针对相关噪声下的异常流检测，提出自适应测量优化算法。
Active Hypothesis Testing for Correlated Combinatorial Anomaly Detection
- 基于切尔诺夫信息设计连续约束测量，主动消除相关噪声
- 在合成与真实场景中均显著优于现有基线方法
- 适合需要高效异常检测的工业系统监控场景
我们研究在相关噪声下识别异常数据流子集的问题，该问题源于对网络物理系统的监控与安全需求。这可视为一种组合纯探索问题，每个数据流相当于一个臂，需在不确定性下逐次分配观测。现有组合贝叶斯与假设检验方法通常假设观测独立，无法利用相关性实现高效测量设计。本文提出ECC-AHT算法，通过选择连续且受约束的测量，最大化不同假设间的切尔诺夫信息，实现通过差分感知的主动降噪。该算法具有最优样本复杂度保证，并在合成与真实相关环境中显著优于最先进基线。代码已开源于https://github.com/VincentdeCristo/ECC-AHT。
原文摘要 · Abstract (English)
We study the problem of identifying an anomalous subset of streams under correlated noise, motivated by monitoring and security in cyber-physical systems. This problem can be viewed as a form of combinatorial pure exploration, where each stream plays the role of an arm and measurements must be allocated sequentially under uncertainty. Existing combinatorial bandit and hypothesis testing methods typically assume independent observations and fail to exploit correlation for efficient measurement design. We propose ECC-AHT, an adaptive algorithm that selects continuous, constrained measurements to maximize Chernoff information between competing hypotheses, enabling active noise cancellation through differential sensing. ECC-AHT achieves optimal sample complexity guarantees and significantly outperforms state-of-the-art baselines in both synthetic and real-world correlated environments. The code is available on https://github.com/VincentdeCristo/ECC-AHT
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。