no code implementations • 20 Apr 2023 • Christoph Lehner, Tilo Wettig
We demonstrate that gauge-equivariant pooling and unpooling layers can perform as well as traditional restriction and prolongation layers in multigrid preconditioner models for lattice QCD.
no code implementations • 10 Feb 2023 • Christoph Lehner, Tilo Wettig
We demonstrate that a state-of-the art multi-grid preconditioner can be learned efficiently by gauge-equivariant neural networks.
no code implementations • 13 Nov 2017 • Peter Boyle, Michael Chuvelev, Guido Cossu, Christopher Kelly, Christoph Lehner, Lawrence Meadows
This displays how a factor of ten speedup in strongly scaled distributed machine learning could be achieved when synchronous stochastic gradient descent is massively parallelised with a fixed mini-batch size.