Efficiency of neural-network state representations of one-dimensional quantum spin systems

Abstract

Neural-network state representations of quantum many-body systems are attracting great attention and more rigorous quantitative analysis about their expressibility and complexity is warranted. Our analysis of the restricted Boltzmann machine (RBM) state representation of one-dimensional (1D) quantum spin systems provides new insight into their computational complexity. We define a class of long-range-fast-decay (LRFD) RBM states with quantifiable upper bounds on truncation errors and provide numerical evidence for a large class of 1D quantum systems that may be approximated by LRFD RBMs of at most polynomial complexities. These results lead us to conjecture that the ground states of a wide range of quantum systems may be exactly represented by LRFD RBMs or a variant of them, even in cases where other state representations become less efficient. At last, we provide the relations between multiple typical state manifolds. Our work proposes a paradigm for doing complexity analysis for generic long-range RBMs which naturally yields a further classification of this manifold. This paradigm and our characterization of their nonlocal structures may pave the way for understanding the natural measure of complexity for quantum many-body states described by RBMs and are generalizable for higher-dimensional systems and deep neural-network quantum states.

arXiv comment20 pages, 7 figures

References in corpus (42)

• Quantum Machine Learning
• Area laws for the entanglement entropy - a review
• Machine learning and the physical sciences
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum support vector machine for big data classification
• Machine learning phases of matter
• Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
• Machine Learning Unifies the Modelling of Materials and Molecules
• Matrix product states represent ground states faithfully
• Discovering Phase Transitions with Unsupervised Learning
• Maximally-localized Wannier orbitals and the extended Hubbard model for the twisted bilayer graphene
• Quantum Entanglement in Neural Network States
• Quantum Boltzmann Machine
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Machine Learning Topological States
• Entanglement entropy for the long range Ising chain
• Learning Thermodynamics with Boltzmann Machines
• Machine Learning Phases of Strongly Correlated Fermions
• Self-Learning Monte Carlo Method
• Symmetries and many-body excited states with neural-network quantum states
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Equivalence of restricted Boltzmann machines and tensor network states
• Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
• Provably efficient machine learning for quantum many-body problems
• Approximating quantum many-body wave-functions using artificial neural networks
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Machine learning meets quantum physics
• Continuous symmetry breaking and a new universality class in 1D long-range interacting quantum systems
• Optimizing large parameter sets in variational quantum Monte Carlo
• Chiral Topological Phases from Artificial Neural Networks
• Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal
• Critical Phenomena and Kibble-Zurek Scaling in the Long-Range Quantum Ising Chain
• Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
• Neural network representation of tensor network and chiral states
• The learnability scaling of quantum states: restricted Boltzmann machines
• Restricted Boltzmann Machines and Matrix Product States of 1D Translational Invariant Stabilizer Codes
• Entanglement entropy scaling of the XXZ chain
• Implementing Majorana fermions in a cold-atom honeycomb lattice with textured pairings