Machine Learning tools for global PDF fits
arXiv:1809.04392
Abstract
The use of machine learning algorithms in theoretical and experimental high-energy physics has experienced an impressive progress in recent years, with applications from trigger selection to jet substructure classification and detector simulation among many others. In this contribution, we review the machine learning tools used in the NNPDF family of global QCD analyses. These include multi-layer feed-forward neural networks for the model-independent parametrisation of parton distributions and fragmentation functions, genetic and covariance matrix adaptation algorithms for training and optimisation, and closure testing for the systematic validation of the fitting methodology.
arXiv comment12 pages, 9 figures, to appear in the proceedings of the XXIIIth Quark Confinement and the Hadron Spectrum conference, 1-6 August 2018, University of Maynooth, Ireland
References in corpus (10)
- A first unbiased global NLO determination of parton distributions and their uncertainties
- APFEL: A PDF Evolution Library with QED corrections
- A first unbiased global determination of polarized PDFs and their uncertainties
- A determination of parton distributions with faithful uncertainty estimation
- Parton distributions and lattice QCD calculations: a community white paper
- Illuminating the photon content of the proton within a global PDF analysis
- Neural Network Parametrization of Deep-Inelastic Structure Functions
- Reweighting NNPDFs: the W lepton asymmetry
- The asymptotic behaviour of parton distributions at small and large
- APFELgrid: a high performance tool for parton density determinations