Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics

Abstract

The integration of deep learning techniques and physics-driven designs is reforming the way we address inverse problems, in which accurate physical properties are extracted from complex data sets. This is particularly relevant for quantum chromodynamics (QCD), the theory of strong interactions, with its inherent limitations in observational data and demanding computational approaches. This perspective highlights advances and potential of physics-driven learning methods, focusing on predictions of physical quantities towards QCD physics, and drawing connections to machine learning(ML). It is shown that the fusion of ML and physics can lead to more efficient and reliable problem-solving strategies. Key ideas of ML, methodology of embedding physics priors, and generative models as inverse modelling of physical probability distributions are introduced. Specific applications cover first-principle lattice calculations, and QCD physics of hadrons, neutron stars, and heavy-ion collisions. These examples provide a structured and concise overview of how incorporating prior knowledge such as symmetry, continuity and equations into deep learning designs can address diverse inverse problems across different physical sciences.

14 pages, 5 figures, submitted version to Nat Rev Phys

References in corpus (72)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Machine learning and the physical sciences
• Machine learning phases of matter
• Hadronic molecules
• Score-Based Generative Modeling through Stochastic Differential Equations
• From hadrons to quarks in neutron stars: a review
• Deep Neural Networks as Gaussian Processes
• Nuclear Force from Lattice QCD
• The Neutron Star Mass-Radius Relation and the Equation of State of Dense Matter
• The Dense Matter Equation of State from Neutron Star Radius and Mass Measurements
• Machine Learning in Nuclear Physics
• 50 Years of Quantum Chromodynamics
• Phenomenological constraints on the transport properties of QCD matter with data-driven model averaging
• Equivariant flow-based sampling for lattice gauge theory
• Unveiling the strong interaction among hadrons at the LHC
• Constraining the Eq. of State of Super-Hadronic Matter from Heavy-Ion Collisions
• Heavy Quarkonium in Extreme Conditions
• Graph Neural Networks in Particle Physics
• A transverse momentum differential global analysis of Heavy Ion Collisions
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Introductory lectures on lattice QCD at nonzero baryon number
• e3nn: Euclidean Neural Networks
• Mapping neutron star data to the equation of state using the deep neural network
• Regressive and generative neural networks for scalar field theory
• Deep Learning and AdS/CFT
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• A Living Review of Machine Learning for Particle Physics
• Determination of the neutron skin of ${}^{208}$Pb from ultrarelativistic nuclear collisions
• Exploring QCD matter in extreme conditions with Machine Learning
• Neural Networks and Quantum Field Theory
• Deep Learning and Holographic QCD
• Inference of the sound speed and related properties of neutron stars
• Machine learning action parameters in lattice quantum chromodynamics
• Machine learning the deuteron
• Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
• Physical Symmetries Embedded in Neural Networks
• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Novel approaches in Hadron Spectroscopy
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Reconstructing the neutron star equation of state from observational data via automatic differentiation
• Bayesian nonparametric inference of neutron star equation of state via neural network
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Deep learning stochastic processes with QCD phase transition
• QCD Equation of State of Dense Nuclear Matter from a Bayesian Analysis of Heavy-Ion Collision Data
• Little-Bang and Femto-Nova in Nucleus-Nucleus Collisions
• A fast centrality-meter for heavy-ion collisions at the CBM experiment
• Quantum field-theoretic machine learning
• Determination of Quark-Gluon-Plasma Parameters from a Global Bayesian Analysis
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Machine-learning physics from unphysics: Finding deconfinement temperature in lattice Yang-Mills theories from outside the scaling window
• Rethinking the ill-posedness of the spectral function reconstruction -- why is it fundamentally hard and how Artificial Neural Networks can help
• Advances in machine-learning-based sampling motivated by lattice quantum chromodynamics
• Diffusion Models as Stochastic Quantization in Lattice Field Theory
• Gravitational-Wave and X-ray Probes of the Neutron Star Equation of State
• Classifying Pole of Amplitude Using Deep Neural Network
• Model independent analysis of coupled-channel scattering: a deep learning approach
• Decoding Neutron Star Observations: Revealing Composition through Bayesian Neural Networks
• Deep-learning quasi-particle masses from QCD equation of state
• Deep Learning Exotic Hadrons
• From NS observations to nuclear matter properties: a machine learning approach
• Examination of nucleon distribution with Bayesian imaging for isobar collisions
• Applications of Machine Learning to Lattice Quantum Field Theory
• Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network
• Geometrical aspects of lattice gauge equivariant convolutional neural networks
• Identifying the nature of the QCD transition in heavy-ion collisions with deep learning
• Lattice QCD and Baryon-Baryon Interactions
• Renormalizing Diffusion Models
• Inverse renormalization group of spin glasses
• Neural Ordinary Differential Equations for Mapping the Magnetic QCD Phase Diagram via Holography
• Building Hadron Potentials from Lattice QCD with Deep Neural Networks
• Doubly charmed tetraquark $T_{cc}^{+}$ in (2+1)-flavor QCD near physical point

Cited by in corpus (11)

• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• Dense Matter in Neutron Stars with eXTP
• Towards constraining QCD phase transitions in neutron star interiors: Bayesian Inference with TOV linear response analysis
• Ultra fast, event-by-event heavy-ion simulations for next generation experiments
• Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
• Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks
• Diffusion Model-based Parameter Estimation in Dynamic Power Systems
• The noiseless limit and improved-prior limit of the maximum entropy method and their implications for the analytic continuation problem
• Nevanlinna-Pick interpolation from uncertain data
• Optimal Observables for the Chiral Magnetic Effect from Machine Learning
• Extraction of the color dipole amplitude with physics-informed neural networks