Neural Network Parametrization of Deep-Inelastic Structure Functions

Abstract

We construct a parametrization of deep-inelastic structure functions which retains information on experimental errors and correlations, and which does not introduce any theoretical bias while interpolating between existing data points. We generate a Monte Carlo sample of pseudo-data configurations and we train an ensemble of neural networks on them. This effectively provides us with a probability measure in the space of structure functions, within the whole kinematic region where data are available. This measure can then be used to determine the value of the structure function, its error, point-to-point correlations and generally the value and uncertainty of any function of the structure function itself. We apply this technique to the determination of the structure function F_2 of the proton and deuteron, and a precision determination of the isotriplet combination F_2[p-d]. We discuss in detail these results, check their stability and accuracy, and make them available in various formats for applications.

Latex, 43 pages, 22 figures. (v2) Final version, published in JHEP; Sect.5.2 and Fig.9 improved, a few typos corrected and other minor improvements. (v3) Some inconsequential typos in Tab.1 and Tab 5 corrected. Neural parametrization available at http://sophia.ecm.ub.es/f2neural

References in corpus (3)

• Parton Distribution Function Uncertainties
• Solving the Altarelli-Parisi equations with truncated moments
• A determination of alpha_s from scaling violations with truncated moments

Cited by in corpus (128)

