RoS-Guard: Robust and Scalable Online Change Detection with Delay-Optimal Guarantees

TL;DR

RoS-Guard is a novel online change detection algorithm that offers robustness against uncertainties, guarantees on detection delay, and high computational efficiency for large-scale linear systems using neural unrolling and GPU acceleration.

Contribution

It introduces RoS-Guard, a robust, delay-optimal online change detection method with theoretical guarantees and scalable GPU-based implementation for uncertain linear systems.

Findings

Achieves significant speedup in large-scale scenarios

Provides theoretical false alarm and delay guarantees

Demonstrates effectiveness through extensive experiments

Abstract

Online change detection (OCD) aims to rapidly identify change points in streaming data and is critical in applications such as power system monitoring, wireless network sensing, and financial anomaly detection. Existing OCD methods typically assume precise system knowledge, which is unrealistic due to estimation errors and environmental variations. Moreover, existing OCD methods often struggle with efficiency in large-scale systems. To overcome these challenges, we propose RoS-Guard, a robust and optimal OCD algorithm tailored for linear systems with uncertainty. Through a tight relaxation and reformulation of the OCD optimization problem, RoS-Guard employs neural unrolling to enable efficient parallel computation via GPU acceleration. The algorithm provides theoretical guarantees on performance, including expected false alarm rate and worst-case average detection delay. Extensive experiments validate the effectiveness of RoS-Guard and demonstrate significant computational speedup in large-scale system scenarios.