Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows

ArXi:2603.11756v1 Announce Type: new Deep generative models for anomaly detection in multivariate time-series are typically trained by maximizing data likelihood. However, likelihood in observation space measures marginal density rather than conformity to structured temporal dynamics, and. therefore. can assign high probability to anomalous or out-of-distribution samples. We address this structural limitation by relocating the notion of anomaly to a prescribed latent space. We