Improving neural network performance for solving quantum sign structure

Abstract

Neural quantum states have emerged as a widely used approach to the numerical study of the ground states of non-stoquastic Hamiltonians. However, existing approaches often rely on a priori knowledge of the sign structure or require a separately pre-trained phase network. We introduce a modified stochastic reconfiguration method that effectively uses differing imaginary time steps to evolve the amplitude and phase. Using a larger time step for phase optimization, this method enables a simultaneous and efficient training of phase and amplitude neural networks. The efficacy of our method is demonstrated on the Heisenberg J_1-J_2 model.

8 pages, 3 figures, to be published in Physical Review B

References in corpus (50)

• The density-matrix renormalization group
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum Spin Liquids
• Topological Insulator Materials
• Quantum Spin Liquid States
• Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations
• Tensor networks for complex quantum systems
• Quantum Entanglement in Neural Network States
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Plaquette Ordered Phase and Quantum Phase Diagram in the Spin-1/2 J1-J2 Square Heisenberg Model
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Symmetries and many-body excited states with neural-network quantum states
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Approximating quantum many-body wave-functions using artificial neural networks
• Magnetic order and disorder in the frustrated quantum Heisenberg antiferromagnet in two dimensions
• Direct evidence for a gapless $Z_2$ spin liquid by frustrating Néel antiferromagnetism
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Constructing exact representations of quantum many-body systems with deep neural networks
• Variational Monte Carlo Method Combined with Quantum-Number Projection and Multi-Variable Optimization
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Dirac-type nodal spin liquid revealed by refined quantum many-body solver using neural-network wave function, correlation ratio, and level spectroscopy
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Solving frustrated quantum many-particle models with convolutional neural networks
• A tensor product state approach to spin-1/2 square $J_1$-$J_2$ antiferromagnetic Heisenberg model: evidence for deconfined quantum criticality
• Ground-State Properties of Quantum Many-Body Systems: Entangled-Plaquette States and Variational Monte Carlo
• Fermionic Wave Functions from Neural-Network Constrained Hidden States
• Neural Gutzwiller-projected variational wave functions
• Transformer variational wave functions for frustrated quantum spin systems
• Gapless quantum spin liquid and global phase diagram of the spin-1/2 $J_1$-$J_2$ square antiferromagnetic Heisenberg model
• Neural network wave functions and the sign problem
• Empowering deep neural quantum states through efficient optimization
• The antiferromagnetic spin-1/2 Heisenberg model on the square lattice in a magnetic field
• Lectures on the Bethe Ansatz
• Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
• 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
• A simple linear algebra identity to optimize Large-Scale Neural Network Quantum States
• The learnability scaling of quantum states: restricted Boltzmann machines
• Optimizing Design Choices for Neural Quantum States
• Dynamical structure factor of the $J_1-J_2$ Heisenberg model in one dimension: the variational Monte Carlo approach
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Deep Learning-Enhanced Variational Monte Carlo Method for Quantum Many-Body Physics
• Determinant-free fermionic wave function using feed-forward neural networks
• Approximating power of machine-learning ansatz for quantum many-body states
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Neural Network Evolution Strategy for Solving Quantum Sign Structures
• A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions
• Entanglement Features of Random Neural Network Quantum States
• Variational optimization of the amplitude of neural-network quantum many-body ground states

Cited by in corpus (2)

• Basis dependence of Neural Quantum States for the Transverse Field Ising Model
• Brute-force positivization of $J_1-J_2$ model ground states