LCQNN: Linear Combination of Quantum Neural Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yao, Hongshun, Liu, Xia, Jing, Mingrui, Li, Guangxi, Wang, Xin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913973998190592
author Yao, Hongshun
Liu, Xia
Jing, Mingrui
Li, Guangxi
Wang, Xin
author_facet Yao, Hongshun
Liu, Xia
Jing, Mingrui
Li, Guangxi
Wang, Xin
contents Quantum neural networks combine quantum computing with advanced data-driven methods, offering promising applications in quantum machine learning. However, the optimal paradigm for balancing trainability and expressivity in QNNs remains an open question. To address this, we introduce the Linear Combination of Quantum Neural Networks (LCQNN) framework, which uses the linear combination of unitaries concept to create a tunable design that mitigates vanishing gradients without incurring excessive classical simulability. We show how specific structural choices, such as adopting $k$-local control unitaries or restricting the model to certain group-theoretic subspaces, prevent gradients from collapsing while maintaining sufficient expressivity for complex tasks. We further employ the LCQNN model to handle supervised learning tasks, demonstrating its effectiveness on real datasets. In group action scenarios, we show that by exploiting symmetry and excluding exponentially large irreducible subspaces, the model circumvents barren plateaus. Overall, LCQNN provides a novel framework for focusing quantum resources into architectures that are practically trainable yet expressive enough to tackle challenging machine learning applications.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02832
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LCQNN: Linear Combination of Quantum Neural Networks
Yao, Hongshun
Liu, Xia
Jing, Mingrui
Li, Guangxi
Wang, Xin
Quantum Physics
Quantum neural networks combine quantum computing with advanced data-driven methods, offering promising applications in quantum machine learning. However, the optimal paradigm for balancing trainability and expressivity in QNNs remains an open question. To address this, we introduce the Linear Combination of Quantum Neural Networks (LCQNN) framework, which uses the linear combination of unitaries concept to create a tunable design that mitigates vanishing gradients without incurring excessive classical simulability. We show how specific structural choices, such as adopting $k$-local control unitaries or restricting the model to certain group-theoretic subspaces, prevent gradients from collapsing while maintaining sufficient expressivity for complex tasks. We further employ the LCQNN model to handle supervised learning tasks, demonstrating its effectiveness on real datasets. In group action scenarios, we show that by exploiting symmetry and excluding exponentially large irreducible subspaces, the model circumvents barren plateaus. Overall, LCQNN provides a novel framework for focusing quantum resources into architectures that are practically trainable yet expressive enough to tackle challenging machine learning applications.
title LCQNN: Linear Combination of Quantum Neural Networks
topic Quantum Physics
url https://arxiv.org/abs/2507.02832