26 July 2026 to 1 August 2026
University of Maryland, College Park
US/Eastern timezone

Learning Low Modes of the Wilson Dirac Operator with Gauge-Equivariant Networks

29 Jul 2026, 11:50
20m
Benjamin Banneker B (Adele H. Stamp Student Union)

Benjamin Banneker B

Adele H. Stamp Student Union

3972 Campus Dr, College Park, MD 20742
Contributed talk Algorithms and artificial intelligence Algorithms and artificial intelligence

Speaker

choi minjae

Description

The low-lying modes of the Wilson Dirac operator are key ingredients in deflation and multigrid algorithms for lattice QCD, where they define the near-null spaces responsible for critical slowing down. In this talk, we present a method for learning such low modes with a gauge-equivariant neural network trained on an ensemble of gauge configurations, using a Rayleigh–Ritz loss that minimizes the sum of the lowest Rayleigh quotients of $D^\dagger D$. Because the network is trained across the ensemble rather than per configuration, its setup cost can be amortized over many solves. We report the generalization of the learned modes to held-out configurations on small lattices, and demonstrate their effectiveness as test vectors in the DD-$\alpha$AMG multigrid solver.

Author

Co-author

Dr Hiroshi Ohno (Center for Computational Sciences, University of Tsukuba)

Presentation materials