Bump hunting in latent space

• Verfasst von: Bortolato, Blaž [VerfasserIn]
• Verfasst von: Smolkovič, Aleks [VerfasserIn]
• Verfasst von: Dillon, Barry M. [VerfasserIn]
• Verfasst von: Kamenik, Jernej F. [VerfasserIn]
• Titel: Bump hunting in latent space
• Verf.angabe: Blaž Bortolato, Aleks Smolkovič, Barry M. Dillon, Jernej F. Kamenik
• E-Jahr: 2022
• Jahr: 3 June 2022
• Umfang: 8 S.
• Fussnoten: Gesehen am 20.01.2023
• Titel Quelle: Enthalten in: Physical review
• Ort Quelle: Ridge, NY : American Physical Society, 2016
• Jahr Quelle: 2022
• Band/Heft Quelle: 105(2022), 11, Artikel-ID 115009, Seite 1-8
• ISSN Quelle: 2470-0029
• DOI: doi:10.1103/PhysRevD.105.115009
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1831607441

Abstract

Unsupervised anomaly-detection could be crucial in future analyses searching for rare phenomena in large datasets, as for example collected at the LHC. To this end, we introduce a physics inspired variational autoencoder (VAE) architecture which performs competitively and robustly on the LHC Olympics Machine Learning Challenge datasets. We demonstrate how embedding some physical observables directly into the VAE latent space, while at the same time keeping the anomaly-detection manifestly agnostic to them, can help to identify and characterize features in measured spectra as caused by the presence of anomalies in a dataset.