论文标题
解释变异自动编码器的速率局限，并使用模型不确定性进行异常检测
Interpreting Rate-Distortion of Variational Autoencoder and Using Model Uncertainty for Anomaly Detection
论文作者
论文摘要
非常需要建立可扩展的机器学习系统，以通过代表性学习为无监督的异常检测。一种普遍的方法之一是通过最大化证据下限，使用变异自动编码器（VAE）的重建误差。我们从信息理论的角度重新审视VAE，以提供一些关于使用重建误差的理论基础，并最终得出了一个更简单，更有效的模型以进行异常检测。此外，为了提高检测异常的有效性，我们将实用模型的不确定性度量纳入度量标准中。我们从基准数据集上凭经验显示了方法的竞争性能。
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 from variational autoencoder (VAE) via 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 and more effective model for anomaly detection. In addition, to enhance the effectiveness of detecting anomalies, we incorporate a practical model uncertainty measure into the metric. We show empirically the competitive performance of our approach on benchmark datasets.
