Quantum Entanglement in Deep Learning Architectures

Abstract

Modern deep learning has enabled unprecedented achievements in various domains. Nonetheless, employment of machine learning for wave function representations is focused on more traditional architectures such as restricted Boltzmann machines (RBMs) and fully-connected neural networks. In this letter, we establish that contemporary deep learning architectures, in the form of deep convolutional and recurrent networks, can efficiently represent highly entangled quantum systems. By constructing Tensor Network equivalents of these architectures, we identify an inherent reuse of information in the network operation as a key trait which distinguishes them from standard Tensor Network based representations, and which enhances their entanglement capacity. Our results show that such architectures can support volume-law entanglement scaling, polynomially more efficiently than presently employed RBMs. Thus, beyond a quantification of the entanglement capacity of leading deep learning architectures, our analysis formally motivates a shift of trending neural-network based wave function representations closer to the state-of-the-art in machine learning.

References in corpus (33)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Machine Translation by Jointly Learning to Align and Translate
• Area laws for the entanglement entropy - a review
• Striving for Simplicity: The All Convolutional Net
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Entanglement renormalization
• Tensor-Entanglement-Filtering Renormalization Approach and Symmetry Protected Topological Order
• A class of quantum many-body states that can be efficiently simulated
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• Solutions of the Two Dimensional Hubbard Model: Benchmarks and Results from a Wide Range of Numerical Algorithms
• Quantum Entanglement in Neural Network States
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Superconductivity and the Pseudogap in the two-dimensional Hubbard model
• Machine Learning Topological States
• Tensor network states and geometry
• Approximating quantum many-body wave-functions using artificial neural networks
• Algorithms for finite Projected Entangled Pair States
• Ground-state phase diagram of the square lattice Hubbard model from density matrix embedding theory
• Constructing exact representations of quantum many-body systems with deep neural networks
• Perfect Sampling with Unitary Tensor Networks
• Solving the Bose-Hubbard model with machine learning
• On the Expressive Power of Deep Learning: A Tensor Analysis
• Gradient optimization of finite projected entangled pair states
• Scaling of entanglement entropy in the (branching) multi-scale entanglement renormalization ansatz
• Categorical Tensor Network States
• Evolution of the Superconductivity Dome in the two dimensional Hubbard Model
• Quantum Max-flow/Min-cut
• On the Expressive Power of Overlapping Architectures of Deep Learning
• Variational Monte Carlo with the Multi-Scale Entanglement Renormalization Ansatz

Cited by in corpus (109)

