Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detection
This work addresses anomaly detection in time series data, which is incremental as it builds on normalizing flows with a novel conditioning approach.
The paper tackles anomaly detection in multivariate time series by introducing temporal-conditioned normalizing flows (tcNF), which model temporal dependencies and uncertainty to identify low-probability events, achieving good accuracy and robustness on diverse datasets.
This paper introduces temporal-conditioned normalizing flows (tcNF), a novel framework that addresses anomaly detection in time series data with accurate modeling of temporal dependencies and uncertainty. By conditioning normalizing flows on previous observations, tcNF effectively captures complex temporal dynamics and generates accurate probability distributions of expected behavior. This autoregressive approach enables robust anomaly detection by identifying low-probability events within the learned distribution. We evaluate tcNF on diverse datasets, demonstrating good accuracy and robustness compared to existing methods. A comprehensive analysis of strengths and limitations and open-source code is provided to facilitate reproducibility and future research.