Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 22 min ago
Peer-reviewedCC BYSciPost Physics

FASTColor – Full-color amplitude surrogate toolkit for QCD

  • Javier Mariño Villadamigo1
  • Rikkert Frederix2
  • Tilman Plehn1
  • Timea Vitos3,4
  • Ramon Winterhalder5,6
6 affiliations
  1. 1Heidelberg University
  2. 2Lund University
  3. 3Eötvös Loránd University
  4. 4Uppsala University
  5. 5INFN Sezione di Milano
  6. 6University of Milan
Open at sourceDOICite

Abstract

High-multiplicity events remain a bottleneck for LHC simulations due to their computational cost. We present a ML-surrogate approach to accelerate matrix element reweighting from leading-color (LC) to full-color (FC) accuracy, building on recent advancements in LC event generation. Comparing a variety of modern network architectures for representative QCD processes, we achieve speed-up of around a factor two over the current LC-to-FC baseline. We also show how transformers learn and exploit underlying symmetries, to improve generalization. Given the gained trust in trained networks and developments in learned uncertainties, the LC-to-FC approach will eventually benefit further from not needing a final classic unweighting step.

Related

  1. Design of Single-Layer Full-Color Achromatic Metagratings Based on Silicon Carbide
    Haoran Zhang, RongKun Wang, Xuejian Xie +3
    Optics ExpressPeer-reviewedLicence not statedOptics & photonicsCrossref
  2. A differentiable PCA-GPR surrogate framework for full-transient Bayesian inverse uncertainty quantification of black-box nuclear thermal-hydraulic systems
    Zikang Yaoa, Eugene Yeea, Fue-Sang Lien
    arXivPreprintarXiv licenceFull textComputational physicsFluid dynamicsarXiv
  3. A 0.35 mm Silicon Carbide Diffractive Waveguide with Dual Parameter Apodization for Full Color Augmented Reality
    Xiaoxuan Li, Ce Li, Yinggang Chen +5
    arXivPreprintCC BY-NC-ND 4.0Full textOptics & photonicsarXiv
  4. meer21cm: an Analysis Pipeline and Comprehensive Toolkit for HI Intensity Mapping
    Zhaoting Chen, Steven Cunnington, Daniel Tassie +23
    HALPreprintLicence not statedGeneral astronomyApplied physics & instrumentationHAL
  5. A virtual reality extension for the Geant4 toolkit
    Benjamin Jobilal, Muhammad Ansar Iqbal, Jay Hauser
    arXivPreprintCC BY 4.0Full textHigh-energy & particle physicsNuclear physicsarXiv

Cite

BibTeXRIS
BibTeX
@article{villadamigo2026fastcolor,
  title = {{FASTColor – Full-color amplitude surrogate toolkit for QCD}},
  author = {Javier Mariño Villadamigo and Rikkert Frederix and Tilman Plehn and Timea Vitos and Ramon Winterhalder},
  journal = {SciPost Physics},
  year = {2026},
  month = jul,
  doi = {10.21468/scipostphys.21.1.001},
  url = {https://doi.org/10.21468/scipostphys.21.1.001},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - FASTColor – Full-color amplitude surrogate toolkit for QCD
AU  - Javier Mariño Villadamigo
AU  - Rikkert Frederix
AU  - Tilman Plehn
AU  - Timea Vitos
AU  - Ramon Winterhalder
PY  - 2026
DA  - 2026/07/01
JO  - SciPost Physics
DO  - 10.21468/scipostphys.21.1.001
UR  - https://doi.org/10.21468/scipostphys.21.1.001
AB  - High-multiplicity events remain a bottleneck for LHC simulations due to their computational cost. We present a ML-surrogate approach to accelerate matrix element reweighting from leading-color (LC) to full-color (FC) accuracy, building on recent advancements in LC event generation. Comparing a variety of modern network architectures for representative QCD processes, we achieve speed-up of around a factor two over the current LC-to-FC baseline. We also show how transformers learn and exploit underlying symmetries, to improve generalization. Given the gained trust in trained networks and developments in learned uncertainties, the LC-to-FC approach will eventually benefit further from not needing a final classic unweighting step.
SN  - 2542-4653
ER  -