Machine-learning physics from unphysics: Finding deconfinement temperature in lattice Yang-Mills theories from outside the scaling window

Abstract

We study the machine learning techniques applied to the lattice gauge theory's critical behavior, particularly to the confinement/deconfinement phase transition in the SU(2) and SU(3) gauge theories. We find that the neural network, trained on lattice configurations of gauge fields at an unphysical value of the lattice parameters as an input, builds up a gauge-invariant function, and finds correlations with the target observable that is valid in the physical region of the parameter space. In particular, if the algorithm aimed to predict the Polyakov loop as the deconfining order parameter, it builds a trace of the gauge group matrices along a closed loop in the time direction. As a result, the neural network, trained at one unphysical value of the lattice coupling $\beta$ predicts the order parameter in the whole region of the $\beta$ values with good precision. We thus demonstrate that the machine learning techniques may be used as a numerical analog of the analytical continuation from easily accessible but physically uninteresting regions of the coupling space to the interesting but potentially not accessible regions.

arXiv comment9 pages, 14 figures; v2: discussions added

References in corpus (22)

• Machine learning and the physical sciences
• Thermodynamics of SU(3) Lattice Gauge Theory
• A high-bias, low-variance introduction to Machine Learning for physicists
• Learning phase transitions by confusion
• Mapping the Phases of Quantum Chromodynamics with Beam Energy Scan
• Machine learning quantum phases of matter beyond the fermion sign problem
• Scaling and Asymptotic Scaling in the SU(2) Gauge Theory
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Equivariant flow-based sampling for lattice gauge theory
• Detection of phase transition via convolutional neural network
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Sampling using $SU(N)$ gauge equivariant flows
• Regressive and generative neural networks for scalar field theory
• Machine learning action parameters in lattice quantum chromodynamics
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• High-Temperature QCD: theory overview
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Extending machine learning classification capabilities with histogram reweighting
• Machine Learning Estimators for Lattice QCD Observables
• On the generalizability of artificial neural networks in spin models
• Topological defects and confinement with machine learning: the case of monopoles in compact electrodynamics
• Classifying Topological Charge in SU(3) Yang-Mills Theory with Machine Learning

Cited by in corpus (19)

• Machine Learning in Nuclear Physics
• Phase Transitions in Particle Physics -- Results and Perspectives from Lattice Quantum Chromo-Dynamics
• Exploring QCD matter in extreme conditions with Machine Learning
• Lattice gauge equivariant convolutional neural networks
• Stochastic normalizing flows as non-equilibrium transformations
• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows
• Probing center vortices and deconfinement in $\mathrm{SU}(2)$ lattice gauge theory with persistent homology
• Homogeneous vector bundles and $G$-equivariant convolutional neural networks
• Adding machine learning within Hamiltonians: Renormalization group transformations, symmetry breaking and restoration
• On the generalizability of artificial neural networks in spin models
• Machine learning spectral functions in lattice QCD
• Decoding Quantum Field Theory with Machine Learning
• Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network
• Unsupervised Machine Learning of Quenched Gauge Symmetries: A Proof-of-Concept Demonstration
• Constructing and Machine Learning Calabi-Yau Five-folds
• Building imaginary-time thermal field theory with artificial neural networks
• Discovering quasiorder parameters in the Potts model: A bridge between machine learning and critical phenomena
• Preserving gauge invariance in neural networks