Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks

Abstract

Given access to accurate solutions of the many-electron Schrödinger equation, nearly all chemistry could be derived from first principles. Exact wavefunctions of interesting chemical systems are out of reach because they are NP-hard to compute in general, but approximations can be found using polynomially-scaling algorithms. The key challenge for many of these algorithms is the choice of wavefunction approximation, or Ansatz, which must trade off between efficiency and accuracy. Neural networks have shown impressive power as accurate practical function approximators and promise as a compact wavefunction Ansatz for spin systems, but problems in electronic structure require wavefunctions that obey Fermi-Dirac statistics. Here we introduce a novel deep learning architecture, the Fermionic Neural Network, as a powerful wavefunction Ansatz for many-electron systems. The Fermionic Neural Network is able to achieve accuracy beyond other variational quantum Monte Carlo Ansätze on a variety of atoms and small molecules. Using no data other than atomic positions and charges, we predict the dissociation curves of the nitrogen molecule and hydrogen chain, two challenging strongly-correlated systems, to significantly higher accuracy than the coupled cluster method, widely considered the most accurate scalable method for quantum chemistry at equilibrium geometry. This demonstrates that deep neural networks can improve the accuracy of variational quantum Monte Carlo to the point where it outperforms other ab-initio quantum chemistry methods, opening the possibility of accurate direct optimization of wavefunctions for previously intractable many-electron systems.

Final proof for Physical Review Research

References in corpus (30)

• SchNet - a deep learning architecture for molecules and materials
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Optimization of quantum Monte Carlo wave functions by energy minimization
• Green Function Monte Carlo with Stochastic Reconfiguration
• Symmetries and many-body excited states with neural-network quantum states
• Fermionic neural-network states for ab-initio electronic structure
• Towards the solution of the many-electron problem in real materials: equation of state of the hydrogen chain with state-of-the-art many-body methods
• Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Deep learning and the Schrödinger equation
• Pfaffian pairing wave functions in electronic structure quantum Monte Carlo
• Optimizing large parameter sets in variational quantum Monte Carlo
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Computing the energy of a water molecule using MultiDeterminants: A simple, efficient algorithm
• Quantum Monte Carlo study of the first-row atoms and ions
• Perturbatively selected configuration-interaction wave functions for efficient geometry optimization in quantum Monte Carlo
• Iterative backflow renormalization procedure for many-body ground state wave functions of strongly interacting normal Fermi liquids
• Strategies for improving the efficiency of quantum Monte Carlo calculations
• Nonlinear Network description for many-body quantum systems in continuous space
• Finite temperature electronic simulations beyond the Born-Oppenheimer approximation
• Method to solve quantum few-body problems with artificial neural networks
• Deep Learning-Enhanced Variational Monte Carlo Method for Quantum Many-Body Physics
• Methods for calculating forces within quantum Monte Carlo simulations
• Complementary First and Second Derivative Methods for Ansatz Optimization in Variational Monte Carlo
• An accelerated linear method for optimizing non-linear wavefunctions in variational Monte Carlo

Cited by in corpus (197)