• Machine learning and the physical sciences
• Quantum Convolutional Neural Networks
• Tensor networks for complex quantum systems
• Recurrent Neural Network Wave Functions
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Fermionic neural-network states for ab-initio electronic structure
• 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
• Constructing neural stationary states for open quantum many-body systems
• A divide-and-conquer algorithm for quantum state preparation
• Quantum Overlapping Tomography
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Neural tensor contractions and the expressive power of deep neural quantum states
• Neural network wave functions and the sign problem
• An end-to-end trainable hybrid classical-quantum classifier
• Efficient quantum state tomography with convolutional neural networks
• Neural network quantum state tomography in a two-qubit experiment
• Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape
• Implicit Regularization in Deep Learning May Not Be Explainable by Norms
• TensorNetwork for Machine Learning
• Supervised Learning with Projected Entangled Pair States
• Extensive deep neural networks for transferring small scale learning to large scale systems
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models
• Probabilistic Simulation of Quantum Circuits with the Transformer
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas
• Advances in Quantum Deep Learning: An Overview
• Deep learning stochastic processes with QCD phase transition
• Configurable sublinear circuits for quantum state preparation
• Machine learning for molecular dynamics with strongly correlated electrons
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Tensor networks for quantum machine learning
• Deep Learning-Enhanced Variational Monte Carlo Method for Quantum Many-Body Physics
• Purifying Deep Boltzmann Machines for Thermal Quantum States
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Scaling of neural-network quantum states for time evolution
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• Unsupervised learning using topological data augmentation
• Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• A perspective on machine learning and data science for strongly correlated electron problems
• Transformer Wave Function for two dimensional frustrated magnets: emergence of a Spin-Liquid Phase in the Shastry-Sutherland Model
• Neural-network quantum states at finite temperature
• Hierarchical quantum circuit representations for neural architecture search
• Reconstructing complex states of a 20-qubit quantum simulator
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Real time evolution with neural-network quantum states
• Opening the black box of deep learning
• Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• Detecting genuine multipartite entanglement via machine learning
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• Entanglement Features of Random Neural Network Quantum States
• Gaussian Process States: A data-driven representation of quantum many-body physics
• Doped stabilizer states in many-body physics and where to find them
• $2^{1296}$ Exponentially Complex Quantum Many-Body Simulation via Scalable Deep Learning Method
• Quantum Gradient Algorithm for General Polynomials
• Conformal Properties of Hyperinvariant Tensor Networks
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• Wave function network description and Kolmogorov complexity of quantum many-body systems
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Neural-network quantum states for a two-leg Bose-Hubbard ladder under magnetic flux
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• Will recent advances in AI result in a paradigm shift in Astrobiology and SETI?
• A Bayesian Inference Framework for Compression and Prediction of Quantum States
• Compact Neural-network Quantum State representations of Jastrow and Stabilizer states
• Explainable Natural Language Processing with Matrix Product States
• Deep Neural Networks as Variational Solutions for Correlated Open Quantum Systems
• Autoregressive neural quantum states of Fermi Hubbard models
• Tensor Network Computations That Capture Strict Variationality, Volume Law Behavior, and the Efficient Representation of Neural Network States
• Measures of distinguishability between stochastic processes
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Approximation Theory of Tree Tensor Networks: Tensorized Univariate Functions -- Part I
• Approximation Theory of Tree Tensor Networks: Tensorized Univariate Functions -- Part II
• Neural-network Quantum States for Spin-1 systems: spin-basis and parameterization effects on compactness of representations
• Interpreting Deep Learning: The Machine Learning Rorschach Test?
• Genuine multipartite entanglement verification with convolutional neural networks
• Residual Matrix Product State for Machine Learning
• Tensor network to learn the wavefunction of data
• Simplicity of mean-field theories in neural quantum states
• Towards quantum gravity with neural networks: Solving the quantum Hamilton constraint of U(1) BF theory
• Efficiency of neural quantum states in light of the quantum geometric tensor
• Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
• Specialising Neural-network Quantum States for the Bose Hubbard Model
• Boltzmann machines and quantum many-body problems
• Tensor networks and efficient descriptions of classical data
• Variational Neural and Tensor Network Approximations of Thermal States
• Coarse-grained spectral projection (CGSP): a deep learning-assisted approach to quantum unitary dynamics
• Entanglement transitions from restricted Boltzmann machines
• Neural Quantum State Study of Fracton Models
• Neural-network quantum state study of the long-range antiferromagnetic Ising chain
• Effective classical correspondence of the Mott transition
• Implicit Regularization in Tensor Factorization
• A Tensor Network Approach to Finite Markov Decision Processes
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Seeding neural network quantum states with tensor network states
• Bound on entanglement in neural quantum states
• Simulating dynamics of the two-dimensional transverse-field Ising model: a comparative study of large-scale classical numerics
• Universal Performance Gap of Neural Quantum States Applied to the Hofstadter-Bose-Hubbard Model
• Kinetic samplers for neural quantum states
• Revealing hidden standard tripartite nonlocality by local filtering
• Tensor Rank bounds for Point Singularities in ${\mathbb{R}}^3$
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning
• Schmidt quantum compressor
• The toric code under antiferromagnetic isotropic Heisenberg interactions
• Magnetic correlations in the $SU(3)$ triangular-lattice $t$-$J$ model at finite doping
• Neural-Network Quantum States for Periodic Systems in Continuous Space