Preprint PUBDB-2020-00300

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png
(Machine) Learning amplitudes for faster event generation

 ;

2019

This record in other databases:    

Please use a persistent id in citations: doi:

Report No.: DESY 19-232; arXiv:1912.11055

Abstract: We propose to replace the exact amplitudes used in MC event generators for trained Machine Learning regressors, with the aim of speeding up the evaluation of {\it slow} amplitudes. As a proof of concept, we study the process $gg \to ZZ$ whose LO amplitude is loop induced. We show that gradient boosting machines like $\texttt{XGBoost}$ can predict the fully differential distributions with errors below $0.1 \%$, and with prediction times $\mathcal{O}(10^3)$ faster than the evaluation of the exact function. This is achieved with training times $\sim 7$ minutes and regressors of size $\lesssim 30$~Mb. These results suggest a possible a new avenue to speed up MC event generators.


Contributing Institute(s):
  1. Theorie-Gruppe (T)
Research Program(s):
  1. 611 - Fundamental Particles and Forces (POF3-611) (POF3-611)
  2. EXC 2121 - Das Quantisierte Universum (390833306) (390833306)
  3. NewAve - New avenues towards solving the dark matter puzzle (638528) (638528)
Experiment(s):
  1. No specific instrument

Appears in the scientific report 2019
Database coverage:
OpenAccess ; Published
Click to display QR Code for this record

The record appears in these collections:
Private Collections > >DESY > >D_DIR > >HH > >FH > T
Document types > Reports > Preprints
Public records
Publications database
OpenAccess


Linked articles:

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Journal Article  ;
Machine learning amplitudes for faster event generation
Physical review / D 107(7), L071901 () [10.1103/PhysRevD.107.L071901]  GO OpenAccess  Download fulltext Files  Download fulltextFulltext by arXiv.org BibTeX | EndNote: XML, Text | RIS


 Record created 2020-01-15, last modified 2023-12-24


OpenAccess:
Download fulltext PDF Download fulltext PDF (PDFA)
External link:
Download fulltextFulltext by arXiv.org
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)