Design principles of deep translationally-symmetric neural quantum states for frustrated magnets
arXiv:2505.03466 · doi:10.1103/ybgv-35jm
Abstract
Deep neural network quantum states have emerged as a leading method for studying the ground states of quantum magnets. Successful architectures exploit translational symmetry, but the root of their effectiveness and differences between architectures remain unclear. Here, we apply the ConvNext architecture, designed to incorporate elements of transformers into convolutional networks, to quantum many-body ground states. We find that it is remarkably similar to the factored vision transformer, which has been employed successfully for several frustrated spin systems, allowing us to relate this architecture to more conventional convolutional networks. Through a series of numerical experiments we design the ConvNext to achieve greatest performance at lowest computational cost, then apply this network to the Shastry-Sutherland and J1-J2 models, obtaining variational energies comparable to the state of the art, providing a blueprint for network design choices of translationally-symmetric architectures to tackle challenging ground-state problems in frustrated magnetism.
arXiv comment15 pages, 8 figures, updated version
References in corpus (49)
- The density-matrix renormalization group in the age of matrix product states
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Quantum Monte Carlo with Directed Loops
- Stochastic series expansion method with operator-loop update
- Exact, Complete, and Universal Continuous-Time Worldline Monte Carlo Approach to the Statistics of Discrete Quantum Systems
- Studying Two Dimensional Systems With the Density Matrix Renormalization Group
- Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
- The Loop Algorithm
- Green Function Monte Carlo with Stochastic Reconfiguration
- Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
- Quantum many-body dynamics in two dimensions with artificial neural networks
- Direct evidence for a gapless spin liquid by frustrating Néel antiferromagnetism
- Critical level crossings and gapless spin liquid in the square-lattice spin- - Heisenberg antiferromagnet
- Lecture Notes of Tensor Network Contractions
- Diagrammatic Monte Carlo
- NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
- Dirac-type nodal spin liquid revealed by refined quantum many-body solver using neural-network wave function, correlation ratio, and level spectroscopy
- Quantum Spin Liquid in Spin 1/2 J1-J2 Heisenberg Model on Square Lattice: Many-Variable Variational Monte Carlo Study Combined with Quantum-Number Projections
- NetKet: A Machine Learning Toolkit for Many-Body Quantum Systems
- Quantum Criticality and Spin Liquid Phase in the Shastry-Sutherland model
- Transformer variational wave functions for frustrated quantum spin systems
- Gapless quantum spin liquid and global phase diagram of the spin-1/2 - square antiferromagnetic Heisenberg model
- Gapless spin liquid and valence-bond solid in the Heisenberg model on the square lattice: insights from singlet and triplet excitations
- Neural network wave functions and the sign problem
- Spectral signatures of fractionalization in the frustrated Heisenberg model on the square lattice
- Empowering deep neural quantum states through efficient optimization
- Quantum-number projection in the path-integral renormalization group method
- Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
- 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
- Optimizing Design Choices for Neural Quantum States
- Unbiasing time-dependent Variational Monte Carlo by projected quantum evolution
- Rise and fall of plaquette order in Shastry-Sutherland magnet revealed by pseudo-fermion functional renormalization group
- Variational Monte Carlo with Large Patched Transformers
- Quantum spin liquid phase in the Shastry-Sutherland model detected by an improved level spectroscopic method
- Investigating Topological Order using Recurrent Neural Networks
- Mapping of attention mechanisms to a generalized Potts model
- Transformer Wave Function for two dimensional frustrated magnets: emergence of a Spin-Liquid Phase in the Shastry-Sutherland Model
- A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions
- Highly resolved spectral functions of two-dimensional systems with neural quantum states
- Exponentially Complex Quantum Many-Body Simulation via Scalable Deep Learning Method
- Neural Projected Quantum Dynamics: a systematic study
- Spin-1/2 kagome Heisenberg antiferromagnet: Machine learning discovery of the spinon pair density wave ground state
- Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
- Fine-tuning Neural Network Quantum States
- Accurate neural quantum states for interacting lattice bosons
- Are queries and keys always relevant? A case study on Transformer wave functions
- Efficiency of neural quantum states in light of the quantum geometric tensor
- Approximately-symmetric neural networks for quantum spin liquids