A novel gauge-equivariant neural-network architecture for preconditioners in lattice QCD
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908986413940736 |
|---|---|
| author | Pfahler, Simon Knüttel, Daniel Lehner, Christoph Wettig, Tilo |
| author_facet | Pfahler, Simon Knüttel, Daniel Lehner, Christoph Wettig, Tilo |
| contents | Lattice QCD simulations are computationally expensive, with the solution of the Dirac equation being the major computational bottleneck of many calculations. We introduce a novel gauge-equivariant neural-network architecture for preconditioning the Dirac equation in the regime where critical slowing down occurs. We study the behavior of this preconditioner as a function of topological charge and lattice volume and show that it mitigates critical slowing down. We also show that this preconditioner transfers to unseen gauge configurations without any retraining, therefore enabling applications not possible with competing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23840 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A novel gauge-equivariant neural-network architecture for preconditioners in lattice QCD Pfahler, Simon Knüttel, Daniel Lehner, Christoph Wettig, Tilo High Energy Physics - Lattice Lattice QCD simulations are computationally expensive, with the solution of the Dirac equation being the major computational bottleneck of many calculations. We introduce a novel gauge-equivariant neural-network architecture for preconditioning the Dirac equation in the regime where critical slowing down occurs. We study the behavior of this preconditioner as a function of topological charge and lattice volume and show that it mitigates critical slowing down. We also show that this preconditioner transfers to unseen gauge configurations without any retraining, therefore enabling applications not possible with competing methods. |
| title | A novel gauge-equivariant neural-network architecture for preconditioners in lattice QCD |
| topic | High Energy Physics - Lattice |
| url | https://arxiv.org/abs/2602.23840 |