Physics-informed neural networks for solving functional renormalization group on a lattice

Abstract

Addressing high-dimensional partial differential equations to derive effective actions within the functional renormalization group is formidable, especially when considering various field configurations, including inhomogeneous states, even on lattices. We leverage physics-informed neural networks (PINNs) as a state-of-the-art machine learning method for solving high-dimensional partial differential equations to overcome this challenge. In a zero-dimensional O($N$) model, we numerically demonstrate the construction of an effective action on an $N$-dimensional configuration space, extending up to $N=100$. Our results underscore the effectiveness of PINN approximation, even in scenarios lacking small parameters such as a small coupling.

11 pages, 5 figures, 4 tables, v3: paper style changed, Tables III & IV added, Appendix A added

References in corpus (30)

• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Exact evolution equation for the effective potential
• Solving high-dimensional partial differential equations using deep learning
• Non-Perturbative Renormalization Flow in Quantum Field Theory and Statistical Physics
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Functional renormalization group approach to correlated fermion systems
• The nonperturbative functional renormalization group and its applications
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Introduction to the functional RG and applications to gauge theories
• Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
• The Hubbard Dimer: A density functional case study of a many-body problem
• A Deep Neural Network Surrogate for High-Dimensional Random Partial Differential Equations
• Effective action and density functional theory
• Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks
• Functional Renormalization Group and Kohn-Sham scheme in Density Functional Theory
• Two-particle irreducible functional renormalization group schemes---a comparative study
• Towards a Renormalization Group Approach to Density Functional Theory - General Formalism and Case Studies -
• Deep Learning the Functional Renormalization Group
• Formation of Selfbound States in a One-Dimensional Nuclear Model -- A Renormalization Group based Density Functional Study
• Functional renormalization-group calculation of the equation of state of one-dimensional nuclear matter inspired by the Hohenberg--Kohn theorem
• Self-Consistent Large-$N$ Analytical Solutions of Inhomogneous Condensates in Quantum $\mathbb{C}{P}^{N-1}$ Model
• Non-perturbative renormalization-group approach to lattice models
• Ab-initio description of excited states of a one-dimensional nuclear matter with the Hohenberg-Kohn-theorem-inspired functional-renormalization-group method
• The zero-dimensional O(N) vector model as a benchmark for perturbation theory, the large-N expansion and the functional renormalization group
• Ab initio construction of the energy density functional for electron systems with the functional-renormalization-group-aided density functional theory
• Functional-renormalization-group aided density-functional analysis for the correlation energy of the two-dimensional homogeneous electron gas
• Microscopic derivation of density functional theory for superfluid systems based on effective action formalism
• Functional-renormalization-group approach to classical liquids with short-range repulsion: a scheme without repulsive reference system
• Construction of energy density functional for arbitrary spin polarization using functional renormalization group

Cited by in corpus (1)

• Unraveling particle dark matter with Physics-Informed Neural Networks