Online Changepoint Detection on a Budget

TL;DR

This paper introduces an online changepoint detection algorithm suitable for real-time data streams, emphasizing low computational and storage costs, and includes an auto-tuning method for hyperparameters.

Contribution

The paper presents a novel online changepoint detection algorithm that is computationally efficient and applicable to multivariate data, with an auto-tuning technique for hyperparameters.

Findings

Performs favorably compared to offline methods

Operates with fixed storage and computational complexity

Applicable to both univariate and multivariate data

Abstract

Changepoints are abrupt variations in the underlying distribution of data. Detecting changes in a data stream is an important problem with many applications. In this paper, we are interested in changepoint detection algorithms which operate in an online setting in the sense that both its storage requirements and worst-case computational complexity per observation are independent of the number of previous observations. We propose an online changepoint detection algorithm for both univariate and multivariate data which compares favorably with offline changepoint detection algorithms while also operating in a strictly more constrained computational model. In addition, we present a simple online hyperparameter auto tuning technique for these algorithms.