Deep neural network solution of the electronic Schrödinger equation

Abstract

[New and updated results were published in Nature Chemistry, doi:10.1038/s41557-020-0544-y.] The electronic Schrödinger equation describes fundamental properties of molecules and materials, but can only be solved analytically for the hydrogen atom. The numerically exact full configuration-interaction method is exponentially expensive in the number of electrons. Quantum Monte Carlo is a possible way out: it scales well to large molecules, can be parallelized, and its accuracy has, as yet, only been limited by the flexibility of the used wave function ansatz. Here we propose PauliNet, a deep-learning wave function ansatz that achieves nearly exact solutions of the electronic Schrödinger equation. PauliNet has a multireference Hartree-Fock solution built in as a baseline, incorporates the physics of valid wave functions, and is trained using variational quantum Monte Carlo (VMC). PauliNet outperforms comparable state-of-the-art VMC ansatzes for atoms, diatomic molecules and a strongly-correlated hydrogen chain by a margin and is yet computationally efficient. We anticipate that thanks to the favourable scaling with system size, this method may become a new leading method for highly accurate electronic-strucutre calculations on medium-sized molecular systems.

arXiv commentAdd notice about new results in journal-published version

References in corpus (26)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine Learning Unifies the Modelling of Materials and Molecules
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Continuum variational and diffusion quantum Monte Carlo calculations
• Alchemical and structural distribution based representation for improved QML
• A Transferable Machine-Learning Model of the Electron Density
• Fermionic neural-network states for ab-initio electronic structure
• Inhomogeneous backflow transformations in quantum Monte Carlo calculations
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Full optimization of Jastrow-Slater wave functions with application to the first-row atoms and homonuclear diatomic molecules
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Multi-Determinant Wave-functions in Quantum Monte Carlo
• Optimizing large parameter sets in variational quantum Monte Carlo
• Fast and accurate quantum Monte Carlo for molecular crystals
• Scheme for adding electron-nucleus cusps to Gaussian orbitals
• Energies of the first row atoms from quantum Monte Carlo
• Quantum Monte Carlo study of the first-row atoms and ions
• Nonlinear Network description for many-body quantum systems in continuous space
• Method to solve quantum few-body problems with artificial neural networks

Cited by in corpus (176)

