Improved neural network Monte Carlo simulation
The algorithm for Monte Carlo simulation of parton-level events based on an Artificial Neural Network (ANN) proposed in arXiv:1810.11509 is used to perform a simulation of $H\to 4\ell$ decay. Improvements in the training algorithm have been implemented to avoid numerical instabilities. The integr...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SciPost
2021-01-01
|
| Series: | SciPost Physics |
| Online Access: | https://scipost.org/SciPostPhys.10.1.023 |
| _version_ | 1818945883666907136 |
|---|---|
| author | I-Kai Chen, Matthew D. Klimek, Maxim Perelstein |
| author_facet | I-Kai Chen, Matthew D. Klimek, Maxim Perelstein |
| author_sort | I-Kai Chen, Matthew D. Klimek, Maxim Perelstein |
| collection | DOAJ |
| description | The algorithm for Monte Carlo simulation of parton-level events based on an
Artificial Neural Network (ANN) proposed in arXiv:1810.11509 is used to perform
a simulation of $H\to 4\ell$ decay. Improvements in the training algorithm have
been implemented to avoid numerical instabilities. The integrated decay width
evaluated by the ANN is within 0.7% of the true value and unweighting
efficiency of 26% is reached. While the ANN is not automatically bijective
between input and output spaces, which can lead to issues with simulation
quality, we argue that the training procedure naturally prefers bijective maps,
and demonstrate that the trained ANN is bijective to a very good approximation. |
| first_indexed | 2024-12-20T08:06:12Z |
| format | Article |
| id | doaj.art-2582d41d84954025bb8e036f48999121 |
| institution | Directory Open Access Journal |
| issn | 2542-4653 |
| language | English |
| last_indexed | 2024-12-20T08:06:12Z |
| publishDate | 2021-01-01 |
| publisher | SciPost |
| record_format | Article |
| series | SciPost Physics |
| spelling | doaj.art-2582d41d84954025bb8e036f489991212022-12-21T19:47:24ZengSciPostSciPost Physics2542-46532021-01-0110102310.21468/SciPostPhys.10.1.023Improved neural network Monte Carlo simulationI-Kai Chen, Matthew D. Klimek, Maxim PerelsteinThe algorithm for Monte Carlo simulation of parton-level events based on an Artificial Neural Network (ANN) proposed in arXiv:1810.11509 is used to perform a simulation of $H\to 4\ell$ decay. Improvements in the training algorithm have been implemented to avoid numerical instabilities. The integrated decay width evaluated by the ANN is within 0.7% of the true value and unweighting efficiency of 26% is reached. While the ANN is not automatically bijective between input and output spaces, which can lead to issues with simulation quality, we argue that the training procedure naturally prefers bijective maps, and demonstrate that the trained ANN is bijective to a very good approximation.https://scipost.org/SciPostPhys.10.1.023 |
| spellingShingle | I-Kai Chen, Matthew D. Klimek, Maxim Perelstein Improved neural network Monte Carlo simulation SciPost Physics |
| title | Improved neural network Monte Carlo simulation |
| title_full | Improved neural network Monte Carlo simulation |
| title_fullStr | Improved neural network Monte Carlo simulation |
| title_full_unstemmed | Improved neural network Monte Carlo simulation |
| title_short | Improved neural network Monte Carlo simulation |
| title_sort | improved neural network monte carlo simulation |
| url | https://scipost.org/SciPostPhys.10.1.023 |
| work_keys_str_mv | AT ikaichenmatthewdklimekmaximperelstein improvedneuralnetworkmontecarlosimulation |