Bayesian Tensor Autoencoder with Physics-informed Predictive Prior for Multi-dimensional Time Series Anomaly Detection

The paper introduces a Physics-informed Predictive Prior Tensor Autoencoder (PPPTAE) for anomaly detection in multi-dimensional time series. It combines reconstruction-based and prediction-based autoencoders by embedding a Bayesian fusion approach and a predictive prior that respects tensor correlations. The method incorporates physical laws via tensor low‑rank decomposition to prevent over‑generalization and is validated on real‑world datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.