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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hernandez, Anderson Melchor, Pastorello, Davide, De Palma, Giacomo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913151449038848
author Hernandez, Anderson Melchor
Pastorello, Davide
De Palma, Giacomo
author_facet Hernandez, Anderson Melchor
Pastorello, Davide
De Palma, Giacomo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient classical computation of the neural tangent kernel of quantum neural networks
Hernandez, Anderson Melchor
Pastorello, Davide
De Palma, Giacomo
Quantum Physics
Mathematical Physics
68Q12, 68Q09, 81P68
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.
title Efficient classical computation of the neural tangent kernel of quantum neural networks
topic Quantum Physics
Mathematical Physics
68Q12, 68Q09, 81P68
url https://arxiv.org/abs/2508.04498