Fetching the paper…

Reading the bibliography…

2023

Gauge-equivariant neural networks as preconditioners in lattice QCD

Lehner, Christoph, Wettig, Tilo

Original
PDF
Post on X

Understand

We demonstrate that a state-of-the art multi-grid preconditioner can be learned efficiently by gauge-equivariant neural networks.

We show that the models require minimal re-training on different gauge configurations of the same gauge ensemble and to a large extent remain efficient under modest modifications of ensemble parameters.
We also demonstrate that important paradigms such as communication avoidance are straightforward to implement in this framework.

Gauge-equivariant neural networks as preconditioners in lattice QCD · Around

Built on

J. He and J. Xu, MgNet: A unified framework of multigrid and convolutional neural network, Sci. China Math. 62
Original
1901
Earlier work this paper cites.
D. Greenfeld, M. Galun, R. Basri, I. Yavneh, and R. Kimmel, Learning to Optimize Multigrid PDE Solvers, in Proceedings of the 36th International Conference on Machine Learning (2019) pp. 2415–2423, arXiv:1902.10248 [math.NA]
Original
1902
Earlier work this paper cites.
T. S. Cohen, M. Weiler, B. Kicanaoglu, and M. Welling, Gauge Equivariant Convolutional Networks and the Icosahedral CNN, in Proceedings of the 36th International Conference on Machine Learning (2019) pp. 1321–1330, arXiv:1902.04615 [cs.LG]
Original
1902
Earlier work this paper cites.
K. G. Wilson, Confinement of Quarks, Phys. Rev. D 10
1974
Earlier work this paper cites.
B. Sheikholeslami and R. Wohlert, Improved continuum limit lattice action for QCD with Wilson fermions, Nucl. Phys. B 259
1985
Earlier work this paper cites.
Y. Saad, A Flexible Inner-Outer Preconditioned GMRES Algorithm, SIAM J. Sci. Comput. 14
1993
Earlier work this paper cites.
Y. Shamir, Chiral fermions from lattice boundaries, Nucl. Phys. B 406
1993
Earlier work this paper cites.
V. Furman and Y. Shamir, Axial symmetries in lattice QCD with Kaplan fermions, Nucl. Phys. B 439
1995
Earlier work this paper cites.
U. Trottenberg, C. Oosterlee, and A. Schuller, Multigrid (Elsevier Science, 2000)
2000
Earlier work this paper cites.
I. Luz, M. Galun, H. Maron, R. Basri, and I. Yavneh, Learning algebraic multigrid using graph neural networks, in Proceedings of the 37th International Conference on Machine Learning (2020) pp. 6489–6499, arXiv:2003.05744 [cs.LG]
Original
2003
Earlier work this paper cites.
G. Kanwar, M. S. Albergo, D. Boyda, K. Cranmer, D. C. Hackett, S. Racanière, D. J. Rezende, and P. E. Shanahan, Equivariant flow-based sampling for lattice gauge theory, Phys. Rev. Lett. 125
Original
2003
Earlier work this paper cites.

Similar

R. C. Brower, M. A. Clark, D. Howarth, E. S. Weinberg, Multigrid for chiral lattice fermions: Domain wall, Phys. Rev. D 102
Original
2004
Cited alongside, same era.
M. Lüscher, Solution of the Dirac equation in lattice QCD using a domain decomposition method, Comput. Phys. Commun. 156
2004
Cited alongside, same era.
J. Brannick, R. C. Brower, M. A. Clark, J. C. Osborn, and C. Rebbi, Adaptive Multigrid Algorithm for Lattice QCD, Phys. Rev. Lett. 100
Original
2008
Cited alongside, same era.
D. Boyda, G. Kanwar, S. Racanière, D. J. Rezende, M. S. Albergo, K. Cranmer, D. C. Hackett, and P. E. Shanahan, Sampling using S U ( N ) SU(N) gauge equivariant flows, Phys. Rev. D 103
Original
2008
Cited alongside, same era.
R. Babich, J. Brannick, R. C. Brower, M. A. Clark, T. A. Manteuffel, S. F. McCormick, J. C. Osborn, and C. Rebbi, Adaptive multigrid algorithm for the lattice Wilson-Dirac operator, Phys. Rev. Lett. 105

