Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Abstract

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using time-dependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagation over long time scales has been observed in the square-lattice Heisenberg model using the Restricted Boltzmann machine architecture. However, achieving similar performance in other systems has proven to be more challenging. In this article, we focus on the two-leg Heisenberg ladder driven out of equilibrium by a pulsed excitation as a benchmark system. We demonstrate that unmitigated noise is strongly amplified by the nonlinear equations of motion for the network parameters, which causes numerical instabilities in the time evolution. As a consequence, the achievable accuracy of the simulated dynamics is a result of the interplay between network expressiveness and measures required to remedy these instabilities. We show that stability can be greatly improved by appropriate choice of regularization. This is particularly useful as tuning of the regularization typically imposes no additional computational cost. Inspired by machine learning practice, we propose a validation-set based diagnostic tool to help determining optimal regularization hyperparameters for t-VMC based propagation schemes. For our benchmark, we show that stable and accurate time propagation can be achieved in regimes of sufficiently regularized variational dynamics.

27 pages, 13 figures

References in corpus (14)

• QuTiP 2: A Python framework for the dynamics of open quantum systems
• Quantum fluids of light
• Nonthermal pathways to ultrafast control in quantum materials
• Controlling many-body dynamics with driven quantum scars in Rydberg atom arrays
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Variational neural network ansatz for steady states in open quantum systems
• Constructing neural stationary states for open quantum many-body systems
• Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape
• Investigating ultrafast quantum magnetism with machine learning
• Scaling of neural-network quantum states for time evolution
• Expressive power of complex-valued restricted Boltzmann machines for solving non-stoquastic Hamiltonians
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Supermagnonic propagation in two-dimensional antiferromagnets

Cited by in corpus (15)

• NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
• Optimizing Design Choices for Neural Quantum States
• Scaling of neural-network quantum states for time evolution
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics
• Variational quantum dynamics of two-dimensional rotor models
• jVMC: Versatile and performant variational Monte Carlo leveraging automated differentiation and GPU acceleration
• Spin-1/2 kagome Heisenberg antiferromagnet: Machine learning discovery of the spinon pair density wave ground state
• Cavity engineering of Hubbard $U$ via phonon polaritons
• Impact of conditional modelling for a universal autoregressive quantum state
• Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations
• An Empirical Study of Quantum Dynamics as a Ground State Problem with Neural Quantum States
• Learning topological defects formation with neural networks in a quantum phase transition
• Correcting and extending Trotterized quantum many-body dynamics
• Predicting sampling advantage of stochastic Ising Machines for Quantum Simulations
• Adaptive quantum dynamics with the time-dependent variational Monte Carlo method