Fast likelihood-based change point detection

TL;DR

This paper introduces a fast, likelihood-based change point detection method for binary data streams, using an approximation scheme that significantly reduces computation time while maintaining high accuracy.

Contribution

It proposes an efficient approximation algorithm for change point detection in binary streams with provable accuracy and reduced computational complexity.

Findings

Achieves $(1 - b)$ approximation in $O(b^{-1} \u2217 \u03bclog^2 n)$ time

Significant speed-up over exact methods with minimal loss in accuracy

Empirical results confirm high approximation quality and efficiency

Abstract

Change point detection plays a fundamental role in many real-world applications, where the goal is to analyze and monitor the behaviour of a data stream. In this paper, we study change detection in binary streams. To this end, we use a likelihood ratio between two models as a measure for indicating change. The first model is a single bernoulli variable while the second model divides the stored data in two segments, and models each segment with its own bernoulli variable. Finding the optimal split can be done in $O(n)$ time, where $n$ is the number of entries since the last change point. This is too expensive for large $n$. To combat this we propose an approximation scheme that yields $(1 - \epsilon)$ approximation in $O(\epsilon^{-1} \log^2 n)$ time. The speed-up consists of several steps: First we reduce the number of possible candidates by adopting a known result from segmentation problems. We then show that for fixed bernoulli parameters we can find the optimal change point in logarithmic time. Finally, we show how to construct a candidate list of size $O(\epsilon^{-1} \log n)$ for model parameters. We demonstrate empirically the approximation quality and the running time of our algorithm, showing that we can gain a significant speed-up with a minimal average loss in optimality.