Generalized Lanczos method for systematic optimization of neural-network quantum states

Abstract

Recently, artificial intelligence for science has made significant inroads into various fields of natural science research. In the field of quantum many-body computation, researchers have developed numerous ground state solvers based on neural-network quantum states (NQSs), achieving ground state energies with accuracy comparable to or surpassing traditional methods such as variational Monte Carlo methods, density matrix renormalization group, and quantum Monte Carlo methods. Here, we combine supervised learning, variational Monte Carlo (VMC), and the Lanczos method to develop a systematic approach to improving the NQSs of many-body systems, which we refer to as the NQS Lanczos method. The algorithm mainly consists of two parts: the supervised learning part and the VMC optimization part. Through supervised learning, the Lanczos states are represented by the NQSs. Through VMC, the NQSs are further optimized. We analyze the reasons for the underfitting problem and demonstrate how the NQS Lanczos method systematically improves the energy in the highly frustrated regime of the two-dimensional Heisenberg $J_1$-$J_2$ model. Compared to the existing method that combines the Lanczos method with the restricted Boltzmann machine, the primary advantage of the NQS Lanczos method is its linearly increasing computational cost.

13 pages, 8 figures, 5 tables

References in corpus (31)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Studying Two Dimensional Systems With the Density Matrix Renormalization Group
• Plaquette Ordered Phase and Quantum Phase Diagram in the Spin-1/2 J1-J2 Square Heisenberg Model
• Simulation of two-dimensional quantum systems using a tree tensor network that exploits the entropic area law
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
• Approximating quantum many-body wave-functions using artificial neural networks
• Direct evidence for a gapless $Z_2$ spin liquid by frustrating Néel antiferromagnetism
• Critical level crossings and gapless spin liquid in the square-lattice spin-$1/2$ $J_1$-$J_2$ Heisenberg antiferromagnet
• Variational quantum Monte Carlo simulations with tensor-network states
• Loop updates for variational and projector quantum Monte Carlo simulations in the valence-bond basis
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Ab-initio quantum chemistry with neural-network wavefunctions
• 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
• 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
• Unbiasing time-dependent Variational Monte Carlo by projected quantum evolution
• Variational ground states of 2D antiferromagnets in the valence bond basis
• Neural-network quantum states for many-body physics
• Automatic Differentiable Monte Carlo: Theory and Application
• Neural Network Evolution Strategy for Solving Quantum Sign Structures
• Neural network approach to quasiparticle dispersions in doped antiferromagnets
• A generalized Lanczos method for systematic optimization of tensor network states
• Neural Projected Quantum Dynamics: a systematic study
• Variational optimization of the amplitude of neural-network quantum many-body ground states
• Many-body quantum sign structures as non-glassy Ising models
• Second-order optimisation strategies for neural network quantum states
• Boltzmann machines and quantum many-body problems