Active Learning for Abrupt Shifts Change-point Detection via Derivative-Aware Gaussian Processes

TL;DR

This paper introduces DACD, an active learning method using derivative-aware Gaussian processes for efficient and accurate change-point detection in data, outperforming existing approaches.

Contribution

The paper presents a novel derivative-aware Gaussian process-based active learning method for change-point detection, improving efficiency and accuracy over prior methods.

Findings

DACD outperforms existing change-point detection methods.

It effectively balances exploration and exploitation in data acquisition.

The method is versatile across diverse scenarios.

Abstract

Change-point detection (CPD) is crucial for identifying abrupt shifts in data, which influence decision-making and efficient resource allocation across various domains. To address the challenges posed by the costly and time-intensive data acquisition in CPD, we introduce the Derivative-Aware Change Detection (DACD) method. It leverages the derivative process of a Gaussian process (GP) for Active Learning (AL), aiming to pinpoint change-point locations effectively. DACD balances the exploitation and exploration of derivative processes through multiple data acquisition functions (AFs). By utilizing GP derivative mean and variance as criteria, DACD sequentially selects the next sampling data point, thus enhancing algorithmic efficiency and ensuring reliable and accurate results. We investigate the effectiveness of DACD method in diverse scenarios and show it outperforms other active learning change-point detection approaches.