Numerical Challenges in Lattice QCD 2022

Session

Machine Learning

Aug 16, 2022, 10:40 AM

Landhaus Nordhelle

Conveners

Machine Learning

• Michael Günther (University of Wuppertal)

Machine Learning

• Francesco Giacomo Knechtli (Bergische Universitaet Wuppertal (DE))

28. Machine learning for ensemble generation

Phiala Shanahan

8/16/22, 10:40 AM

I will discuss the use of machine learning methods to accelerate algorithms for gauge field generation, in particular via flow models.

29. Continuous Normalizing Flow for Lattice QCD based on Trivializing Maps

Simone Bacchio

8/16/22, 11:20 AM

In this presentation we will show the connection between Continuous Normalizing Flows (CNF) and Trivializing Maps by Luescher. Based on the latter, we will construct a CNF that can be trained to simulate lattice field theories. We discuss strategies to train the CNF for 2D and 4D SU(3) pure-gauge theories.

27. Tackling critical slowing down using global correction steps with equivariant flows within the 2D Schwinger model

Jacob Finkenrath

8/16/22, 2:30 PM

Discretisation of gauge theories are an elegant and successful way to solve them via supercomputers. To obtain results at the continuum, the discretised model is simulated via Monte Carlo simulations at fixed physics at different lattice spacings and then extrapolated to the continuum. In many cases the major systematic effect of the obtained result is given by the extrapolation error. To...

46. Gradient estimators for normalising flows

Prof. Piotr Białas (Jagiellonian University)

8/16/22, 3:10 PM

ecently a machine learning approach to Monte-Carlo simulations called Neural Markov Chain Monte-Carlo (NMCMC) is gaining traction. In its most popular form it uses neural networks to construct normalizing flows which are then trained to approximate the desired target distribution. The training is done using some form of gradient descent so gradient estimation is necessery. In my talk I will...