Generative networks for precision enthusiasts
Generative networks are opening new avenues in fast event generation for the LHC. We show how generative flow networks can reach percent-level precision for kinematic distributions, how they can be trained jointly with a discriminator, and how this discriminator improves the generation. Our joint tr...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article (Journal) Chapter/Article |
| Language: | English |
| Published: |
9 Dec 2021
|
| In: |
Arxiv
Year: 2020, Pages: 1-27 |
| DOI: | 10.48550/arXiv.2110.13632 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2110.13632 Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2110.13632 
|
| Author Notes: | Anja Butter, Theo Heimel, Sander Hummerich, Tobias Krebs, Tilman Plehn, Armand Rousselot, and Sophia Vent |
| Summary: | Generative networks are opening new avenues in fast event generation for the LHC. We show how generative flow networks can reach percent-level precision for kinematic distributions, how they can be trained jointly with a discriminator, and how this discriminator improves the generation. Our joint training relies on a novel coupling of the two networks which does not require a Nash equilibrium. We then estimate the generation uncertainties through a Bayesian network setup and through conditional data augmentation, while the discriminator ensures that there are no systematic inconsistencies compared to the training data. |
|---|---|
| Item Description: | Gesehen am 15.09.2022 |
| Physical Description: | Online Resource |
| DOI: | 10.48550/arXiv.2110.13632 |