Detecting Abrupt Changes in High-Dimensional Self-Exciting Poisson Processes
Methodology
2020-06-08 v1 Statistics Theory
Statistics Theory
Abstract
High-dimensional self-exciting point processes have been widely used in many application areas to model discrete event data in which past and current events affect the likelihood of future events. In this paper, we are concerned with detecting abrupt changes of the coefficient matrices in discrete-time high-dimensional self-exciting Poisson processes, which have yet to be studied in the existing literature due to both theoretical and computational challenges rooted in the non-stationary and high-dimensional nature of the underlying process. We propose a penalized dynamic programming approach which is supported by a theoretical rate analysis and numerical evidence.
Cite
@article{arxiv.2006.03572,
title = {Detecting Abrupt Changes in High-Dimensional Self-Exciting Poisson Processes},
author = {Daren Wang and Yi Yu and Rebecca Willett},
journal= {arXiv preprint arXiv:2006.03572},
year = {2020}
}