Machine learning phase transitions of the three-dimensional Ising universality class
arXiv:2112.13987 · doi:10.1088/1674-1137/aca5f5
Abstract
Exploration of the QCD phase diagram and critical point is one of the main goals in current relativistic heavy-ion collisions. The QCD critical point is expected to belong to a three-dimensional (3D) Ising universality class. Machine learning techniques are found to be powerful in distinguishing different phases of matter and provide a new way to study the phase diagram. We investigate phase transitions in the 3D cubic Ising model using supervised learning methods. It is found that a 3D convolutional neural network can be trained to effectivelly predict physical quantities in different spin configurations. With a uniform neural network architecture, it can encode phases of matter and identify both second- and first-order phase transitions. The important features that discriminate different phases in the classification processes are investigated. These findings can help study and understand QCD phase transitions in relativistic heavy-ion collisions.
arXiv comment8 pages, 7 figures, published version
References in corpus (66)
- Fault-tolerant quantum computation by anyons
- Experimental and Theoretical Challenges in the Search for the Quark Gluon Plasma: The STAR Collaboration's Critical Assessment of the Evidence from RHIC Collisions
- Machine learning and the physical sciences
- The order of the quantum chromodynamics transition predicted by the standard model of particle physics
- Critical Phenomena and Renormalization-Group Theory
- Machine learning phases of matter
- Signatures of the Tricritical Point in QCD
- A high-bias, low-variance introduction to Machine Learning for physicists
- The QCD transition temperature: results with physical masses in the continuum limit
- Critical point of QCD at finite T and μ, lattice results for physical quark masses
- Learning phase transitions by confusion
- Non-Gaussian fluctuations near the QCD critical point
- Discovering Phase Transitions with Unsupervised Learning
- On the Phase Diagram of QCD
- Color Superconductivity and Chiral Symmetry Restoration at Nonzero Baryon Density and Temperature
- Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
- Energy Dependence of Moments of Net-proton Multiplicity Distributions at RHIC
- Mapping the Phases of Quantum Chromodynamics with Beam Energy Scan
- On the sign of kurtosis near the QCD critical point
- Search for the QCD Critical Point with Fluctuations of Conserved Quantities in Relativistic Heavy-Ion Collisions at RHIC : An Overview
- Fluctuation Probes of Quark Deconfinement
- Machine learning quantum phases of matter beyond the fermion sign problem
- Higher Moments of Net-proton Multiplicity Distributions at RHIC
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Beam energy dependence of moments of the net-charge multiplicity distributions in Au+Au collisions at RHIC
- Scale for the Phase Diagram of Quantum Chromodynamics
- Baryon-strangeness correlations: a diagnostic of strongly interacting matter
- QCD at finite chemical potential with six time slices
- Learning Thermodynamics with Boltzmann Machines
- Non-monotonic energy dependence of net-proton number fluctuations
- The Magnetization of the 3D Ising Model
- Critical Points in the Linear Sigma Model with Quarks
- Detection of phase transition via convolutional neural network
- Cumulants and Correlation Functions of Net-proton, Proton and Antiproton Multiplicity Distributions in Au+Au Collisions at energies available at the BNL Relativistic Heavy Ion Collider
- Kernel methods for interpretable machine learning of order parameters
- QCD critical region and higher moments for three flavor models
- The Chiral Critical Point in 3-Flavour QCD
- Collision Energy Dependence of Moments of Net-Kaon Multiplicity Distributions at RHIC
- Critical exponents of the 3d Ising and related models from Conformal Bootstrap
- Unveiling phase transitions with machine learning
- QCD and the Chiral Critical Point
- Measurement of higher cumulants of net-charge multiplicity distributions in AuAu collisions at GeV
- Parameter diagnostics of phases and phase transition learning by neural networks
- Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
- Smallest Neural Network to Learn the Ising Criticality
- A machine learning study to identify spinodal clumping in high energy nuclear collisions
- Nuclear liquid-gas phase transition with machine learning
- Machine Learning as a universal tool for quantitative investigations of phase transition
- Thermodynamics and Feature Extraction by Machine Learning
- The critical temperature of the 2D-Ising model through Deep Learning Autoencoders
- Mapping distinct phase transitions to a neural network
- Quartic cumulant of baryon number in the presence of QCD critical point
- Universality of the critical point mapping between Ising model and QCD at small quark mass
- Extracting Critical Exponent by Finite-Size Scaling with Convolutional Neural Networks
- Variational autoencoder reconstruction of complex many-body physics
- Finite-size scaling around the critical point in the heavy quark region of QCD
- Few-shot machine learning in the three-dimensional Ising model
- Phase transition encoded in neural network
- An equation-of-state-meter for CBM using PointNet
- Generalization capabilities of translationally equivariant neural networks
- Machine learning generated configurations in presence of a conserved quantity: a cautionary tale
- Classification of Equation of State in Relativistic Heavy-Ion Collisions Using Deep Learning
- Overview of intermittency analysis in heavy-ion collisions
- The Chiral Critical Point in 3-Flavour QCD
- Equation of state for QCD with a critical point from the 3D Ising Model
- Measurement of Intermittency for Charged Particles in Au + Au Collisions at = 7.7-200 GeV from STAR