• Machine Learning Force Fields
• The Variational Quantum Eigensolver: a review of methods and best practices
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Machine learning for electronically excited states of molecules
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Intelligent Computing: The Latest Advances, Challenges and Future
• Towards self-driving laboratories: The central role of density functional theory in the AI age
• A practical guide to machine learning interatomic potentials -- Status and future
• Perspective on integrating machine learning into computational chemistry and materials science
• A perspective on the current state-of-the-art of quantum computing for drug discovery applications
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• Quantum Machine Learning for Chemistry and Physics
• Interactions between Large Molecules: Puzzle for Reference Quantum-Mechanical Methods
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Ab-initio quantum chemistry with neural-network wavefunctions
• Neural tensor contractions and the expressive power of deep neural quantum states
• Fermionic Wave Functions from Neural-Network Constrained Hidden States
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Natural quantum reservoir computing for temporal information processing
• Discovering Quantum Phase Transitions with Fermionic Neural Networks
• Graph Neural Networks for Molecules
• Prospects of Quantum Computing for Molecular Sciences
• 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
• Phases of two-dimensional spinless lattice fermions with first-quantized deep neural-network quantum states
• Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
• Matrix Model simulations using Quantum Computing, Deep Learning, and Lattice Monte Carlo
• Physics-Informed Supervised Residual Learning for Electromagnetic Modeling
• Accurate Computation of Quantum Excited States with Neural Networks
• Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models
• El Agente: An Autonomous Agent for Quantum Chemistry
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas
• Neural-network quantum states for many-body physics
• Gauge equivariant neural networks for quantum lattice gauge theories
• Determinant-free fermionic wave function using feed-forward neural networks
• Investigating Topological Order using Recurrent Neural Networks
• Deep learning probability flows and entropy production rates in active matter
• Scientific intuition inspired by machine learning generated hypotheses
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Optimizing Jastrow factors for the transcorrelated method
• Neural Networks Enforcing Physical Symmetries in Nonlinear Dynamical Lattices: The Case Example of the Ablowitz-Ladik Model
• DeepQMC: an open-source software suite for variational optimization of deep-learning molecular wave functions
• Neural network approaches for solving Schrödinger equation in arbitrary quantum wells
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Predicting Superconducting Transition Temperature through Advanced Machine Learning and Innovative Feature Engineering
• Fast and flexible long-range models for atomistic machine learning
• Ab-initio variational wave functions for the time-dependent many-electron Schrödinger equation
• Automatic Differentiable Monte Carlo: Theory and Application
• Convergence to the fixed-node limit in deep variational Monte Carlo
• Ground state phases of the two-dimension electron gas with a unified variational approach
• PyQMC: an all-Python real-space quantum Monte Carlo module in PySCF
• Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation
• Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities
• Interatomic force from neural network based variational quantum Monte Carlo
• A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions
• Optimal Thermometers with Spin Networks
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets
• Neural network approach to quasiparticle dispersions in doped antiferromagnets
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• jVMC: Versatile and performant variational Monte Carlo leveraging automated differentiation and GPU acceleration
• Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer
• Gaussian Process States: A data-driven representation of quantum many-body physics
• Neural network backflow for ab-initio quantum chemistry
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• Variational Quantum-Neural Hybrid Error Mitigation
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Solving and visualizing fractional quantum Hall wavefunctions with neural network
• Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistry
• Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states
• Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Solving the nuclear pairing model with neural network quantum states
• Neural Wave Functions for Superfluids
• Is attention all you need to solve the correlated electron problem?
• Hybrid Auxiliary Field Quantum Monte Carlo for Molecular Systems
• Computation of forces and stresses in solids: Towards accurate structural optimization with auxiliary-field quantum Monte Carlo
• LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
• Data-driven Refinement of Electronic Energies from Two-Electron Reduced-Density-Matrix Theory
• Data-driven compression of electron-phonon interactions
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression
• Functional Tensor Network Solving Many-body Schrödinger Equation
• Artificial-intelligence-based surrogate solution of dissipative quantum dynamics: physics-informed reconstruction of the universal propagator
• Taming Landau level mixing in fractional quantum Hall states with deep learning
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• Highly Accurate Real-space Electron Densities with Neural Networks
• Modeling lens potentials with continuous neural fields in galaxy-scale strong lenses
• Extending the reach of quantum computing for materials science with machine learning potentials
• Electric Polarization from Many-Body Neural Network Ansatz
• Deep Neural Networks as Variational Solutions for Correlated Open Quantum Systems
