Symmetries and Many-Body Excitations with Neural-Network Quantum States.

  title={Symmetries and Many-Body Excitations with Neural-Network Quantum States.},
  author={Kenny Choo and Giuseppe Carleo and Nicolas Regnault and Titus Neupert},
  journal={Physical review letters},
  volume={121 16},
Artificial neural networks have been recently introduced as a general ansatz to represent many-body wave functions. In conjunction with variational Monte Carlo calculations, this ansatz has been applied to find Hamiltonian ground states and their energies. Here, we provide extensions of this method to study excited states, a central task in several many-body quantum calculations. First, we give a prescription that allows us to target eigenstates of a (nonlocal) symmetry of the Hamiltonian… 

Figures from this paper

Restricted Boltzmann Machines for Quantum States with Non-Abelian or Anyonic Symmetries.
This work applies its methodology to find the ground states of the one-dimensional antiferromagnetic Heisenberg (AFH) model with spin-1/2 andspin-1 degrees of freedom, and obtains a substantially higher accuracy than when using the s_{z} basis as an input to the neural network.
Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
  • Y. Nomura
  • Physics, Computer Science
    Journal of physics. Condensed matter : an Institute of Physics journal
  • 2021
This work constructs a variational wave function with one of the simplest neural networks, the restricted Boltzmann machine (RBM), and applies it to a fundamental but unsolved quantum spin Hamiltonian, the two-dimensional J 1–J 2 Heisenberg model on the square lattice.
Fermionic neural-network states for ab-initio electronic structure
An extension of neural-network quantum states to model interacting fermionic problems and use neural-networks to perform electronic structure calculations on model diatomic molecules to achieve chemical accuracy.
Two-dimensional frustrated J1−J2 model studied with neural network quantum states
This paper uses a fully convolutional neural network model as a variational ansatz to study the frustrated spin-1/2 J1-J2 Heisenberg model on the square lattice and demonstrates that the resulting predictions for both ground-state energies and properties are competitive with, and often improve upon, existing state-of-the-art methods.
Variational Monte Carlo Calculations of A≤4 Nuclei with an Artificial Neural-Network Correlator Ansatz.
This work introduces a neural-network quantum state ansatz to model the ground-state wave function of light nuclei, and approximately solve the nuclear many-body Schrödinger equation.
Many-body quantum states with exact conservation of non-Abelian and lattice symmetries through variational Monte Carlo
This work presents an ansatz where global non-abelian symmetries are inherently embedded in its structure and extends the model to incorporate lattice asymmetries as well, allowing to find the wave functions of excited states with definite quantum numbers associated to the considered symmetry without modifying the architecture of the network.
Correlation-enhanced neural networks as interpretable variational quantum states
This letter introduces a neural-network based variational ansatz that retains the flexibility of these generic methods while allowing for a tunability with respect to the relevant correlations governing the physics of the system.
Approximating power of machine-learning ansatz for quantum many-body states
The connection between the structure of RBM and perturbation series is uncovered, which explains the excellent precision achieved by RBM ansazt in certain simple models, and the numerical algorithm is improved to achieve better performance of R BM in cases where local minima complicate the convergence to the global one.
Constructing neural stationary states for open quantum many-body systems
A new variational scheme based on the neural-network quantum states to simulate the stationary states of open quantum many-body systems, which is dubbed as the neural stationary state ansatz, and shown to simulate various spin systems efficiently.
Neural network wave functions and the sign problem
This work proposes a neural network architecture with a simple, explicit, and interpretable phase ansatz, which can robustly represent low-energy states and achieve state-of-the-art variational energies for both conventional and frustrated antiferromagnets.


Approximating quantum many-body wave functions using artificial neural networks
In this paper, we demonstrate the expressibility of artificial neural networks (ANNs) in quantum many-body physics by showing that a feed-forward neural network with a small number of hidden layers
Neural-Network Quantum States, String-Bond States, and Chiral Topological States
The results demonstrate the efficiency of neural networks to describe complex quantum wave functions and pave the way towards the use of String-Bond States as a tool in more traditional machine-learning applications.
Efficient representation of quantum many-body states with deep neural networks
A proof that, assuming a widely believed computational complexity conjecture, a deep neural network can efficiently represent most physical states, including the ground states of many-body Hamiltonians and states generated by quantum dynamics, while a shallow network representation with a restricted Boltzmann machine cannot efficiently represent some of those states.
Probing many-body localization with neural networks
We show that a simple artificial neural network trained on entanglement spectra of individual states of a many-body quantum system can be used to determine the transition between a many-body
Solving the quantum many-body problem with artificial neural networks
A variational representation of quantum states based on artificial neural networks with a variable number of hidden neurons and a reinforcement-learning scheme that is capable of both finding the ground state and describing the unitary time evolution of complex interacting quantum systems.
Quantum Entanglement in Neural Network States
The results uncover the unparalleled power of artificial neural networks in representing quantum many-body states, which paves a novel way to bridge computer science based machine learning techniques to outstanding quantum condensed matter physics problems.
Machine Learning Technique to Find Quantum Many-Body Ground States of Bosons on a Lattice
A variational method to obtain many-body ground states of the Bose–Hubbard model using feedforward artificial neural networks is developed and it is shown that many- body ground states with different numbers of particles can be generated by a single network.
Machine learning technique to find quantum many-body ground states of bosons on a lattice
A variational method to obtain many-body ground states of the Bose-Hubbard model using feedforward artificial neural networks is developed and it is shown that many- body ground states with different numbers of atoms can be generated by a single network.
Learning hard quantum distributions with variational autoencoders
This work introduces a practically usable deep architecture for representing and sampling from probability distributions of quantum states based on variational auto-encoders, a type of generative model in the form of a neural network, and shows that this model is able to learn efficient representations of states that are easy to simulate classically and can compress states which are not classically tractable.
Restricted Boltzmann machine learning for solving strongly correlated quantum systems
The combined method substantially improves the accuracy beyond that ever achieved by each method separately, in the Heisenberg as well as Hubbard models on square lattices, thus proving its power as a highly accurate quantum many-body solver.