Normalizing Flows for High-Dimensional Detector Simulations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916643230187520 |
|---|---|
| author | Ernst, Florian Favaro, Luigi Krause, Claudius Plehn, Tilman Shih, David |
| author_facet | Ernst, Florian Favaro, Luigi Krause, Claudius Plehn, Tilman Shih, David |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09290 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Normalizing Flows for High-Dimensional Detector Simulations Ernst, Florian Favaro, Luigi Krause, Claudius Plehn, Tilman Shih, David High Energy Physics - Phenomenology 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. |
| title | Normalizing Flows for High-Dimensional Detector Simulations |
| topic | High Energy Physics - Phenomenology |
| url | https://arxiv.org/abs/2312.09290 |