• Accurate neural quantum states for interacting lattice bosons
• Autoregressive neural quantum states of Fermi Hubbard models
• Impact of conditional modelling for a universal autoregressive quantum state
• Solving the Schrodinger equation with genetic algorithms: a practical approach
• A deep learning based reduced order modeling for stochastic underground flow problems
• Interpolating many-body wave functions for accelerated molecular dynamics on the near-exact electronic surface
• Solving Schrodinger equations using physically constrained neural network
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
• Quantum Transport in Open Spin Chains using Neural-Network Quantum States
• Reproducibility of fixed-node diffusion Monte Carlo across diverse community codes: The case of water-methane dimer
• An improved penalty-based excited-state variational Monte Carlo approach with deep-learning ansatzes
• Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
• Rayleigh-Gauss-Newton optimization with enhanced sampling for variational Monte Carlo
• Deep learning methods for the computation of vibrational wavefunctions
• Deep learning quantum Monte Carlo for solids
• A deep neural network approach to solve the Dirac equation
• Time evolution as an optimization problem: The hydrogen atom in strong laser fields in a basis of time-dependent Gaussian wave packets
• Second-order optimisation strategies for neural network quantum states
• Maximising Quantum-Computing Expressive Power through Randomised Circuits
• Investigating Network Parameters in Neural-Network Quantum States
• Deep learning nonlocal and scalable energy functionals for quantum Ising models
• Quantum many-body solver using artificial neural networks and its applications to strongly correlated electron systems
• Machine learning one-dimensional spinless trapped fermionic systems with neural-network quantum states
• DeepQuark: A Deep-Neural-Network Approach to Multiquark Bound States
• Boltzmann machines and quantum many-body problems
• Quantum computing quantum Monte Carlo algorithm
• Simulation of Charge Stability Diagrams for Automated Tuning Solutions (SimCATS)
• Multi-body wave function of ground and low-lying excited states using unornamented deep neural networks
• Beyond single-reference fixed-node approximation in ab initio Diffusion Monte Carlo using antisymmetrized geminal power applied to systems with hundreds of electrons
• Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations
• Stochastic Algorithms for Self-consistent Calculations of Electronic Structures
• Exploring explicit coarse-grained structure in artificial neural networks
• Shifting sands of hardware and software in exascale quantum mechanical simulations
• Coarse-grained spectral projection (CGSP): a deep learning-assisted approach to quantum unitary dynamics
• Quantum-assisted variational Monte Carlo
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schrödinger Equation
• Inferring Hidden Symmetries of Exotic Magnets from Detecting Explicit Order Parameters
• Neural-network quantum state study of the long-range antiferromagnetic Ising chain
• Machine learning the deuteron: new architectures and uncertainty quantification
• Synergy between deep neural networks and the variational Monte Carlo method for small ${}^{4}H{e}_N$ clusters
• Deep quantum Monte Carlo approach for polaritonic chemistry
• Quantum Machine Learning of Molecular Energies with Hybrid Quantum-Neural Wavefunction
• Fully numerical Hartree-Fock calculations for atoms and small molecules with quantics tensor trains
• Understanding and eliminating spurious modes in variational Monte Carlo using collective variables
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Adapting reservoir computing to solve the Schrödinger equation
• Deep learning neural network for approaching Schrödinger problems with arbitrary two-dimensional confinement
• Solving Fermi-Hubbard-type Models by Tensor Representations of Backflow Corrections
• Mott Transition and Volume Law Entanglement with Neural Quantum States
• Determinant- and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions
• Simple Fermionic backflow states via a systematically improvable tensor decomposition
• Phase diagram and crystal melting of helium-4 in two dimensions
• Simulating methylamine using symmetry adapted qubit-excitation-based variational quantum eigensolver
• NNQS-AFQMC: Neural network quantum states enhanced fermionic quantum Monte Carlo
• Generalization Error Estimates of Machine Learning Methods for Solving High Dimensional Schrödinger Eigenvalue Problems
• Machine learning the single-$\Lambda$ hypernuclei with neural-network quantum states
• Bound on entanglement in neural quantum states
• Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations
• Convergence of variational Monte Carlo simulation and scale-invariant pre-training
• Expressivity of determinantal ansatzes for neural network wave functions
• Gaussian Processes for Finite Size Extrapolation of Many-Body Simulations
• Neuralized Fermionic Tensor Networks for Quantum Many-Body Systems
• Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling
• Topological Learning in Multi-Class Data Sets
• Neural Wave Functions for High-Pressure Atomic Hydrogen
• A Denser Hydrogen Inferred from First-Principles Simulations Challenges Jupiter's Interior Models
• Entanglement scaling and criticality of infinite-size quantum many-body systems in continuous space addressed by a tensor network approach
• Worldline algorithm by oracle-guided variational autoregressive network
• Multiclass classification of dephasing channels
• Precise Quantum Chemistry calculations with few Slater Determinants
• Quantum-Classical Computing for Time-Dependent Ion-Atom Collision Dynamics: Applications to Charge Transfer Cross Section Simulations
• Neural Mode Jump Monte Carlo
• Variational Neural Network Approach to QFT in the Field Basis
• Improving the performance of fermionic neural networks with the Slater exponential Ansatz
• Electronic excited states in deep variational Monte Carlo
• Neural-Network Quantum States for Periodic Systems in Continuous Space
• HOAX: A Hyperparameter Optimization Algorithm Explorer for Neural Networks