This title appears in the Scientific Report :
2023
Please use the identifier:
http://dx.doi.org/10.34734/FZJ-2023-05418 in citations.
From Theory to Practice: Applying Neural Networks to Simulate Real Systems with Sign Problems
From Theory to Practice: Applying Neural Networks to Simulate Real Systems with Sign Problems
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...
Saved in:
Personal Name(s): | Rodekamp, Marcel (Corresponding author) |
---|---|
Berkowitz, Evan / Dincă, Maria / Gäntgen, Christoph / Krieg, Stefan / Luu, Tom | |
Contributing Institute: |
Theorie der Starken Wechselwirkung; IAS-4 Center for Advanced Simulation and Analytics; CASA Jülich Supercomputing Center; JSC Institut 3 (Theoretische Kernphysik); IKP-3 |
Published in: | Proceedings of Science / International School for Advanced Studies, 453 (2023) |
Imprint: |
Trieste
SISSA
2023
|
Physical Description: |
XXX |
DOI: |
10.34734/FZJ-2023-05418 |
Conference: | The 40th International Symposium on Lattice Field Theory, Batavia, Illinois (USA), 2023-07-31 - 2023-08-04 |
Document Type: |
Contribution to a conference proceedings Journal Article |
Research Program: |
Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups |
Link: |
Get full text OpenAccess |
Publikationsportal JuSER |
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. |