Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2506.08455 · Quantum science and technology

The Interplay of Robustness and Generalization in Quantum Machine Learning

Julian Berberich, Tobias Fellner, Christian Holm

Published Jan 1, 2026• 0 citations
arXivHTMLPDF
DOI
10.1007/978-3-032-11153-1_9

Related papers

Adversarial Robustness in Quantum Machine Learning

Nicola Franco, Aman Saxena, Tom Wollschläger +3 more

Quantum science and technology•Jan 1, 2026•0 citations

Quantum Machine Learning: Adaptive Noise Injection for Enhanced Generalization and Robustness

Jincheng Zhang

Quantum Machine Learning (QML) is a rapidly evolving field that explores the potential of quantum algorithms to revolutionize machine learning tasks. A critical challenge in QML is the need for robust models that can generalize well to unseen data and exhibit resilience to perturbations. This paper introduces a novel QML model, Quantum Machine Learning with Adaptive Noise Injection (QML-ALI), designed to address this challenge by incorporating a dynamic noise injection mechanism. We propose a mechanism that intelligently adjusts the amount of noise injected during training based on the observed training dynamics, ultimately promoting improved generalization and robustness. This approach contrasts with traditional methods that rely on fixed noise levels, offering a more adaptable and potentially superior solution. The core claims and mechanisms are detailed, and the paper concludes with a discussion of the potential implications and future directions of this research.

•Sep 6, 2026•0 citations

Self-Adaptive Quantum Machine Learning: Topological Structure Learning

Jincheng Zhang

This paper introduces a novel self-adaptive quantum machine learning framework based on quantum potential fields and topological structures. We propose a method for learning complex machine learning models by dynamically optimizing the quantum system's parameters through the interplay of these structural elements. The framework aims to enhance model performance and generalization capabilities by leveraging the unique properties of quantum mechanics. This work addresses the challenges of training deep, complex models, particularly in scenarios requiring high fidelity and robustness. The core mechanism focuses on creating and manipulating quantum states to iteratively refine the model's parameters, ultimately leading to improved results. We demonstrate the effectiveness of this approach through theoretical analysis and preliminary experimental results on a subset of benchmark datasets.

•Sep 4, 2026•0 citations

Noise, Errors, and Adversarial Robustness in Quantum Machine Learning

Alex Jin, Manas Mukherjee

Quantum science and technology•Jan 1, 2026•0 citations

Machine Learning in a Quantum World

Esma Aı̈meur, Gilles Brassard A, Sébastien Gambs

Lecture notes in computer science•Jan 1, 2006•160 citations

Quantum Neural Networks under Depolarization Noise: Exploring White-Box Attacks and Defenses

David Winderl, Nicola Franco, Jeanette Miriam Lorenz

Leveraging the unique properties of quantum mechanics, Quantum Machine Learning (QML) promises computational breakthroughs and enriched perspectives where traditional systems reach their boundaries. However, similarly to classical machine learning, QML is not immune to adversarial attacks. Quantum adversarial machine learning has become instrumental in highlighting the weak points of QML models when faced with adversarial crafted feature vectors. Diving deep into this domain, our exploration shines light on the interplay between depolarization noise and adversarial robustness. While previous results enhanced robustness from adversarial threats through depolarization noise, our findings paint a different picture. Interestingly, adding depolarization noise discontinued the effect of providing further robustness for a multi-class classification scenario. Consolidating our findings, we conducted experiments with a multi-class classifier adversarially trained on gate-based quantum simulators, further elucidating this unexpected behavior.

arXiv:2311.17458•Nov 29, 2023•2 citations
Quantum Machine Learning (QML) is a rapidly evolving field that explores the potential of quantum algorithms to revolutionize machine learning tasks. A critical challenge in QML is the need for robust models that can generalize well to unseen data and exhibit resilience to perturbations. This paper introduces a novel QML model, Quantum Machine Learning with Adaptive Noise Injection (QML-ALI), designed to address this challenge by incorporating a dynamic noise injection mechanism. We propose a mechanism that intelligently adjusts the amount of noise injected during training based on the observed training dynamics, ultimately promoting improved generalization and robustness. This approach contrasts with traditional methods that rely on fixed noise levels, offering a more adaptable and potentially superior solution. The core claims and mechanisms are detailed, and the paper concludes with a discussion of the potential implications and future directions of this research.
This paper introduces a novel self-adaptive quantum machine learning framework based on quantum potential fields and topological structures. We propose a method for learning complex machine learning models by dynamically optimizing the quantum system's parameters through the interplay of these structural elements. The framework aims to enhance model performance and generalization capabilities by leveraging the unique properties of quantum mechanics. This work addresses the challenges of training deep, complex models, particularly in scenarios requiring high fidelity and robustness. The core mechanism focuses on creating and manipulating quantum states to iteratively refine the model's parameters, ultimately leading to improved results. We demonstrate the effectiveness of this approach through theoretical analysis and preliminary experimental results on a subset of benchmark datasets.
Leveraging the unique properties of quantum mechanics, Quantum Machine Learning (QML) promises computational breakthroughs and enriched perspectives where traditional systems reach their boundaries. However, similarly to classical machine learning, QML is not immune to adversarial attacks. Quantum adversarial machine learning has become instrumental in highlighting the weak points of QML models when faced with adversarial crafted feature vectors. Diving deep into this domain, our exploration shines light on the interplay between depolarization noise and adversarial robustness. While previous results enhanced robustness from adversarial threats through depolarization noise, our findings paint a different picture. Interestingly, adding depolarization noise discontinued the effect of providing further robustness for a multi-class classification scenario. Consolidating our findings, we conducted experiments with a multi-class classifier adversarially trained on gate-based quantum simulators, further elucidating this unexpected behavior.