Generalization Bounds in Hybrid Quantum-Classical Machine Learning Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Tongyan, Bentellis, Amine, Sakhnenko, Alona, Lorenz, Jeanette Miriam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912908407996416
author Wu, Tongyan
Bentellis, Amine
Sakhnenko, Alona
Lorenz, Jeanette Miriam
author_facet Wu, Tongyan
Bentellis, Amine
Sakhnenko, Alona
Lorenz, Jeanette Miriam
contents Hybrid classical-quantum models aim to harness the strengths of both quantum computing and classical machine learning, but their practical potential remains poorly understood. In this work, we develop a unified mathematical framework for analyzing generalization in hybrid models, offering insight into how these systems learn from data. We establish a novel generalization bound of the form $\tilde{\mathcal O}\left( \tfrac{α^{k}}{\sqrt{N}}\, \big( k^{\tfrac{3}{2}}\sqrt{m n}\;+\;\sqrt{T\log T}\big) \right)$ for $N$ training data points, $T$ trainable quantum gates, $n$ dimensional quantum circuit output, and $k$ bounded linear layers $ \|F_i\|_F \leq α$ where $ i = 1, \dots, k $ and $F_i \in \mathbb{R}^{m \times n} $ interspersed with activation functions. This generalization bound decomposes into quantum and classical contributions, providing a theoretical framework to separate their influence and clarifying their interaction. Alongside the bound, we highlight conceptual limitations of applying classical statistical learning theory in the hybrid setting and suggest promising directions for future theoretical work.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08456
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalization Bounds in Hybrid Quantum-Classical Machine Learning Models
Wu, Tongyan
Bentellis, Amine
Sakhnenko, Alona
Lorenz, Jeanette Miriam
Quantum Physics
Artificial Intelligence
Hybrid classical-quantum models aim to harness the strengths of both quantum computing and classical machine learning, but their practical potential remains poorly understood. In this work, we develop a unified mathematical framework for analyzing generalization in hybrid models, offering insight into how these systems learn from data. We establish a novel generalization bound of the form $\tilde{\mathcal O}\left( \tfrac{α^{k}}{\sqrt{N}}\, \big( k^{\tfrac{3}{2}}\sqrt{m n}\;+\;\sqrt{T\log T}\big) \right)$ for $N$ training data points, $T$ trainable quantum gates, $n$ dimensional quantum circuit output, and $k$ bounded linear layers $ \|F_i\|_F \leq α$ where $ i = 1, \dots, k $ and $F_i \in \mathbb{R}^{m \times n} $ interspersed with activation functions. This generalization bound decomposes into quantum and classical contributions, providing a theoretical framework to separate their influence and clarifying their interaction. Alongside the bound, we highlight conceptual limitations of applying classical statistical learning theory in the hybrid setting and suggest promising directions for future theoretical work.
title Generalization Bounds in Hybrid Quantum-Classical Machine Learning Models
topic Quantum Physics
Artificial Intelligence
url https://arxiv.org/abs/2504.08456