Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)

Alanazi, Yasir; Sato, Nobuo; Liu, Tianbo; Melnitchouk, Wally; Ambrozewicz, Pawel; Hauenstein, Florian; Kuchera, Michelle P.; Pritchard, Evan; Robertson, Michael; Strauss, Ryan; Velasco, Luisa; Li, Yaohang

doi:10.24963/ijcai.2021/293

Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)

Yasir Alanazi, Nobuo Sato, Tianbo Liu, Wally Melnitchouk, Pawel Ambrozewicz, Florian Hauenstein, Michelle P. Kuchera, Evan Pritchard, Michael Robertson, Ryan Strauss, Luisa Velasco, Yaohang Li

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 2126-2132.

https://doi.org/10.24963/ijcai.2021/293

Keywords

Multidisciplinary Topics and Applications: Natural Sciences
Machine Learning: Learning Generative Models
Machine Learning: Deep Learning

Abstract

We apply generative adversarial network (GAN) technology to build an event generator that simulates particle production in electron-proton scattering that is free of theoretical assumptions about underlying particle dynamics. The difficulty of efficiently training a GAN event simulator lies in learning the complicated patterns of the distributions of the particles physical properties. We develop a GAN that selects a set of transformed features from particle momenta that can be generated easily by the generator, and uses these to produce a set of augmented features that improve the sensitivity of the discriminator. The new Feature-Augmented and Transformed GAN (FAT-GAN) is able to faithfully reproduce the distribution of final state electron momenta in inclusive electron scattering, without the need for input derived from domain-based theoretical assumptions. The developed technology can play a significant role in boosting the science of existing and future accelerator facilities, such as the Electron-Ion Collider.

Yasir Alanazi, Nobuo Sato, Tianbo Liu, Wally Melnitchouk, Pawel Ambrozewicz, Florian Hauenstein, Michelle P. Kuchera, Evan Pritchard, Michael Robertson, Ryan Strauss, Luisa Velasco, and Yaohang Li. 2021. Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN). In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 2126–2132. https://doi.org/10.24963/ijcai.2021/293

@inproceedings{ijcai2021p293,
  title     = {Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)},
  author    = {Alanazi, Yasir and Sato, Nobuo and Liu, Tianbo and Melnitchouk, Wally and Ambrozewicz, Pawel and Hauenstein, Florian and Kuchera, Michelle P. and Pritchard, Evan and Robertson, Michael and Strauss, Ryan and Velasco, Luisa and Li, Yaohang},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {2126--2132},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/293},
  url       = {https://doi.org/10.24963/ijcai.2021/293},
}

TY  - CPAPER
TI  - Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
AU  - Alanazi, Yasir
AU  - Sato, Nobuo
AU  - Liu, Tianbo
AU  - Melnitchouk, Wally
AU  - Ambrozewicz, Pawel
AU  - Hauenstein, Florian
AU  - Kuchera, Michelle P.
AU  - Pritchard, Evan
AU  - Robertson, Michael
AU  - Strauss, Ryan
AU  - Velasco, Luisa
AU  - Li, Yaohang
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 2126
EP  - 2132
DO  - 10.24963/ijcai.2021/293
UR  - https://doi.org/10.24963/ijcai.2021/293
ER  -