Then

J. Brannick, A. Frommer, K. Kahl, B. Leder, M. Rottmann, and A. Strebel, Multigrid Preconditioning for the Overlap Operator in Lattice QCD, Numer. Math. 132
Original
2016
Later among the works it cites.
T. Cohen and M. Welling, Group Equivariant Convolutional Networks, in Proceedings of The 33rd International Conference on Machine Learning (2016) pp. 2990–2999, arXiv:1602.07576 [cs.LG]
Original
2016
Later among the works it cites.
A. Katrutsa, T. Daulbaev, and I. Oseledets, Deep Multigrid: learning prolongation and restriction matrices (2017), arXiv:1711.03825 [math.NA]
Original
2017
Later among the works it cites.
R. C. Brower, M. A. Clark, A. Strelchenko, and E. Weinberg, Multigrid algorithm for staggered lattice fermions, Phys. Rev. D 97
Original
2018
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Original

2010

Cited alongside, same era.

Y. Osaki and K.-I. Ishikawa, Domain Decomposition method on GPU cluster, PoS LATTICE2010

2010

Cited alongside, same era.

M. Eliasof, J. Ephrath, L. Ruthotto, and E. Treister, MGIC: Multigrid-in-Channels Neural Network Architectures (2020), arXiv:2011.09128 [cs.CV]

2011

Cited alongside, same era.

R. Babich, M. A. Clark, B. Joo, G. Shi, R. C. Brower, and S. Gottlieb, Scaling Lattice QCD beyond 100 GPUs, in SC11 International Conference for High Performance Computing, Networking, Storage and Analysis (2011) arXiv:1109.2935 [hep-lat]

2011

Cited alongside, same era.

M. Favoni, A. Ipp, D. I. Müller, and D. Schuh, Lattice Gauge Equivariant Convolutional Neural Networks, Phys. Rev. Lett. 128

2012

Cited alongside, same era.

A. Frommer, K. Kahl, S. Krieg, B. Leder, and M. Rottmann, Adaptive Aggregation Based Domain Decomposition Multigrid for the Lattice Wilson Dirac Operator, SIAM J. Sci. Comput. 36

2014

Cited alongside, same era.

D. P. Kingma and J. Ba, Adam: A method for stochastic optimization (2014), arXiv:1412.6980 [cs.LG]

2014

Cited alongside, same era.

C. Lehner et al., Grid Python Toolkit (GPT)

Cited in the paper.

P. Boyle and A. Yamaguchi, Comparison of Domain Wall Fermion Multigrid Methods (2021), arXiv:2103.05034 [hep-lat]

2021

Later among the works it cites.

R. Huang, R. Li, and Y. Xi, Learning optimal multigrid smoothers via neural networks, SIAM J. Sci. Comput. , S199 (2021) , arXiv:2102.12071 [math.NA]

2021

Later among the works it cites.

J. Tu, M. A. Clark, C. Jung, and R. Mawhinney, Solving DWF Dirac Equation Using Multi-splitting Preconditioned Conjugate Gradient with Tensor Cores on NVIDIA GPUs, in PASC ’21: Proceedings of the Platform for Advanced Scientific Computing Conference (2021) pp. 1–11, arXiv:2104.05615 [hep-lat]

2021

Later among the works it cites.

A. S. Kronfeld et al. (USQCD), Lattice QCD and Particle Physics (2022), arXiv:2207.07641 [hep-lat]

2022

Later among the works it cites.

P. Boyle et al. , Lattice QCD and the Computational Frontier (2022), arXiv:2204.00039 [hep-lat]

2022

Later among the works it cites.

A. van Betteray, M. Rottmann, and K. Kahl, MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions (2022), arXiv:2211.05525 [cs.CV]

2022

Later among the works it cites.

R. Abbott et al. , Gauge-equivariant flow models for sampling in lattice field theories with pseudofermions, Phys. Rev. D 106

2022

Later among the works it cites.