🤖 AI Summary
Online change detection (OCD) in linear systems under model uncertainty—particularly for streaming data—remains challenging, as existing methods often assume perfect model knowledge and suffer from poor scalability.
Method: We propose RoS-Guard, a robust OCD algorithm that employs compact relaxation and optimization-based reconstruction to explicitly account for model uncertainty. It introduces a differentiable architecture via neural network unfolding and leverages GPU parallelization for efficient computation.
Contribution/Results: RoS-Guard is the first method to theoretically guarantee both a prescribed expected false alarm rate and an upper bound on the worst-case average detection delay. Experiments demonstrate that, on large-scale systems, it achieves several-fold speedup over conventional OCD algorithms while maintaining high detection accuracy and strong robustness to model mismatch.
📝 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.