LeapfrogLayers: A Trainable Framework for Effective Topological Sampling
This addresses a domain-specific challenge in computational physics for researchers working on lattice gauge theories, with incremental improvements over existing methods.
The paper tackled the problem of efficiently sampling the topology of a 2D U(1) lattice gauge theory by introducing LeapfrogLayers, an invertible neural network architecture, and showed an improvement in the integrated autocorrelation time of the topological charge compared to traditional HMC.
We introduce LeapfrogLayers, an invertible neural network architecture that can be trained to efficiently sample the topology of a 2D $U(1)$ lattice gauge theory. We show an improvement in the integrated autocorrelation time of the topological charge when compared with traditional HMC, and look at how different quantities transform under our model. Our implementation is open source, and is publicly available on github at https://github.com/saforem2/l2hmc-qcd.