time complexity is linear and its space complexity constant, and thus it is two orders of magnitudes faster than its closest competitor. In addition, it outperforms the state of the art for multivariate data.