Orateur
Lorenz Vogel
(ITP, 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, although neural network-based anomaly scores have transformative potential, they suffer from a lack of statistical interpretability. The normalized autoencoder (NAE) provides a probabilistic interpretation of the standard bottleneck architecture, tying the anomaly score to a learned likelihood. We validate this relation for a toy model, test it for jets using a dual-NAE setup, and show how a Bayesian NAE learns this likelihood with an uncertainty.
Auteurs
Ranit Das
(ITP, Heidelberg University)
Jonathan Ostertag-Henning
(ITP, Heidelberg University)
Tilman Plehn
(ITP and IWR, Heidelberg University)
Lorenz Vogel
(ITP, Heidelberg University)