Multi-body wave function of ground and low-lying excited states using unornamented deep neural networks
arXiv:2302.08965 · doi:10.1103/PhysRevResearch.5.033189
Abstract
We propose a method to calculate wave functions and energies not only of the ground state but also of low-lying excited states using a deep neural network and the unsupervised machine learning technique. For systems composed of identical particles, a simple method to perform symmetrization for bosonic systems and antisymmetrization for fermionic systems is also proposed.
arXiv comment23 pages, 18 figures, 8 tables; Typo of Eq. (25) corrected
References in corpus (40)
- The density-matrix renormalization group
- Electronic Structure Calculations with Dynamical Mean-Field Theory: A Spectral Density Functional Approach
- First-principles Calculations of the Electronic Structure and Spectra of Strongly Correlated Systems: Dynamical Mean-field Theory
- Density matrix embedding: A simple alternative to dynamical mean-field theory
- Ab Initio Quantum Chemistry using the Density Matrix Renormalization Group
- Deep neural network solution of the electronic Schrödinger equation
- Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
- Precise solution of few-body problems with stochastic variational method on correlated Gaussian basis
- Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
- From Few to Many: Observing the Formation of a Fermi Sea One Atom at a Time
- Benchmark Test Calculation of a Four-Nucleon Bound State
- The Density Matrix Renormalization Group in Chemistry and Molecular Physics: Recent Developments and New Challenges
- Lattice simulations for few- and many-body systems
- Time-dependent density-functional description of nuclear dynamics
- Symmetries and many-body excited states with neural-network quantum states
- Few-nucleon systems in translationally invariant harmonic oscillator basis
- Time-dependent Hartree-Fock calculations for multinucleon transfer processes in Ca+Sn, Ca+Pb, and Ni+Pb reactions
- State Dependent Effective Interaction for the Hyperspherical Formalism
- Constructing exact representations of quantum many-body systems with deep neural networks
- A Full Configuration Interaction Perspective on the Homogeneous Electron Gas
- Auxiliary field diffusion Monte Carlo calculations of light and medium-mass nuclei with local chiral interactions
- Investigation of the Full Configuration Interaction Quantum Monte Carlo Method Using Homogeneous Electron Gas Models
- Deep Learning and AdS/CFT
- A lattice theory for low energy fermions at finite chemical potential
- Deep Learning and Holographic QCD
- Quantum Monte Carlo study of the first-row atoms and ions
- Four-nucleon shell-model calculations in a Faddeev-like approach
- Machine learning the deuteron
- Lattice methods for strongly interacting many-body systems
- Time-dependent density functional theory of high-intensity, short-pulse laser irradiation on insulators
- AdS/CFT as a deep Boltzmann machine
- Time-dependent Hartree-Fock plus Langevin approach for hot fusion reactions to synthesize the superheavy element
- Time-dependent generator coordinate method study of mass-asymmetric fission of actinides
- Method to solve quantum few-body problems with artificial neural networks
- Finite Temperature Auxiliary Field Quantum Monte Carlo in the Canonical Ensemble
- Machine Learning Quantum States -- Extensions to Fermion-Boson Coupled Systems and Excited-State Calculations
- Hartree-Fock+BCS approach to unstable nuclei with the Skyrme force
- Development of the temperature-dependent interatomic potential for molecular dynamics simulation of metal irradiated with an ultrashort pulse laser
- Green Function Monte Carlo Method for Excited States of Quantum System
- Monte-Carlo Study of Bound States in a Few-Nucleon System - Method of Continued Fractions -