Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational A

论文：《Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder》 Thus， in this paper we propose Bagel, a robust and unsupervised anomaly detection algorithm for KPI that can handle time information related anomalies.

主要细节去看Donut的论文比看这篇论文更好，两篇结合查看更有助于理解。

KPI: key performance indicator

1. CVAE(conditional variational auto-encoder, 条件变分自编码器）:arxiv.org/abs/1511.06…

用于处理时序信息

2. dropout layer：to avoid overfitting.

• KPI v = (v1, v2, ..., vn)
• the i-th window of the KPI is x(i) = (vi, vi+1, ..., vi+W−1)
• z prior：p(z|y)=p(z)=N(0, i)
• z posterior: $q_{\phi}(z|x,y)=N(\mu_{z},diag(\sigma^2_z))$
• x posterior: $p_{\theta}(x|z,y)=N(\mu_x,diag(\sigma^2_x))$
• $\mu_z = W^T_{\mu_z}f_{\phi}(x)+b_{\mu_z}$
• $\mu_x=W^T_{\mu_x}f_{\theta}(z)+b_{\mu_x}$
• $\sigma_z=ln(1+exp(f_\phi(x)))+\Delta$
• $\sigma_x=ln(1+exp(f_\theta(z)))+\Delta$