4–8 Nov 2024
LPNHE, Paris, France
Europe/Paris timezone

Learning powerful jet representations via self-supervision

7 Nov 2024, 16:00
20m
Salle Séminaires

Salle Séminaires

Speaker

Shudong Wang (Chinese Academy of Sciences (CN))

Description

We propose a new approach to learning powerful jet representations directly from unlabelled data. The method employs a Particle Transformer to predict masked particle representations in a latent space, overcoming the need for discrete tokenization and enabling it to extend to arbitrary input features beyond the Lorentz four-vectors. We demonstrate the effectiveness and flexibility of this method in several downstream tasks, including jet tagging and anomaly detection. Our approach provides a new path to a foundation model for particle physics.

Authors

Congqiao Li (Peking University (CN)) Huilin Qu (CERN) Qibin Liu (Tsung-Dao Lee Institute (CN) & Shanghai Jiao Tong University (CN)) Shudong Wang (Chinese Academy of Sciences (CN))

Presentation materials