Trained quantum neural networks are Gaussian processes

Abstract

We study quantum neural networks made by parametric one-qubit gates and fixed two-qubit gates in the limit of infinite width, where the generated function is the expectation value of the sum of single-qubit observables over all the qubits. First, we prove that the probability distribution of the function generated by the untrained network with randomly initialized parameters converges in distribution to a Gaussian process whenever each measured qubit is correlated only with few other measured qubits. Then, we analytically characterize the training of the network via gradient descent with square loss on supervised learning problems. We prove that, as long as the network is not affected by barren plateaus, the trained network can perfectly fit the training set and that the probability distribution of the function generated after training still converges in distribution to a Gaussian process. Finally, we consider the statistical noise of the measurement at the output of the network and prove that a polynomial number of measurements is sufficient for all the previous results to hold and that the network can always be trained in polynomial time.

116 pages

References in corpus (17)

• Deep Learning in Neural Networks: An Overview
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• The effect of data encoding on the expressive power of variational quantum machine learning models
• A rigorous and robust quantum speed-up in supervised machine learning
• Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Theory of overparametrization in quantum neural networks
• The Quantum Wasserstein Distance of Order 1
• Representation Learning via Quantum Neural Tangent Kernels
• Learning quantum data with the quantum Earth Mover's distance
• Analytic theory for the dynamics of wide quantum neural networks
• Moderate deviations via cumulants

Cited by in corpus (3)

• Quantitative convergence of trained quantum neural networks to a Gaussian process
• Efficient classical computation of the neural tangent kernel of quantum neural networks
• Mean-field limit from general mixtures of experts to quantum neural networks