| Home > Publications database > Machine learning amplitudes for faster event generation |
| Typ | Amount | VAT | Currency | Share | Status | Cost centre |
| Hybrid-OA | 0.00 | 0.00 | EUR | (Flatrate) | 28920 / 476153 | |
| Sum | 0.00 | 0.00 | EUR | |||
| Total | 0.00 |
| Journal Article | PUBDB-2023-07947 |
;
2023
American Physical Society
Ridge, NY
This record in other databases:
Please use a persistent id in citations: doi:10.1103/PhysRevD.107.L071901 doi:10.3204/PUBDB-2023-07947
Report No.: DESY-19-232; arXiv:1912.11055
Abstract: We propose to replace the exact amplitudes used in Monte Carlo event generators for trained machine learning regressors, with the aim of speeding up the evaluation of slow amplitudes. As a proof of concept, we study the process $gg→ZZ$, whose leading-order amplitude is loop induced. We show that gradient boosting machines like xgboost can predict the fully differential distributions with errors below 0.1%, and with prediction times $O(10^3)$ faster than the evaluation of the exact function. This is achieved with training times $∼ 23$ $minutes$ and regressors of size $≲ 22$ $Mb$. We also find that xgboost performs well over the entire phase space, while interpolation gives much larger errors in regions where the function is peaked. These results suggest a possible new avenue to speed up Monte Carlo event generators.
Keyword(s): Monte Carlo ; scattering amplitude ; gluon gluon --> Z0 Z0 ; neural network ; gluon gluon ; computer ; numerical calculations
;
|
The record appears in these collections: |
Preprint
(Machine) Learning amplitudes for faster event generation
(2019) [10.3204/PUBDB-2020-00300]
Files
Fulltext by arXiv.org
BibTeX |
EndNote:
XML,
Text |
RIS