Anomaly-Free Self-Optimization via AUC Bounds

2026-09-23

AI Summary

论文提出使用AUC界限作为无异常目标，直接优化异常检测系统的连续参数，解决了因缺乏异常数据导致的模型泛化问题。

Abstract

Anomalies are rare, and anomalous data are often unavailable during development, making it difficult to determine which anomaly detection models and configurations will generalize to unseen anomalies. Recent approaches address this challenge by generating pseudo-anomalies and using bounds on the achievable area under the ROC curve (AUC) to select the optimal configuration from a finite set of candidates. Instead, we use the AUC bound as a differentiable, anomaly-free objective for directly optimizing continuous parameters of anomaly detection systems. We demonstrate this framework by optimizing ensemble weights and introducing a learnable score-rescaling mechanism that adapts pseudo-anomaly scores, enabling optimization beyond a predefined candidate set. Experiments across multiple datasets and embedding models show that AUC-bound optimization achieves significant performance gains over conventional model selection and prior development-set-based parameter selection. The results further show that direct optimization is less sensitive to the choice of pseudo-anomaly construction.

Problem

• anomaly detection
• pseudo-anomalies
• AUC bounds
• model generalization

Innovation

• AUC bounds
• anomaly-free optimization
• ensemble weights
• learnable score-rescaling
• pseudo-anomalies