Machine Learning Spatial Geometry from Entanglement Features

Abstract

Motivated by the close relations of the renormalization group with both the holography duality and the deep learning, we propose that the holographic geometry can emerge from deep learning the entanglement feature of a quantum many-body state. We develop a concrete algorithm, call the entanglement feature learning (EFL), based on the random tensor network (RTN) model for the tensor network holography. We show that each RTN can be mapped to a Boltzmann machine, trained by the entanglement entropies over all subregions of a given quantum many-body state. The goal is to construct the optimal RTN that best reproduce the entanglement feature. The RTN geometry can then be interpreted as the emergent holographic geometry. We demonstrate the EFL algorithm on 1D free fermion system and observe the emergence of the hyperbolic geometry (AdS${}_3$ spatial geometry) as we tune the fermion system towards the gapless critical point (CFT${}_2$ point).

14 pages, 14 figures

References in corpus (8)

• A class of quantum many-body states that can be efficiently simulated
• Tensor renormalization group approach to 2D classical lattice models
• Criticality, the area law, and the computational power of PEPS
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Holography as deep learning
• Spectral Dynamics of Learning Restricted Boltzmann Machines
• Restricted Boltzmann Machines for the Long Range Ising Models
• Deep Restricted Boltzmann Networks

Cited by in corpus (59)

• Identifying topological order through unsupervised machine learning
• Machine Learning in Nuclear Physics
• Entanglement Transitions from Holographic Random Tensor Networks
• Self-Organized Error Correction in Random Unitary Circuits with Measurement
• Neural Network Renormalization Group
• Quantum Adversarial Machine Learning
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Quantum Neural Network States: A Brief Review of Methods and Applications
• Deep Learning and AdS/CFT
• Classical Shadow Tomography with Locally Scrambled Quantum Dynamics
• Deep Learning Topological Invariants of Band Insulators
• Deep Learning and Holographic QCD
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
• Machine Learning meets Quantum Foundations: A Brief Survey
• AdS/CFT as a deep Boltzmann machine
• Scalable and Flexible Classical Shadow Tomography with Tensor Networks
• Deep Learning and AdS/QCD
• Machine Learning Holographic Mapping by Neural Network Renormalization Group
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Entanglement Features of Random Hamiltonian Dynamics
• Limitations of Linear Cross-Entropy as a Measure for Quantum Advantage
• Method to solve quantum few-body problems with artificial neural networks
• Markovian Entanglement Dynamics under Locally Scrambled Quantum Evolution
• Classical shadows with Pauli-invariant unitary ensembles
• Deep learning black hole metrics from shear viscosity
• Deriving dilaton potential in improved holographic QCD from meson spectrum
• Neural ODE and Holographic QCD
• Deep Quantum Geometry of Matrices
• Deep learning bulk spacetime from boundary optical conductivity
• Random tensor networks with nontrivial links
• Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
• Optimal Renormalization Group Transformation from Information Theory
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture
• Holographic reconstruction of black hole spacetime: machine learning and entanglement entropy
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• Learning the black hole metric from holographic conductivity
• Machine Learning Statistical Gravity from Multi-Region Entanglement Entropy
• Building Bulk Geometry from the Tensor Radon Transform
• RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior
• Differentiable Programming of Isometric Tensor Networks
• Bulk reconstruction of metrics inside black holes by complexity
• Gravitational Duals from Equations of State
• Visualizing Neural Network Developing Perturbation Theory
• Multi-Region Entanglement in Locally Scrambled Quantum Dynamics
• Neural networks in quantum many-body physics: a hands-on tutorial
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE
• Adversarial Machine Learning Phases of Matter
• Efficient Classical Shadow Tomography through Many-body Localization Dynamics
• Holographic entanglement renormalisation of topological order in a quantum liquid
• Spacetime as the optimal generative network of quantum states: a roadmap to QM=GR?
• Deep learning-based holography for T-linear resistivity
• Neural network representation of quantum systems
• The Algebraic Structure Underlying Pole-Skipping Points
• Holographic Classical Shadow Tomography
• Self-regularizing restricted Boltzmann machines
• Building bulk from Wilson loops
• Time from quantum state complexity and the pace of time flow