Efficient classical computation of the neural tangent kernel of quantum neural networks
Preprint
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.}, arXiv:2412.03182], 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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- The Clifford theory of the n-qubit Clifford groupJournal of Mathematical Physics, 2026
- Classically Estimating Observables of Noiseless Quantum CircuitsPhysical Review Letters, 2025
- Quantitative Convergence of Trained Quantum Neural Networks to a Gaussian ProcessAnnales Henri Poincare, 2025
- Efficient Simulation of Parametrized Quantum Circuits under Nonunital Noise through Pauli BackpropagationPhysical Review Letters, 2025
- Expressibility-induced concentration of quantum neural tangent kernelsReports on Progress in Physics, 2024
- Concise Guide to Quantum Machine Learning2023
- A rigorous and robust quantum speed-up in supervised machine learningNature Physics, 2021
- Supervised learning with quantum-enhanced feature spacesNature, 2019
- Supervised Learning with Quantum Computers2018
- User-Friendly Tail Bounds for Sums of Random MatricesFoundations of Computational Mathematics, 2011