Online Multivariate Changepoint Detection : Leveraging Links With Computational Geometry

Pishchagina, Liudmila and Romano, Gaetano and Fearnhead, Paul and Runge, Vincent and Rigaill, Guillem (2023) Online Multivariate Changepoint Detection : Leveraging Links With Computational Geometry. Other. Arxiv.

[thumbnail of 2311.01174v1]
Text (2311.01174v1)
2311.01174v1.pdf - Submitted Version
Available under License Creative Commons Attribution.

Download (32MB)

Abstract

The increasing volume of data streams poses significant computational challenges for detecting changepoints online. Likelihood-based methods are effective, but their straightforward implementation becomes impractical online. We develop two online algorithms that exactly calculate the likelihood ratio test for a single changepoint in p-dimensional data streams by leveraging fascinating connections with computational geometry. Our first algorithm is straightforward and empirically quasi-linear. The second is more complex but provably quasi-linear: $\mathcal{O}(n\log(n)^{p+1})$ for $n$ data points. Through simulations, we illustrate, that they are fast and allow us to process millions of points within a matter of minutes up to $p=5$.

Item Type:
Monograph (Other)
Additional Information:
31 pages,15 figures
Subjects:
?? stat.co ??
ID Code:
209818
Deposited By:
Deposited On:
14 Nov 2023 12:45
Refereed?:
No
Published?:
Published
Last Modified:
04 Nov 2024 03:20