Guardado en:
Detalles Bibliográficos
Autor principal: Ohno, Hiroshi
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.09771
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909578909712384
author Ohno, Hiroshi
author_facet Ohno, Hiroshi
contents The paper presents a generalization bound for quantum neural networks based on a dynamical Lie algebra. Using covering numbers derived from a dynamical Lie algebra, the Rademacher complexity is derived to calculate the generalization bound. The obtained result indicates that the generalization bound is scaled by O(sqrt(dim(g))), where g denotes a dynamical Lie algebra of generators. Additionally, the upper bound of the number of the trainable parameters in a quantum neural network is presented. Numerical simulations are conducted to confirm the validity of the obtained results.
format Preprint
id arxiv_https___arxiv_org_abs_2504_09771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalization analysis of quantum neural networks using dynamical Lie algebras
Ohno, Hiroshi
Quantum Physics
The paper presents a generalization bound for quantum neural networks based on a dynamical Lie algebra. Using covering numbers derived from a dynamical Lie algebra, the Rademacher complexity is derived to calculate the generalization bound. The obtained result indicates that the generalization bound is scaled by O(sqrt(dim(g))), where g denotes a dynamical Lie algebra of generators. Additionally, the upper bound of the number of the trainable parameters in a quantum neural network is presented. Numerical simulations are conducted to confirm the validity of the obtained results.
title Generalization analysis of quantum neural networks using dynamical Lie algebras
topic Quantum Physics
url https://arxiv.org/abs/2504.09771