Building a scalable machine learning system for unsupervised anomaly detection via representation learning is highly desirable. One of the prevalent methods is using a reconstruction error of variational autoencoder (VAE) by maximizing the evidence lower bound. We revisit VAE from the perspective of information theory to provide some theoretical foundations on using the reconstruction error and finally arrive at a simpler yet effective model for anomaly detection. In addition, to enhance the effectiveness of detecting anomalies, we incorporate a practical model uncertainty measure into the anomaly score. We show empirically the competitive performance of our approach on benchmark data sets.

迫切需要构建一种可扩展的机器学习系统，以通过表示学习进行无监督的异常检测。一种流行的方法是通过最大化证据下界来使用变分自动编码器（VAE）的重构误差。我们从信息论的角度重新审视VAE，以提供一些有关使用重构误差的理论基础，最后得出一个更简单而有效的异常检测模型。另外，为了提高检测异常的有效性，我们将实用的模型不确定性度量合并到异常评分中。我们从经验上展示了我们的基准数据集方法的竞争性表现。