Efficient classical computation of the neural tangent kernel of quantum neural networks

Abstract

We propose an efficient classical algorithm to estimate the Neural Tangent Kernel (NTK) associated with a broad class of quantum neural networks. These networks consist of arbitrary unitary operators belonging to the Clifford group interleaved with parametric gates given by the time evolution generated by an arbitrary Hamiltonian belonging to the Pauli group. The proposed algorithm leverages a key insight: the average over the distribution of initialization parameters in the NTK definition can be exactly replaced by an average over just four discrete values, chosen such that the corresponding parametric gates are Clifford operations. This reduction enables an efficient classical simulation of the circuit. Combined with recent results establishing the equivalence between wide quantum neural networks and Gaussian processes [Girardi \emph{et al.}, Comm. Math. Phys. 406, 92 (2025); Melchor Hernandez \emph{et al.}, Ann. Henri Poincar{é} (2025)], our method enables efficient computation of the expected output of wide, trained quantum neural networks, and therefore shows that such networks cannot achieve quantum advantage.

References in corpus (17)

• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Improved Simulation of Stabilizer Circuits
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• An introduction to quantum machine learning
• The effect of data encoding on the expressive power of variational quantum machine learning models
• User-friendly tail bounds for sums of random matrices
• A rigorous and robust quantum speed-up in supervised machine learning
• The Clifford group, stabilizer states, and linear and quadratic operations over GF(2)
• Measuring Analytic Gradients of General Quantum Evolution with the Stochastic Parameter Shift Rule
• Does provable absence of barren plateaus imply classical simulability?
• Representation Learning via Quantum Neural Tangent Kernels
• Classically estimating observables of noiseless quantum circuits
• Improved simulation of quantum circuits dominated by free fermionic operations
• Efficient simulation of parametrized quantum circuits under non-unital noise through Pauli backpropagation
• Trained quantum neural networks are Gaussian processes
• Quantitative convergence of trained quantum neural networks to a Gaussian process