Normalizing flows for high-dimensional detector simulations
SciPost Physics · 05.03.2025 · 18 (3)
DOI: 10.21468/scipostphys.18.3.081 ↗Kurz gefasst
Fachartikel in der Zeitschrift SciPost Physics, online erschienen am 05.03.2025. Verfasst von Florian Ernst und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 115 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Baden-Württemberg Stiftung, Deutsche Forschungsgemeinschaft, United States Department of Energy.
Abstract (Originalsprache)
Whenever invertible generative networks are needed for LHC physics, normalizing flows show excellent performance. In this work, we investigate their performance for fast calorimeter shower simulations with increasing phase space dimension. We use fast and expressive coupling spline transformations applied to the CaloChallenge datasets. In addition to the base flow architecture we also employ a VAE to compress the dimensionality and train a generative network in the latent space. We evaluate our networks on several metrics, including high-level features, classifiers, and generation timing. Our findings demonstrate that invertible neural networks have competitive performance when compared to autoregressive flows, while being substantially faster during generation.
Förderung
- Baden-Württemberg Stiftung
- Deutsche Forschungsgemeinschaft
- United States Department of Energy
Zitieren
APA
Ernst, F., Favaro, L., Krause, C., Plehn, T., & Shih, D. (2025). Normalizing flows for high-dimensional detector simulations. SciPost Physics, 18(3). https://doi.org/10.21468/scipostphys.18.3.081
Vancouver
Ernst F, Favaro L, Krause C, Plehn T, Shih D. Normalizing flows for high-dimensional detector simulations. SciPost Physics. 2025;18(3). doi:10.21468/scipostphys.18.3.081
BibTeX
@article{Ernst2025,
author = {Ernst, Florian and Favaro, Luigi and Krause, Claudius and Plehn, Tilman and Shih, David},
title = {Normalizing flows for high-dimensional detector simulations},
journal = {SciPost Physics},
year = {2025},
volume = {18},
number = {3},
doi = {10.21468/scipostphys.18.3.081}
}
EUVIMED