Pith. sign in

REVIEW 9 cited by

Lattice gauge equivariant convolutional neural networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.12901 v2 pith:UQ3632TE submitted 2020-12-23 hep-lat cs.LGhep-phhep-thstat.ML

classification hep-latcs.LGhep-phhep-thstat.ML
keywords gaugeconvolutionallatticenetworksneuralequivariantl-cnnsloops
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We propose Lattice gauge equivariant Convolutional Neural Networks (L-CNNs) for generic machine learning applications on lattice gauge theoretical problems. At the heart of this network structure is a novel convolutional layer that preserves gauge equivariance while forming arbitrarily shaped Wilson loops in successive bilinear layers. Together with topological information, for example from Polyakov loops, such a network can in principle approximate any gauge covariant function on the lattice. We demonstrate that L-CNNs can learn and generalize gauge invariant quantities that traditional convolutional neural networks are incapable of finding.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Extended framework for the hybrid Monte Carlo in lattice gauge theory

    hep-lat 2024-12 conditional novelty 7.0 of 10

    An exact hybrid Monte Carlo framework is built by embedding SU(N) into complex matrix space, enabling non-separable Hamiltonians like Riemannian manifold HMC in lattice gauge theory without gauge fixing.

  2. Higher-order hopping-parameter expansion by human-AI collaboration

    hep-lat 2026-06 conditional novelty 6.5 of 10

    Trie-structured algorithms compute κ^8 to κ^12 terms in the hopping expansion of Tr ln M at costs scaling from 20x to 8900x a staple, verified by direct comparison to a reference calculation.

  3. Progress in Normalizing Flows for 4d Gauge Theories

    hep-lat 2025-02 conditional novelty 6.0 of 10

    Learned active loops improve spectral flow models, and correlated flow ensembles reduce statistical errors by 2-3x in Nf=2 QCD for the pion gluon momentum fraction, with a computational advantage after roughly 4,000 c...

  4. Diffusion Models for SU(2) Lattice Gauge Theory in Two Dimensions

    hep-lat 2026-02 conditional novelty 5.0 of 10

    A flat-space quaternion diffusion model, trained at β=2.0 on an 8×8 lattice, reproduces the exact SU(2) plaquette to |Δ|≤0.001 near the training coupling and within 0.06 over β∈[1,4].

  5. AI for Pattern Hunter: Application in Wilson Loop of 2D Lattice Yang-Mills Theory

    hep-th 2025-10 conditional novelty 5.0 of 10

    A Transformer predicts the analytic expectation values of 2D lattice Yang-Mills Wilson loops from tokenized loop shapes with over 99% accuracy for loops up to length 16, but does not extrapolate to longer loops.

  6. HMC and gradient flow with machine-learned classically perfect fixed-point actions

    hep-lat 2025-02 conditional novelty 5.0 of 10

    A machine-learned fixed-point action for 4D SU(3) gauge theory is simulated with HMC and shows greatly reduced lattice artifacts in gradient-flow scale setting.

  7. Symmetry-preserving neural networks in lattice field theories

    hep-lat 2025-06 conditional novelty 4.0 of 10

    Translation- and gauge-equivariant neural networks (L-CNNs) predict Wilson loops, topological charge, and flux observables with orders-of-magnitude lower error than symmetry-breaking baselines, and neural gradient flo...

  8. Diffusion models and stochastic quantisation in lattice field theory

    hep-lat 2024-12 unverdicted novelty 2.0 of 10

    Diffusion models, whose backward denoising step resembles stochastic quantisation, can learn from HMC data to generate configurations for 2D scalar lattice field theory.

  9. Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics

    hep-lat 2025-01 unverdicted novelty 1.0 of 10

    A perspective article reviewing physics-driven machine learning for inverse problems in QCD, without introducing new data, derivations, or quantitative results.

Pith tools