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

TL;DR

This paper introduces a classical algorithm to efficiently compute the Neural Tangent Kernel of certain quantum neural networks, demonstrating these networks cannot surpass classical methods in performance.

Contribution

The authors develop a novel classical simulation technique for quantum neural networks using Clifford group properties, enabling efficient NTK computation.

Findings

Efficient classical estimation of NTK for broad quantum neural network classes.

Shows wide quantum neural networks cannot achieve quantum advantage.

Leverages Clifford group properties for simulation efficiency.

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{\'e} (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.