Recurrent Neural Network Wave Functions

Abstract

A core technology that has emerged from the artificial intelligence revolution is the recurrent neural network (RNN). Its unique sequence-based architecture provides a tractable likelihood estimate with stable training paradigms, a combination that has precipitated many spectacular advances in natural language processing and neural machine translation. This architecture also makes a good candidate for a variational wave function, where the RNN parameters are tuned to learn the approximate ground state of a quantum Hamiltonian. In this paper, we demonstrate the ability of RNNs to represent several many-body wave functions, optimizing the variational parameters using a stochastic approach. Among other attractive features of these variational wave functions, their autoregressive nature allows for the efficient calculation of physical estimators by providing independent samples. We demonstrate the effectiveness of RNN wave functions by calculating ground state energies, correlation functions, and entanglement entropies for several quantum spin models of interest to condensed matter physicists in one and two spatial dimensions.

The GitHub link to the open-source code is fixed

References in corpus (26)

• A variational eigenvalue solver on a quantum processor
• Holographic Derivation of Entanglement Entropy from AdS/CFT
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Spin Liquid Ground State of the $S=1/2$ Kagome Heisenberg Model
• Many-body quantum state tomography with neural networks
• Tensor networks for complex quantum systems
• Dimerization and Incommensurate Spiral Spin Correlations in the Zigzag Spin Chain: Analogies to the Kondo Lattice
• Measuring Renyi Entanglement Entropy with Quantum Monte Carlo
• Tensor Network Renormalization
• Reconstructing quantum states with generative models
• Numerical Evidence for Multiplicative Logarithmic Corrections from Marginal Operators
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Fermionic neural-network states for ab-initio electronic structure
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Topological Entanglement Renyi Entropy and Reduced Density Matrix Structure
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Quantum Entanglement in Deep Learning Architectures
• Gradient methods for variational optimization of projected entangled-pair states
• Variational quantum Monte Carlo simulations with tensor-network states
• Artificial Neural Network Methods in Quantum Mechanics
• Zero-variance principle for Monte Carlo algorithms
• Zero-Variance Zero-Bias Principle for Observables in quantum Monte Carlo: Application to Forces
• Error estimates for extrapolations with matrix-product states
• How much entanglement is needed to reduce the energy variance?
• Long-Range Entangled-Plaquette States for Critical and Frustrated Quantum Systems on a Lattice

Cited by in corpus (61)

• Provably efficient machine learning for quantum many-body problems
• Exploring entanglement and optimization within the Hamiltonian Variational Ansatz
• Machine Learning for Quantum Matter
• Ab-initio quantum chemistry with neural-network wavefunctions
• Neural tensor contractions and the expressive power of deep neural quantum states
• Transformer variational wave functions for frustrated quantum spin systems
• Variational Neural Annealing
• Autoregressive Transformer Neural Network for Simulating Open Quantum Systems via a Probabilistic Formulation
• Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape
• High-accuracy variational Monte Carlo for frustrated magnets with deep neural networks
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Neural Error Mitigation of Near-Term Quantum Simulations
• Transformer Quantum State: A Multi-Purpose Model for Quantum Many-Body Problems
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models
• Advances in Quantum Deep Learning: An Overview
• U(1) symmetric recurrent neural networks for quantum state reconstruction
• Direct sampling of projected entangled-pair states
• Gauge equivariant neural networks for quantum lattice gauge theories
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Scaling of neural-network quantum states for time evolution
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics
• Expressive power of complex-valued restricted Boltzmann machines for solving non-stoquastic Hamiltonians
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• QGOpt: Riemannian optimization for quantum technologies
• Quantum-tailored machine-learning characterization of a superconducting qubit
• Protocol Discovery for the Quantum Control of Majoranas by Differentiable Programming and Natural Evolution Strategies
• Unitary long-time evolution with quantum renormalization groups and artificial neural networks
• Reconstructing complex states of a 20-qubit quantum simulator
• Iterative Retraining of Quantum Spin Models Using Recurrent Neural Networks
• Dynamical large deviations of two-dimensional kinetically constrained models using a neural-network state ansatz
• Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines
• Reconstructing quantum molecular rotor ground states
• Adaptive Quantum State Tomography with Active Learning
• Rapid training of quantum recurrent neural networks
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• jVMC: Versatile and performant variational Monte Carlo leveraging automated differentiation and GPU acceleration
• Gaussian Process States: A data-driven representation of quantum many-body physics
• $m^{\ast }$ of two-dimensional electron gas: a neural canonical transformation study
• Neural network enhanced measurement efficiency for molecular groundstates
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization
• Ground state search by local and sequential updates of neural network quantum states
• Supplementing Recurrent Neural Networks with Annealing to Solve Combinatorial Optimization Problems
• Matrix Product States with Backflow correlations
• Wave function network description and Kolmogorov complexity of quantum many-body systems
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• Deep reinforcement learning for preparation of thermal and prethermal quantum states
• Certificates of quantum many-body properties assisted by machine learning
• Accelerating equilibrium spin-glass simulations using quantum annealers via generative deep learning
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Rayleigh-Gauss-Newton optimization with enhanced sampling for variational Monte Carlo
• Lee-Yang theory of quantum phase transitions with neural network quantum states
• Learning Potentials of Quantum Systems using Deep Neural Networks
• Watch and learn -- a generalized approach for transferrable learning in deep neural networks via physical principles
• Machine Learning Wavefunction
• Time-dependent variational principle for open quantum systems with artificial neural networks
• Multiqubit state learning with entangling quantum generative adversarial networks
• Revisiting the dynamics of Bose-Einstein condensates in a double well by deep learning with a hybrid network
• An Empirical Study of Quantum Dynamics as a Ground State Problem with Neural Quantum States
• Worldline algorithm by oracle-guided variational autoregressive network
• Tensorization of neural networks for improved privacy and interpretability