Solving Many-Electron Schrödinger Equation Using Deep Neural Networks

Abstract

We introduce a new family of trial wave-functions based on deep neural networks to solve the many-electron Schrödinger equation. The Pauli exclusion principle is dealt with explicitly to ensure that the trial wave-functions are physical. The optimal trial wave-function is obtained through variational Monte Carlo and the computational cost scales quadratically with the number of electrons. The algorithm does not make use of any prior knowledge such as atomic orbitals. Yet it is able to represent accurately the ground-states of the tested systems, including He, H2, Be, B, LiH, and a chain of 10 hydrogen atoms. This opens up new possibilities for solving large-scale many-electron Schrödinger equation.

References in corpus (7)

• A unified deep artificial neural network approach to partial differential equations in complex geometries
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• DeePCG: constructing coarse-grained models via deep neural networks
• Solving the Bose-Hubbard model with machine learning
• Reinforced dynamics for enhanced sampling in large atomic and molecular systems
• Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
• Method to solve quantum few-body problems with artificial neural networks

Cited by in corpus (91)

• Machine learning and the physical sciences
• Recent developments in the PySCF program package
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Machine learning for electronically excited states of molecules
• Fermionic neural-network states for ab-initio electronic structure
• Perspective on integrating machine learning into computational chemistry and materials science
• Data-Driven Deep Learning of Partial Differential Equations in Modal Space
• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• The Modern Mathematics of Deep Learning
• Ab-initio quantum chemistry with neural-network wavefunctions
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• An overview on deep learning-based approximation methods for partial differential equations
• Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
• On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton--Jacobi partial differential equations
• Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
• Ab initio calculation of real solids via neural network ansatz
• Towards the ground state of molecules via diffusion Monte Carlo on neural networks
• Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
• Learning nonlocal constitutive models with neural networks
• Machine Learning from a Continuous Viewpoint
• Atomic, molecular and optical physics applications of longitudinally coherent and narrow bandwidth Free-Electron Lasers
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Neural Networks Enforcing Physical Symmetries in Nonlinear Dynamical Lattices: The Case Example of the Ablowitz-Ladik Model
• Integrating Machine Learning with Physics-Based Modeling
• DeepQMC: an open-source software suite for variational optimization of deep-learning molecular wave functions
• Machine-learning-corrected quantum dynamics calculations
• Reconstructing complex states of a 20-qubit quantum simulator
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Neural network approaches for solving Schrödinger equation in arbitrary quantum wells
• Deep-learning quasi-particle masses from QCD equation of state
• Convergence to the fixed-node limit in deep variational Monte Carlo
• A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for Deep BSDE solver
• Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines
• Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation
• Interatomic force from neural network based variational quantum Monte Carlo
• MIM: A deep mixed residual method for solving high-order partial differential equations
• Fermi Arcs From Dynamical Variational Monte Carlo
• Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities
• Neural network architectures using min-plus algebra for solving certain high dimensional optimal control problems and Hamilton-Jacobi PDEs
• Active Importance Sampling for Variational Objectives Dominated by Rare Events: Consequences for Optimization and Generalization
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistry
• Hybrid Auxiliary Field Quantum Monte Carlo for Molecular Systems
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Functional Tensor Network Solving Many-body Schrödinger Equation
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• Highly Accurate Real-space Electron Densities with Neural Networks
• Taming Landau level mixing in fractional quantum Hall states with deep learning
• Phase diagram reconstruction of the Bose-Hubbard model with a Restricted Boltzmann Machine wavefunction
• Electric Polarization from Many-Body Neural Network Ansatz
• Solving Schrodinger equations using physically constrained neural network
• A deep learning based reduced order modeling for stochastic underground flow problems
• Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
• Better, Faster Fermionic Neural Networks
• Investigating Network Parameters in Neural-Network Quantum States
• Deep learning quantum Monte Carlo for solids
• Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions
• DeepQuark: A Deep-Neural-Network Approach to Multiquark Bound States
• Quantum many-body solver using artificial neural networks and its applications to strongly correlated electron systems
• Boltzmann machines and quantum many-body problems
• Dynamical Variational Monte Carlo as a quantum impurity solver: Application to Cluster Dynamical Mean-Field Theory
• Quasi-Monte Carlo sampling for machine-learning partial differential equations
• Coarse-grained spectral projection (CGSP): a deep learning-assisted approach to quantum unitary dynamics
• Machine Learning Wavefunction
• Shifting sands of hardware and software in exascale quantum mechanical simulations
• Partial Differential Equations is All You Need for Generating Neural Architectures -- A Theory for Physical Artificial Intelligence Systems
• Quantum Machine Learning of Molecular Energies with Hybrid Quantum-Neural Wavefunction
• Deep quantum Monte Carlo approach for polaritonic chemistry
• Variational Quantum Imaginary Time Evolution for Matrix Product State Ansatz with Tests on Transcorrelated Hamiltonians
• Random Batch Algorithms for Quantum Monte Carlo simulations
• Deep learning neural network for approaching Schrödinger problems with arbitrary two-dimensional confinement
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Perturbation theory approach to study the latent space degeneracy of Variational Autoencoders
• Approximating Ground State Energies and Wave Functions of Physical Systems with Neural Networks
• Convergence of variational Monte Carlo simulation and scale-invariant pre-training
• Generalization Error Estimates of Machine Learning Methods for Solving High Dimensional Schrödinger Eigenvalue Problems
• Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling
• Ground States of Quantum Many Body Lattice Models via Reinforcement Learning
• Machine learning the single-$\Lambda$ hypernuclei with neural-network quantum states
• Neural-Network Quantum States for Periodic Systems in Continuous Space
• Geometry of backflow transformation ansatz for quantum many-body fermionic wavefunctions
• Lower Bound on the Representation Complexity of Antisymmetric Tensor Product Functions
• Fast evaluation of interaction integrals for confined systems with machine learning
• Hyperbolic recurrent neural network as the first type of non-Euclidean neural quantum state ansatz
• Electronic excited states in deep variational Monte Carlo
• Weakly-supervised learning on Schrodinger equation
• Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network