Equivariant flow-based sampling for lattice gauge theory
read the original abstract
We define a class of machine-learned flow-based sampling algorithms for lattice gauge theories that are gauge-invariant by construction. We demonstrate the application of this framework to U(1) gauge theory in two spacetime dimensions, and find that near critical points in parameter space the approach is orders of magnitude more efficient at sampling topological quantities than more traditional sampling procedures such as Hybrid Monte Carlo and Heat Bath.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Scalable Generative Sampling and Multilevel Estimation for Lattice Field Theories Near Criticality
A hierarchical generative model for critical lattice scalar field theories achieves orders-of-magnitude lower autocorrelation times than HMC while enabling exact multilevel Monte Carlo.
-
Probing Proton Structure via Physics-Guided Neural Networks in Holographic QCD
A physics-guided neural network embedding AdS5 Dirac equation and holographic Pomeron fits SLAC proton F2 data with chi-squared per degree of freedom of 0.91 and identifies a kinematic crossover at x approximately 0.1...
-
Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection
Continuous normalizing flows exhibit the likelihood paradox on OOD speech data but geometric signals from sub-flow velocity fields enable superior zero-shot phoneme-level mispronunciation detection over likelihood baselines.
-
Diffusion model for SU(N) gauge theories
Implicit score matching trains diffusion models that successfully sample SU(3) Wilson gauge configurations on lattices, with a Hamiltonian-dynamics corrector needed for strong coupling.
-
Scaling flow-based approaches for topology sampling in $\mathrm{SU}(3)$ gauge theory
Out-of-equilibrium simulations with open-to-periodic boundary switching plus a tailored stochastic normalizing flow enable efficient topology sampling in the continuum limit of four-dimensional SU(3) Yang-Mills theory.
-
Improvement of Heatbath Algorithm in LFT using Generative models
Generative models learn conditional local distributions conditioned on neighbors and action parameters to improve Heatbath proposals for continuous-variable lattice models without target samples.
-
Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection
Lagrangian sub-flows and velocity-based geometric diagnostics in CNFs outperform likelihood for zero-shot phoneme mispronunciation detection in speech models.
-
Machine learning for four-dimensional SU(3) lattice gauge theories
Machine learning generative models and renormalization-group neural networks are used to enhance gauge field sampling and learn fixed-point actions in 4D SU(3) lattice gauge theories, with presented scaling results to...
-
FLAG Review 2024
The FLAG 2024 review provides updated averages of lattice QCD determinations for quark masses, decay constants, form factors, mixing parameters, and nucleon matrix elements.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.