• Parton distributions for the LHC Run II
• Machine learning and the physical sciences
• Parton distributions with LHC data
• Phenomenology with Massive Neutrinos
• Heavy-flavour and quarkonium production in the LHC era: from proton-proton to heavy-ion collisions
• QCD and strongly coupled gauge theories: challenges and perspectives
• The Path to Proton Structure at One-Percent Accuracy
• A first unbiased global NLO determination of parton distributions and their uncertainties
• Impact of Heavy Quark Masses on Parton Distributions and LHC Phenomenology
• A determination of parton distributions with faithful uncertainty estimation
• Parton distributions and lattice QCD calculations: a community white paper
• The Structure of the Proton in the LHC Precision Era
• 50 Years of Quantum Chromodynamics
• GPD phenomenology and DVCS fitting - Entering the high-precision era
• Learning New Physics from a Machine
• A determination of the fragmentation functions of pions, kaons, and protons with faithful uncertainties
• Investigations into the flavor dependence of partonic transverse momentum
• Towards a fitting procedure for deeply virtual Compton scattering at next-to-leading order and beyond
• Progress in the Determination of the Partonic Structure of the Proton
• Precision determination of electroweak parameters and the strange content of the proton from neutrino deep-inelastic scattering
• First extraction of valence transversities in a collinear framework
• Fitting Parton Distribution Data with Multiplicative Normalization Uncertainties
• Machine Learning and LHC Event Generation
• The Theory of Deeply Inelastic Scattering
• Snowmass 2021 whitepaper: Proton structure at the precision frontier
• Neural network determination of parton distributions: the nonsinglet case
• Hadron structure in high-energy collisions
• Reconstructing parton distribution functions from Ioffe time data: from Bayesian methods to Neural Networks
• Nuclear Parton Distributions from Lepton-Nucleus Scattering and the Impact of an Electron-Ion Collider
• Saturation in Deep Inelastic Scattering from AdS/CFT
• Exploring QCD matter in extreme conditions with Machine Learning
• Search for leptonic decays of W' bosons in pp collisions at sqrt(s) = 7 TeV
• nNNPDF2.0: Quark Flavor Separation in Nuclei from LHC Data
• A Kinematically Complete Measurement of the Proton Structure Function F2 in the Resonance Region and Evaluation of Its Moments
• Parton momentum and helicity distributions in the nucleon
• Hadrons and Nuclei
• Deviations from NLO QCD evolution in inclusive HERA data
• Neural network parametrization of spectral functions from hadronic tau decays and determination of QCD vacuum condensates
• Open-source QCD analysis of nuclear parton distribution functions at NLO and NNLO
• Hunting BFKL in semi-hard reactions at the LHC
• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Unbiased determination of the proton structure function F_2^p with faithful uncertainty estimation
• Tevatron Run II combination of the effective leptonic electroweak mixing angle
• Determination of the Atmospheric Neutrino Fluxes from Atmospheric Neutrino Data
• Neural network generated parametrizations of deeply virtual Compton form factors
• Novel approaches in Hadron Spectroscopy
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Neutrino Structure Functions from GeV to EeV Energies
• Application of neural network to sign problem via path optimization method
• Reconstructing the neutron star equation of state from observational data via automatic differentiation
• Reconstruction of Monte Carlo replicas from Hessian parton distributions
• Determination of the $WW$ polarization fractions in $pp\to W^{\pm }{W}^{\pm }jj$ using a deep machine learning technique
• HERA data and DGLAP evolution: theory and phenomenology
• Soft-gluon resummation effects on parton distributions
• Bottom-flavored inclusive emissions in the variable-flavor number scheme: A high-energy analysis
• High-energy emissions of light mesons plus heavy flavor at the LHC and the Forward Physics Facility
• Reconstructing spectral functions via automatic differentiation
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Deuteron Uncertainties in the Determination of Proton PDFs
• Towards a Deep Learning Model for Hadronization
• Evolution of singlet structure functions from DGLAP equation at next-to-next-to-leading order at small-x
• Revealing the nature of hidden charm pentaquarks with machine learning
• A global extraction of the jet transport coefficient in cold nuclear matter
• Mueller-Navelet jets at the LHC: hunting data with azimuthal distributions
• Vector quarkonia at the LHC with JETHAD: A high-energy viewpoint
• Deep Learning Exotic Hadrons
• Towards a new generation of parton densities with deep learning models
• Determination of alpha_s from scaling violations of truncated moments of structure functions
• Emergence of high-energy dynamics from cascade-baryon detections at the LHC
• Re-evaluation of the Gottfried sum using neural networks
• Measurement of ${\sin }^2{\theta }_{\mathrm{eff}}^{\mathrm{lept}}$ using $e^{+}{e}^{-}$ pairs from ${\gamma }^{\ast }/Z$ bosons produced in $p\bar{p}$ collisions at a center-of-momentum energy of 1.96 TeV
• NNVub: a Neural Network Approach to $B\to X_u\ell \nu$
• Charting the low-loss region in Electron Energy Loss Spectroscopy with machine learning
• High-energy QCD dynamics from bottom flavor fragmentation at the Hi-Lumi LHC
• A high-energy QCD portal to exotic matter: Heavy-light tetraquarks at the HL-LHC
• Parton distributions at the dawn of the LHC
• Exotic tetraquarks at the HL-LHC with JETHAD: A high-energy viewpoint
• Future tests of parton distributions
• A journey into the proton structure: Progresses and challenges
• On the Impact of NMC Data on NLO and NNLO Parton Distributions and Higgs Production at the Tevatron and the LHC
• Neural Network Parameterizations of Electromagnetic Nucleon Form Factors
• On the determination of uncertainties in parton densities
• Machine learning of log-likelihood functions in global analysis of parton distributions
• Learning Multivariate New Physics
• EasyScan_HEP: a tool for connecting programs to scan the parameter space of physics models
• No-quenching baseline for energy loss signals in oxygen-oxygen collisions
• New avenue to the Parton Distribution Functions: Self-Organizing Maps
• Deep Neural Network application: Higgs boson CP state mixing angle in H to tau tau decay and at LHC
• QCD analysis of $W$- and $Z$-boson production at Tevatron
• Probing gluon helicity with heavy flavor at the EIC
• Machine Learning tools for global PDF fits
• Neural network parametrization of the lepton energy spectrum in semileptonic B meson decays
• Parton distribution functions
• New extraction of alpha_s(MZ) from proton DIS data
• Reconstructing partonic kinematics at colliders with Machine Learning
• A data-based parametrization of parton distribution functions
• The high-energy limit of perturbative QCD: Theory and phenomenology
• Pseudoscalar heavy-quarkonium hadroproduction from nonrelativistic fragmentation at NLL/NLO${}^{+}$
• NNPDF1.0 parton set for the LHC
• Extraction of characteristic constants in QCD with perturbative and nonperturbative methods
• Triply Heavy $\Omega$ Baryons with JETHAD: A High-Energy Viewpoint
• Tetraquark-Jet Systems at the High-Luminosity LHC
• The neural network approach to parton distribution functions
• The Bjorken sum rule with Monte Carlo and Neural Network techniques
• Neural network approach to parton distributions fitting
• Structure Functions and Parton Distributions
• Determination of $K_S^0$ Fragmentation Functions including BESIII Measurements and using Neural Networks
• Fragmentation Functions for ${\Xi }^{-}/{\bar{\Xi }}^{+}$ Using Neural Networks
• Exploring Nucleon Structure with the Self-Organizing Maps Algorithm
• Progress on neural parton distributions
• On the derivatives of feed-forward neural networks
• Parametrizing Compton form factors with neural networks
• Cascade Training Technique for Particle Identification
• Proton structure at the LHC
• Dihadron Fragmentation Functions and Transversity
• The NNPDF1.2 parton set: implications for the LHC
• inclusiveAI: A machine learning representation of the $F_2$ structure function over all charted $Q^2$ and $x$ range
• The neural network approach to parton distributions
• Self-Organizing Maps Algorithm for Parton Distribution Functions Extraction
• Determination of the atmospheric neutrino fluxes from experimental data
• A multivariate approach to heavy flavour tagging with cascade training
• Semileptonic decays of heavy mesons with artificial neural networks
• Monte Carlo analysis of CLAS data
• Continuous simulation of hypothetical physics processes with multiple free parameters
• Assessing the impact of the electron ion collider in China on Deeply Virtual Compton Scattering
• Exploring the substructure of nucleons and nuclei with machine learning
• DGLAP equation and x-evolution of Non-singlet structure function in Leading order
• Extraction of the atmospheric neutrino fluxes from experimental event rate data