• The Variational Quantum Eigensolver: a review of methods and best practices
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Deep neural network solution of the electronic Schrödinger equation
• Machine learning for electronically excited states of molecules
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Fermionic neural-network states for ab-initio electronic structure
• Perspective on integrating machine learning into computational chemistry and materials science
• 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
• Interactions between Large Molecules: Puzzle for Reference Quantum-Mechanical Methods
• Machine Learning for Quantum Matter
• Variational and Diffusion Quantum Monte Carlo Calculations with the CASINO Code
• Ab-initio quantum chemistry with neural-network wavefunctions
• Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modeling
• Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
• 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
• Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning
• Discovering Quantum Phase Transitions with Fermionic Neural Networks
• Autoregressive Transformer Neural Network for Simulating Open Quantum Systems via a Probabilistic Formulation
• Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
• Physics-informed neural networks for quantum control
• 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
• Accurate Computation of Quantum Excited States with Neural Networks
• Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models
• Unbiasing time-dependent Variational Monte Carlo by projected quantum evolution
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas
• Machine Learning from a Continuous Viewpoint
• Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
• 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
• Excited states in variational Monte Carlo using a penalty method
• HomPINNs: homotopy physics-informed neural networks for solving the inverse problems of nonlinear differential equations with multiple solutions
• Investigating Topological Order using Recurrent Neural Networks
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Deep learning probability flows and entropy production rates in active matter
• Quasinormal modes of dS and AdS Black Holes: Feedforward neural network method
• A hybrid approach to excited-state-specific variational Monte Carlo and doubly excited states
• Optimizing Jastrow factors for the transcorrelated method
• Towards DMC accuracy across chemical space with scalable $\Delta$-QML
• 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 Density Functional Theory Based on Variational Energy Minimization
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Automatic Differentiable Monte Carlo: Theory and Application
• Quantum neural networks force fields generation
• Ab-initio variational wave functions for the time-dependent many-electron Schrödinger equation
• Inferring electrochemical performance and parameters of Li-ion batteries based on deep operator networks
• Convergence to the fixed-node limit in deep variational Monte Carlo
• Deep Variational Free Energy Approach to Dense Hydrogen
• Ground state phases of the two-dimension electron gas with a unified variational approach
• Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation
• PyQMC: an all-Python real-space quantum Monte Carlo module in PySCF
• Fermi Arcs From Dynamical Variational Monte Carlo
• Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities
• Interatomic force from neural network based variational quantum Monte Carlo
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions
• Neural network approach to quasiparticle dispersions in doped antiferromagnets
• Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• Foundation Neural-Networks Quantum States as a Unified Ansatz for Multiple Hamiltonians
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• Gaussian Process States: A data-driven representation of quantum many-body physics
• Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer
• Assessing and Advancing the Potential of Quantum Computing: A NASA Case Study
• Neural network backflow for ab-initio quantum chemistry
• Benchmark Phaseless Auxiliary-Field Quantum Monte Carlo Method for Small Molecules
• jVMC: Versatile and performant variational Monte Carlo leveraging automated differentiation and GPU acceleration
• Variational Quantum-Neural Hybrid Error Mitigation
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• $m^{\ast }$ of two-dimensional electron gas: a neural canonical transformation study
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Solving the nuclear pairing model with neural network quantum states
• Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states
• Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistry
• Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
• Solving and visualizing fractional quantum Hall wavefunctions with neural network
• Neural Wave Functions for Superfluids
• Spin-1/2 kagome Heisenberg antiferromagnet: Machine learning discovery of the spinon pair density wave ground state
• Hybrid Auxiliary Field Quantum Monte Carlo for Molecular Systems
• Is attention all you need to solve the correlated electron problem?
• Variational optimization of the amplitude of neural-network quantum many-body ground states
• Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• Data-driven compression of electron-phonon interactions
• LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
• Computation of forces and stresses in solids: Towards accurate structural optimization with auxiliary-field quantum Monte Carlo
• Towards chemical accuracy using the Jastrow correlated antisymmetrized geminal power ansatz
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Artificial-intelligence-based surrogate solution of dissipative quantum dynamics: physics-informed reconstruction of the universal propagator
• Nematic metal in a multi-valley electron gas: Variational Monte Carlo analysis and application to AlAs
• Taming Landau level mixing in fractional quantum Hall states with deep learning
• Highly Accurate Real-space Electron Densities with Neural Networks
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• Extending the reach of quantum computing for materials science with machine learning potentials
• Deep reinforcement learning for preparation of thermal and prethermal quantum states
• Fine-tuning Neural Network Quantum States
• Deep Neural Networks as Variational Solutions for Correlated Open Quantum Systems
• Autoregressive neural quantum states of Fermi Hubbard models
• Are queries and keys always relevant? A case study on Transformer wave functions
• Electric Polarization from Many-Body Neural Network Ansatz
