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

The versatility of flow-based fast calorimeter surrogate models

7 Nov 2024, 09:20
20m
Amphi Charpak

Amphi Charpak

Amphi Charpak

Speaker

Ian Pang

Description

Normalizing flows have proven to be state-of-the-art for fast calorimeter simulation. With access to the likelihood, these flow-based fast calorimeter surrogate models can be used for other tasks such as unsupervised anomaly detection (arXiv:2312.11618) and particle incident energy calibration (arXiv:2404.18992) without any additional training costs. Using CaloFlow as an example, we show that the unsupervised anomaly detector is sensitive to a wide range of signals, while the calibration approach is prior-independent and has access to per-shower resolution information.

Authors

Ben Nachman (Lawrence Berkeley National Lab. (US)) Dr Claudius Krause (HEPHY Vienna (ÖAW)) David Shih Haoxing Du Ian Pang Vinicius Massami Mikuni (Lawrence Berkeley National Lab. (US)) Yunhao Zhu

Presentation materials