Quantum-enhanced neural networks in the neural tangent kernel framework

Abstract

Recently, quantum neural networks or quantum-classical neural networks (qcNN) have been actively studied, as a possible alternative to the conventional classical neural network (cNN), but their practical and theoretically-guaranteed performance is still to be investigated. In contrast, cNNs and especially deep cNNs, have acquired several solid theoretical basis; one of those basis is the neural tangent kernel (NTK) theory, which can successfully explain the mechanism of various desirable properties of cNNs, particularly the global convergence in the training process. In this paper, we study a class of qcNN composed of a quantum data-encoder followed by a cNN. The quantum part is randomly initialized according to unitary 2-designs, which is an effective feature extraction process for quantum states, and the classical part is also randomly initialized according to Gaussian distributions; then, in the NTK regime where the number of nodes of the cNN becomes infinitely large, the output of the entire qcNN becomes a nonlinear function of the so-called projected quantum kernel. That is, the NTK theory is used to construct an effective quantum kernel, which is in general nontrivial to design. Moreover, NTK defined for the qcNN is identical to the covariance matrix of a Gaussian process, which allows us to analytically study the learning process. These properties are investigated in thorough numerical experiments; particularly, we demonstrate that the qcNN shows a clear advantage over fully classical NNs and qNNs for the problem of learning the quantum data-generating process.

arXiv comment34 pages, 12 figures

References in corpus (48)

• Adam: A Method for Stochastic Optimization
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Circuit-centric quantum classifiers
• The power of quantum neural networks
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Efficient Learning for Deep Quantum Neural Networks
• Exact and Approximate Unitary 2-Designs: Constructions and Applications
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Deep Neural Networks as Gaussian Processes
• Quantum advantage in learning from experiments
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum autoencoders for efficient compression of quantum data
• Transfer learning in hybrid classical-quantum neural networks
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Layerwise learning for quantum neural networks
• Detection of Symmetry Protected Topological Phases in 1D
• Qulacs: a fast and versatile quantum circuit simulator for research purpose
• The Expressive Power of Parameterized Quantum Circuits
• Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
• Quantum generalisation of feedforward neural networks
• Provably efficient machine learning for quantum many-body problems
• Is quantum advantage the right goal for quantum machine learning?
• Supervised quantum machine learning models are kernel methods
• Entanglement Devised Barren Plateau Mitigation
• Barren plateaus preclude learning scramblers
• Avoiding barren plateaus using classical shadows
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• Quantum neural network
• Representation Learning via Quantum Neural Tangent Kernels
• Symbolic integration with respect to the Haar measure on the unitary group
• A Universal Training Algorithm for Quantum Deep Learning
• Analytic theory for the dynamics of wide quantum neural networks
• Hybrid quantum-classical neural network for calculating ground state energies of molecules
• Quantum Phase Recognition via Quantum Kernel Methods
• Quantum semi-supervised generative adversarial network for enhanced data classification
• Representation Theory for Geometric Quantum Machine Learning
• Quantum kernels to learn the phases of quantum matter
• Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems
• Symmetric Pruning in Quantum Neural Networks
• Quantum Fisher kernel for mitigating the vanishing similarity issue

Cited by in corpus (1)

• Quantitative convergence of trained quantum neural networks to a Gaussian process