A novel gauge-equivariant neural network architecture for preconditioners in lattice QCD

Simon Pfahler1, Daniel Knüttel1, Christoph Lehner1, Tilo Wettig1

1 Department of Physics, University of Regensburg

Correspondence: simon.pfahler@ur.de

Slides

Paper

The proceedings article explaining everything in more detail is available here:
https://doi.org/10.48550/arXiv.2602.23840

Code availability

Code to reproduce the results presented in the talk is available in this GitHub repository, which relies heavily on the python package qcd_ml.

Funding

This work is supported by the German Academic Scholarship Foundation (Studienstiftung des deutschen Volkes).