Unsupervised tagging of semivisible jets with normalized autoencoders in CMS
Open access
Author
Date
2024-03-21Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
A particularly interesting application of autoencoders (AE) for High Energy Physics is their use as anomaly detection (AD) algorithms to perform a signal-agnostic search for new physics. This is achieved by training the AE on standard model physics and tagging potential signal events as anomalies. The use of an AE as an AD algorithm relies on the assumption that the network better reconstructs examples it was trained on than ones drawn from a different probability distribution, i.e. anomalies. Using the search for non resonant production of semivisible jets as a benchmark, we demonstrate the tendency of AEs to generalize beyond the dataset they are trained on, hindering their performance. We show how normalized AEs, specifically designed to suppress this effect, give a sizable boost in performance. We further propose a different loss function and signal-agnostic training stopping condition to reach the optimal performance. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000667795Publication status
publishedExternal links
Book title
The European Physical Society Conference on High Energy PhysicsJournal / series
PoS: Proceedings of ScienceVolume
Publisher
Sissa MedialabEvent
Organisational unit
02532 - Institut für Teilchen- und Astrophysik / Inst. Particle Physics and Astrophysics
Notes
On behalf of the CMS Collaboration.More
Show all metadata
ETH Bibliography
yes
Altmetrics