We discuss the prediction of critical behavior of lattice observables in SU(2) and SU(3) gauge theories. We show that feed-forward neural network, trained on the lattice configurations of gauge fields as input data, finds correlations with the target observable, which is also true in the critical region where the neural network has not been trained. We have verified that the neural network constructs a gauge-invariant function and this property does not change over the entire range of the parameter space.
@article{arxiv.2112.07865,
title = {Applying machine learning methods to prediction problems of lattice observables},
author = {N. V. Gerasimeniuk and M. N. Chernodub and V. A. Goy and D. L. Boyda and S. D. Liubimov and A. V. Molochkov},
journal= {arXiv preprint arXiv:2112.07865},
year = {2022}
}
Comments
7 pages, 2 figures, 1 table, contribution to the proceedings of XXXIII International (ONLINE) Workshop on High Energy Physics "Hard Problems of Hadron Physics: Non-Perturbative QCD & Related Quests" November 8-12, 2021, Submission to SciPost