Efficiency of neural quantum states in light of the quantum geometric tensor
arXiv:2402.01565 · doi:10.1038/s42005-025-02005-4
Abstract
Neural quantum state (NQS) ansätze have shown promise in variational Monte Carlo algorithms by their theoretical capability of representing any quantum state. However, the reason behind the practical improvement in their performance with an increase in the number of parameters is not fully understood. In this work, we systematically study the efficiency of a shallow neural network to represent the ground states in different phases of the spin-1 bilinear-biquadratic chain, as the number of parameters increases. We train our ansatz by a supervised learning procedure, minimizing the infidelity w.r.t. the exact ground state. We observe that the accuracy of our ansatz improves with the network width in most cases, and eventually saturates. We demonstrate that this can be explained by looking at the spectrum of the quantum geometric tensor (QGT), particularly its rank. By introducing an appropriate indicator, we establish that the QGT rank provides a useful diagnostic for the practical representation power of an NQS ansatz.
References in corpus (30)
- The density-matrix renormalization group in the age of matrix product states
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- An Area Law for One Dimensional Quantum Systems
- Quantum Natural Gradient
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
- Geometric Quantum Mechanics
- Efficient Representation of Quantum Many-body States with Deep Neural Networks
- Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
- Scaling of entanglement support for Matrix Product States
- Green Function Monte Carlo with Stochastic Reconfiguration
- Wave function optimization in the variational Monte Carlo method
- 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
- Variational neural network ansatz for steady states in open quantum systems
- Quantum Entanglement in Deep Learning Architectures
- Spin nematic correlations in bilinear-biquadratic S=1 spin chains
- Spin nematics in the bilinear-biquadratic S=1 spin chain
- Theory of overparametrization in quantum neural networks
- Physical Meaning of the Affleck-Kennedy-Lieb-Tasaki S=1 Quantum spin chain
- NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
- Classical and Quantum Fisher Information in the Geometrical Formulation of Quantum Mechanics
- NetKet: A Machine Learning Toolkit for Many-Body Quantum Systems
- An extended massless phase and the Haldane phase in a spin-1 isotropic antiferromagnetic chain
- Fermionic Wave Functions from Neural-Network Constrained Hidden States
- Transformer variational wave functions for frustrated quantum spin systems
- Empowering deep neural quantum states through efficient optimization
- Unbiasing time-dependent Variational Monte Carlo by projected quantum evolution
- Variational quantum dynamics of two-dimensional rotor models
- Low-energy physics of isotropic spin-1 chains in the critical and Haldane phases
- Neural-network Quantum States for Spin-1 systems: spin-basis and parameterization effects on compactness of representations
Cited by in corpus (6)
- Neural Projected Quantum Dynamics: a systematic study
- Design principles of deep translationally-symmetric neural quantum states for frustrated magnets
- Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
- Basis dependence of Neural Quantum States for the Transverse Field Ising Model
- Hybrid between biologically and quantum-inspired many-body states
- Adaptive quantum dynamics with the time-dependent variational Monte Carlo method