| Issue |
EPJ Web Conf.
Volume 258, 2022
A Virtual Tribute to Quark Confinement and the Hadron Spectrum (vConf21)
|
|
|---|---|---|
| Article Number | 09004 | |
| Number of page(s) | 8 | |
| Section | Parallel Presentations Track H | |
| DOI | https://doi.org/10.1051/epjconf/202225809004 | |
| Published online | 11 January 2022 | |
https://doi.org/10.1051/epjconf/202225809004
Preserving gauge invariance in neural networks
1 Institute for Theoretical Physics, TU Wien, Wiedner Hauptstr. 8-10, 1040 Vienna, Austria
2 Speaker and corresponding author
* e-mail: favoni@hep.itp.tuwien.ac.at
** e-mail: ipp@hep.itp.tuwien.ac.at
*** e-mail: dmueller@hep.itp.tuwien.ac.at
**** e-mail: schuh@hep.itp.tuwien.ac.at
Published online: 11 January 2022
In these proceedings we present lattice gauge equivariant convolutional neural networks (L-CNNs) which are able to process data from lattice gauge theory simulations while exactly preserving gauge symmetry. We review aspects of the architecture and show how L-CNNs can represent a large class of gauge invariant and equivariant functions on the lattice. We compare the performance of L-CNNs and non-equivariant networks using a non-linear regression problem and demonstrate how gauge invariance is broken for non-equivariant models.
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.