From Theory to Practice: Applying Neural Networks to Simulate Real Systems with Sign Problems

2023/11/30 by Rodekamp, Marcel, Berkowitz, Evan, Dincă, Maria +3
#FOS: Physical sciences #High Energy Physics - Lattice (hep-lat) #Strongly Correlated Electrons (cond-mat.str-el)

paper · doi:10.48550/arxiv.2311.18312

Abstract

The numerical sign problem poses a seemingly insurmountable barrier to the simulation of many fascinating systems. We apply neural networks to deform the region of integration, mitigating the sign problem of systems with strongly correlated electrons. In this talk we present our latest architectural developments as applied to contour deformation. We also demonstrate its applicability to real systems, namely perylene.

Related

• Mitigating the Hubbard Sign Problem. A Novel Application of Machine Learning
• Exploring Group Convolutional Networks for Sign Problem Mitigation via Contour Deformation
• Neural Network Enhanced Polyconvexification of Isotropic Energy Densities in Computational Mechanics
• Neural Network Ground State from the Neural Tangent Kernel Perspective: The Sign Bias
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models