Garchinger Maier-Leibnitz-Kolloquium: Gauge-equivariant multigrid neural networks

by Prof. Tilo Wettig (Universität Regensburg)

Lecture Hall, ground floor (west) (LMU building, Am Coulombwall 1, campus Garching)

Lecture Hall, ground floor (west)

LMU building, Am Coulombwall 1, campus Garching


Lattice simulations are an important tool to compute nonperturbative results in quantum field theories such as QCD. The most time-consuming part in lattice calculations is the solution of the Dirac equation for a given SU(3) gauge field. In the interesting physical limits, critical slowing down occurs, which can be overcome by state-of-the-art multigrid methods. We introduce gauge-equivariant neural networks that can learn the general paradigms of a multigrid. These networks can perform equally well as standard multigrids but are more general and therefore have the potential to address a larger range of research questions.

Hybrid access via ZOOM:
Meeting ID: 984 5733 2925
Passcode: 979953

Organized by

Peter Thirolf (LMU) / Norbert Kaiser (TUM)