Machine Learning Green's Functions of Strongly Correlated Hubbard Models

2025/11/10 by Wuttig, Mateo Cárdenes
Physics and Astronomy · Materials Science · #Quantum many-body systems #Machine Learning in Materials Science #Physics of Superconductivity and Magnetism

paper · doi:10.48550/arxiv.2511.07252

Abstract

We demonstrate that a machine learning framework based on kernel ridge regression can encode and predict the self-energy of one-dimensional Hubbard models using only mean-field features such as static and dynamic Hartree-Fock quantities and first-order GW calculations. This approach is applicable across a wide range of on-site Coulomb interaction strengths U/t, ranging from weakly interacting systems (U/t ≪ 1) to strong correlations (U/t > 8). The predicted self-energy is transformed via Dyson's equation and analytic continuation to obtain the real-frequency Green's function, which allows access to the spectral function and density of states. This method can be used for nearest-neighbor interactions t and long-range hopping terms t', t'', and t'''.

Citations

• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• Predicting nonequilibrium Green's function dynamics and photoemission spectra via nonlinear integral operator learning
• From Architectures to Applications: A Review of Neural Quantum States
• Machine Learning Many-Body Green's Functions for Molecular Excitation Spectra
• Applicability and limitations of cluster perturbation theory for Hubbard models
• NNQS-Transformer: an Efficient and Scalable Neural Network Quantum States Approach for Ab initio Quantum Chemistry
• Recent developments in the PySCF program package
• The Python-based Simulations of Chemistry Framework (PySCF)
• Understanding Kernel Ridge Regression: Common behaviors from simple\n functions to density functionals
• Limitations of the hybrid functional approach to electronic structure of\n transition metal oxides
• The density-matrix renormalization group in the age of matrix product states
• Sign problem in the numerical simulation of many-electron systems
• New Method for Calculating the One-Particle Green's Function with Application to the Electron-Gas Problem

Related

• Machine Learning Many-Body Green's Functions for Molecular Excitation Spectra
• Improving Spectral Resolution from Real-time Evolution for Correlated Systems
• Machine learning for many-body physics: efficient solution of dynamical mean-field theory
• Machine-learning semi-local exchange-correlation functionals for Kohn-Sham density functional theory of the Hubbard model
• A Kernel-based Machine Learning Approach to Computing Quasiparticle\n Energies within Many-Body Green's Functions Theory