• Accurate neural quantum states for interacting lattice bosons
• Impact of conditional modelling for a universal autoregressive quantum state
• Equivariant Neural Networks for Spin Dynamics Simulations of Itinerant Magnets
• Hybrid Ground-State Quantum Algorithms based on Neural Schrödinger Forging
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Interpolating many-body wave functions for accelerated molecular dynamics on the near-exact electronic surface
• A deep learning based reduced order modeling for stochastic underground flow problems
• Solving Schrodinger equations using physically constrained neural network
• Efficient Solutions of Fermionic Systems using Artificial Neural Networks
• An improved penalty-based excited-state variational Monte Carlo approach with deep-learning ansatzes
• Rayleigh-Gauss-Newton optimization with enhanced sampling for variational Monte Carlo
• Deep learning methods for the computation of vibrational wavefunctions
• Reproducibility of fixed-node diffusion Monte Carlo across diverse community codes: The case of water-methane dimer
• Quantum Transport in Open Spin Chains using Neural-Network Quantum States
• Maximising Quantum-Computing Expressive Power through Randomised Circuits
• Investigating Network Parameters in Neural-Network Quantum States
• A deep neural network approach to solve the Dirac equation
• Deep learning quantum Monte Carlo for solids
• 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
• All you need is spin: SU(2) equivariant variational quantum circuits based on spin networks
• Energy Transfer in Random-Matrix ensembles of Floquet Hamiltonians
• Quantum computing quantum Monte Carlo algorithm
• Quantum many-body solver using artificial neural networks and its applications to strongly correlated electron systems
• Multi-body wave function of ground and low-lying excited states using unornamented deep neural networks
• Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations
• Performance assessment of the effective core potentials under the Fermionic neural network: first and second row elements
• Beyond single-reference fixed-node approximation in ab initio Diffusion Monte Carlo using antisymmetrized geminal power applied to systems with hundreds of electrons
• Machine learning one-dimensional spinless trapped fermionic systems with neural-network quantum states
• Boltzmann machines and quantum many-body problems
• DeepQuark: A Deep-Neural-Network Approach to Multiquark Bound States
• Dynamical Variational Monte Carlo as a quantum impurity solver: Application to Cluster Dynamical Mean-Field Theory
• Coarse-grained spectral projection (CGSP): a deep learning-assisted approach to quantum unitary dynamics
• Machine Learning Wavefunction
• Quantum-assisted variational Monte Carlo
• Exploring explicit coarse-grained structure in artificial neural networks
• Inferring Hidden Symmetries of Exotic Magnets from Detecting Explicit Order Parameters
• Shifting sands of hardware and software in exascale quantum mechanical simulations
• Deep learning methods for Hamiltonian parameter estimation and magnetic domain image generation in twisted van der Waals magnets
• Quantum Machine Learning of Molecular Energies with Hybrid Quantum-Neural Wavefunction
• 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
• Neural-network quantum state study of the long-range antiferromagnetic Ising chain
• Fully numerical Hartree-Fock calculations for atoms and small molecules with quantics tensor trains
• Deep quantum Monte Carlo approach for polaritonic chemistry
• Simulating methylamine using symmetry adapted qubit-excitation-based variational quantum eigensolver
• Deep variational free energy prediction of dense hydrogen solid at 1200K
• Understanding and eliminating spurious modes in variational Monte Carlo using collective variables
• Determinant- and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions
• Deep learning neural network for approaching Schrödinger problems with arbitrary two-dimensional confinement
• Mott Transition and Volume Law Entanglement with Neural Quantum States
• Solving Fermi-Hubbard-type Models by Tensor Representations of Backflow Corrections
• Simple Fermionic backflow states via a systematically improvable tensor decomposition
• Adapting reservoir computing to solve the Schrödinger equation
• NNQS-AFQMC: Neural network quantum states enhanced fermionic quantum Monte Carlo
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Efficient Learning of Long-Range and Equivariant Quantum Systems
• Phase diagram and crystal melting of helium-4 in two dimensions
• Physics-informed Transformers for Electronic Quantum States
• Convergence of variational Monte Carlo simulation and scale-invariant pre-training
• Physics-enhanced neural networks for equation-of-state calculations
• Physics-informed neural networks viewpoint for solving the Dyson-Schwinger equations of quantum electrodynamics
• Neuralized Fermionic Tensor Networks for Quantum Many-Body Systems
• Graphic characterization and clustering configuration descriptors of determinant space for molecules
• Highly efficient nuclear population transfer through physics-informed neural networks
• 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
• Topological Order in Neural Wavefunctions
• Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows
• Gaussian Processes for Finite Size Extrapolation of Many-Body Simulations
• Orbital Expansion Variational Quantum Eigensolver: Enabling Efficient Simulation of Molecules with Shallow Quantum Circuit
• Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling
• Neural Wave Functions for High-Pressure Atomic Hydrogen
• Neural Quantum States for Light Nuclei with Chiral Two- and Three-Body Interactions
• Expressivity of determinantal ansatzes for neural network wave functions
• Quantum-Inspired Tempering for Ground State Approximation using Artificial Neural Networks
• Lower Bound on the Representation Complexity of Antisymmetric Tensor Product Functions
• A Denser Hydrogen Inferred from First-Principles Simulations Challenges Jupiter's Interior Models
• Electronic excited states in deep variational Monte Carlo
• Generalized Lanczos method for systematic optimization of neural-network quantum states
• Neural-Network Quantum States for Periodic Systems in Continuous Space
• Entanglement scaling and criticality of infinite-size quantum many-body systems in continuous space addressed by a tensor network approach
• Variational Neural Network Approach to QFT in the Field Basis
• Improving the performance of fermionic neural networks with the Slater exponential Ansatz
• Precise Quantum Chemistry calculations with few Slater Determinants