Speaker
Jonathan Ostertag-Henning
(Institute for Theoretical Physics, Heidelberg University)
Description
Unsupervised anomaly detection with autoencoders is a promising data-driven and model-agnostic approach for new physics searches at the LHC. However, current anomaly scores assigned by neural networks suffer from a lack of statistical interpretability. The normalized autoencoder (NAE) combines a standard bottleneck architecture with a well-defined probabilistic description. We show that the NAE ties its anomaly score to a learned likelihood via an energy-based training objective, and introduce a Bayesian version of the NAE (BNAE) that additionally provides machine-learned uncertainty estimates. We validate both on a toy model and demonstrate competitive and symmetric anomaly-tagging performance on top-versus-QCD jet tagging.
Authors
Ranit Das
(Rutgers University)
Jonathan Ostertag-Henning
(Institute for Theoretical Physics, Heidelberg University)
Tilman Plehn
Lorenz Vogel
(Institute for Theoretical Physics, Heidelberg University)