Nonlinear Network description for many-body quantum systems in continuous space

Abstract

We show that the recently introduced iterative backflow renormalization can be interpreted as a general neural network in continuum space with non-linear functions in the hidden units. We use this wave function within Variational Monte Carlo for liquid ${}^4$He in two and three dimensions, where we typically find a tenfold increase in accuracy over currently used wave functions. Furthermore, subsequent stages of the iteration procedure define a set of increasingly good wave functions, each with its own variational energy and variance of the local energy: extrapolation of these energies to zero variance gives values in close agreement with the exact values. For two dimensional ${}^4$He, we also show that the iterative backflow wave function can describe both the liquid and the solid phase with the same functional form -a feature shared with the Shadow Wave Function, but now joined by much higher accuracy. We also achieve significant progress for liquid ${}^3$He in three dimensions, improving previous variational and fixed-node energies for this very challenging fermionic system.

References in corpus (12)

• The density-matrix renormalization group in the age of matrix product states
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Inhomogeneous backflow transformations in quantum Monte Carlo calculations
• Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
• Solving the Bose-Hubbard model with machine learning
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Exact ground state Monte Carlo method for Bosons without importance sampling
• Iterative backflow renormalization procedure for many-body ground state wave functions of strongly interacting normal Fermi liquids
• Continuous Matrix Product States for Quantum Fields: an Energy Minimization Algorithm
• Unitary dynamics of strongly-interacting Bose gases with time-dependent variational Monte Carlo in continuous space
• On the Sign Problem of the Fermionic Shadow Wave Function

Cited by in corpus (36)

• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Fermionic neural-network states for ab-initio electronic structure
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Ab-initio quantum chemistry with neural-network wavefunctions
• Discovering Quantum Phase Transitions with Fermionic Neural Networks
• Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas
• Electronic band gaps from Quantum Monte Carlo methods
• Neural-network quantum states for many-body physics
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Itinerant-electron magnetism: the importance of many-body correlations
• Self-learning projective quantum Monte Carlo simulations guided by restricted Boltzmann machines
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Neural-network quantum states at finite temperature
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines
• Ground state phases of the two-dimension electron gas with a unified variational approach
• Orbital-dependent backflow wave functions for real-space quantum Monte Carlo
• A simplified approach to the repulsive Bose gas from low to high densities and its numerical accuracy
• Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states
• Two-dimensional Mixture of Dipolar Fermions: Equation of State and Magnetic Phases
• Training models using forces computed by stochastic electronic structure methods
• Second layer crystalline phase of helium films on graphite
• Phase diagram reconstruction of the Bose-Hubbard model with a Restricted Boltzmann Machine wavefunction
• Accurate neural quantum states for interacting lattice bosons
• Solving Schrodinger equations using physically constrained neural network
• Better, Faster Fermionic Neural Networks
• A deep neural network approach to solve the Dirac equation
• Synergy between deep neural networks and the variational Monte Carlo method for small ${}^{4}H{e}_N$ clusters
• Mott Transition and Volume Law Entanglement with Neural Quantum States
• Phase diagram and crystal melting of helium-4 in two dimensions
• Determinant- and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions
• Neural Wave Functions for High-Pressure Atomic Hydrogen
• Ab-initio Quantum Monte Carlo study of ultracold atomic mixtures
• Neural-Network Quantum States for Periodic Systems in Continuous Space