Pure density functional for strong correlations and the thermodynamic limit from machine learning

Abstract

We use density-matrix renormalization group, applied to a one-dimensional model of continuum Hamiltonians, to accurately solve chains of hydrogen atoms of various separations and numbers of atoms. We train and test a machine-learned approximation to $F[n]$, the universal part of the electronic density functional, to within quantum chemical accuracy. Our calculation (a) bypasses the standard Kohn-Sham approach, avoiding the need to find orbitals, (b) includes the strong correlation of highly-stretched bonds without any specific difficulty (unlike all standard DFT approximations) and (c) is so accurate that it can be used to find the energy in the thermodynamic limit to quantum chemical accuracy.

arXiv comment10 figures, 9 pages

References in corpus (16)

• The density-matrix renormalization group in the age of matrix product states
• The density-matrix renormalization group
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Localization and delocalization errors in density functional theory and implications for band-gap prediction
• Finding Density Functionals with Machine Learning
• Ab Initio Quantum Chemistry using the Density Matrix Renormalization Group
• Understanding and reducing errors in density functional calculations
• DFT: A Theory Full of Holes?
• Orbital-free Bond Breaking via Machine Learning
• Infinite size density matrix renormalization group, revisited
• One-dimensional Continuum Electronic Structure with the Density Matrix Renormalization Group and Its Implications For Density Functional Theory
• Reference electronic structure calculations in one dimension
• Density functional theory in one-dimension for contact-interacting fermions
• Kohn-Sham calculations with the exact functional
• Guaranteed convergence of the Kohn-Sham equations
• One Dimensional Mimicking of Electronic Structure: The Case for Exponentials

Cited by in corpus (52)

• By-passing the Kohn-Sham equations with machine learning
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Quantum Machine Learning for Chemistry and Physics
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Probing many-body localization with neural networks
• Kernel methods for interpretable machine learning of order parameters
• Deep Learning and Density Functional Theory
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Machine learning of phase transitions in the percolation and XY models
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability
• A review on non-relativistic fully numerical electronic structure calculations on atoms and diatomic molecules
• Analytic continuation via domain-knowledge free machine learning
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Kinetic energy densities based on the fourth order gradient expansion: performance in different classes of materials and improvement via machine learning
• Deep learning the Hohenberg-Kohn maps of Density Functional Theory
• Convolutional neural networks for atomistic systems
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Data-driven kinetic energy density fitting for orbital-free DFT: linear vs Gaussian process regression
• Evolving symbolic density functionals
• Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
• Machine Learning Exchange-Correlation Potential in Time Dependent Density Functional Theory
• Phase Diagrams of Three-Dimensional Anderson and Quantum Percolation Models using Deep Three-Dimensional Convolutional Neural Network
• Machine learning electron correlation in a disordered medium
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture
• Exact constraints and appropriate norms in machine learned exchange-correlation functionals
• Efficient Learning of a One-dimensional Density Functional Theory
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Extracting many-particle entanglement entropy from observables using supervised machine learning
• Bypassing the computational bottleneck of quantum-embedding theories for strong electron correlations with machine learning
• Density functionals and Kohn-Sham potentials with minimal wavefunction preparations on a quantum computer
• The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
• Neural networks in quantum many-body physics: a hands-on tutorial
• Efficient prediction of 3D electron densities using machine learning
• Conditional probability density functional theory
• Chemical accuracy from small, system-adapted basis functions
• Insights into one-body density matrices using deep learning
• Deep learning density functionals for gradient descent optimization
• Deep learning nonlocal and scalable energy functionals for quantum Ising models
• Linear convergence in optimization over directed graphs with row-stochastic matrices
• Improving Malware Detection Accuracy by Extracting Icon Information
• The Levy-Lieb embedding of density functional theory and its Quantum Kernel: Illustration for the Hubbard Dimer using near-term quantum algorithms
• Learning DFT
• Predicting fermionic densities using a Projected Quantum Kernel method
• Machine-learning semi-local density functional theory for many-body lattice models at zero and finite temperature
• Gaussian Processes for Finite Size Extrapolation of Many-Body Simulations
• Solving deep-learning density functional theory via variational autoencoders
• Build your own tensor network library: DMRjulia I. Basic library for the density matrix renormalization group
• A Finite Element Configuration Interaction Method for Wigner Localization
• Charge Transfer in Classical Molecular Dynamics Simulations of Met-enkephalin: Improving Traditional Force Field with Data Driven Models