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:2509.10141 · Advanced Quantum Technologies

Loss Behavior in Supervised Learning With Entangled States

Alexander E. Mandl, Johanna Barzen, Marvin Bechtold, Frank Leymann, Lavinia Stiliadou

Published Jan 13, 2026• 0 citations
arXivHTMLPDF

Abstract

ABSTRACT Quantum machine learning (QML) aims to leverage the principles of quantum mechanics to speed up the process of solving machine learning problems or improve the quality of solutions. In supervised learning, training samples that are entangled with an auxiliary system were shown to reduce the approximation error of the trained model. However, also the training process is affected by various properties of the supervised learning task, including the model's circuit structure, the used cost function, and noise on the quantum computer. To evaluate the applicability of entanglement in supervised learning, the effect of highly entangled training data on the trainability is investigated in this work. This study shows that for highly expressive models, i.e., models capable of expressing a large number of candidate solutions, the possible improvement of loss function values in constrained neighborhoods during optimization is severely limited when maximally entangled states are used. Furthermore, this finding is experimentally supported by simulating training with Parameterized Quantum Circuits (PQCs). As the expressivity of the PQC increases, this training process becomes more susceptible to loss concentration induced by entangled training data. Lastly, for non‐maximally entangled states, the experiments highlight the fundamental role of entanglement entropy as a predictor for the trainability.

DOI
10.1002/qute.202500754

Related papers

Quantum Machine Learning: The Superhero That Classical Machine Learning Never Knew It Needed

Mithu Roy

Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the principles of quantum mechanics and machine learning to develop algorithms that can potentially outperform classical algorithms in certain tasks. QML leverages the unique properties of quantum systems, such as superposition and entanglement, to process information in ways that are not possible with classical computers. This paper provides a comprehensive overview of QML, including its principles, algorithms, and applications. We focus particularly on supervised learning methods, which involve training a quantum model on labeled data to make predictions on new, unseen data. We discuss the potential of QML to revolutionize various domains, such as finance, chemistry, and materials science, and highlight the challenges associated with the development and implementation of QML algorithms, including the need for more advanced quantum hardware and software. This paper aims to provide a clear understanding of the current state of QML research and its potential impact on future computational capabilities.

International Journal For Multidisciplinary Research•Jun 29, 2024•0 citations

Quantum Machine Learning: The Superhero That Classical Machine Learning Never Knew It Needed

Mahule Roy

Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the principles of quantum mechanics and machine learning to develop algorithms that can potentially outperform classical algorithms in certain tasks. QML leverages the unique properties of quantum systems, such as superposition and entanglement, to process information in ways that are not possible with classical computers. This paper provides a comprehensive overview of QML, including its principles, algorithms, and applications. We focus particularly on supervised learning methods, which involve training a quantum model on labeled data to make predictions on new, unseen data. We discuss the potential of QML to revolutionize various domains, such as finance, chemistry, and materials science, and highlight the challenges associated with the development and implementation of QML algorithms, including the need for more advanced quantum hardware and software. This paper aims to provide a clear understanding of the current state of QML research and its potential impact on future computational capabilities.

•Oct 6, 2024•0 citations

Quantum Machine Learning: Adaptive Loss Functions

Jincheng Zhang

Quantum Machine Learning (QML) is an emerging field that explores the potential of quantum computing to revolutionize various computational tasks. This paper introduces a novel quantum machine learning framework leveraging adaptive loss functions to optimize quantum model parameters, ultimately aiming to improve model performance and reduce computational costs. The core mechanism involves dynamically adjusting the loss weight based on the model's error during training, providing a more sophisticated and adaptable approach compared to traditional, fixed loss functions. We analyze the benefits of this approach across different quantum model architectures and demonstrate its effectiveness through simulations and preliminary experiments. The paper concludes with a discussion of future research directions, focusing on expanding the applicability of this adaptive loss function to diverse quantum machine learning applications.

•Sep 4, 2026•0 citations

Entangled Datasets for Quantum Machine Learning

Louis Schatzki, Andrew Arrasmith, Patrick J. Coles +1 more

High-quality, large-scale datasets have played a crucial role in the development and success of classical machine learning. Quantum Machine Learning (QML) is a new field that aims to use quantum computers for data analysis, with the hope of obtaining a quantum advantage of some sort. While most proposed QML architectures are benchmarked using classical datasets, there is still doubt whether QML on classical datasets will achieve such an advantage. In this work, we argue that one should instead employ quantum datasets composed of quantum states. For this purpose, we introduce the NTangled dataset composed of quantum states with different amounts and types of multipartite entanglement. We first show how a quantum neural network can be trained to generate the states in the NTangled dataset. Then, we use the NTangled dataset to benchmark QML models for supervised learning classification tasks. We also consider an alternative entanglement-based dataset, which is scalable and is composed of states prepared by quantum circuits with different depths. As a byproduct of our results, we introduce a novel method for generating multipartite entangled states, providing a use-case of quantum neural networks for quantum entanglement theory.

arXiv:2109.03400•Sep 8, 2021•86 citations

Exploring the Power of Entangled Data in Quantum Machine Learning

Xinbiao Wang, Yuxuan DU, Zhuozhuo Tu +3 more

Quantum entanglement is a key resource for achieving superiority of quantum computing.Currently, scientists are extensively focusing on how to integrate quantum entanglement into various components of quantum machine learning (QML) models, aiming to surpass the performance of traditional machine learning models.Notable successes include the use of entangled measurements [1][2][3] and entangled channels [4] , which have been shown to reduce query complexity or improve the prediction precision for specified QML tasks.Quantum entangled data, capable of encoding more information compared to classical data of the same size, is recognized for its potential to achieve quantum advantages.Nevertheless, the impact of the entanglement degree in quantum data on model performance remains a challenging and unresolved research question.Recently, Wang and collaborators [5] (Nat Commun 2024, 15, 3716) rigorously analyzed the impact of the entanglement degree of quantum data, the number and type of measurements, and the size of training dataset on the prediction error of QML models by establishing the quantum no-free-lunch (NFL) theorem.They consider tasks of quantum dynamics learning with entangled data, which is fundamental to many advanced quantum algorithms, as illustrated in Fig. 1.While conventional understanding suggests that entanglement mainly confers benefits to QML in terms of sample complexity [6,7] , this study demonstrates that the effect of the degree of entanglement on prediction error exhibits a dual effect, that is, whether quantum entanglement improves performance depends on the number of measurements allowed.With a sufficient number of measurements, increasing the entanglement degree in quan-

Wuhan University Journal of Natural Sciences•Jun 1, 2024•2 citations

QSEA: Quantum Self‐Supervised Learning with Entanglement Augmentation

Lingxiao Li, XiaoHui Ni, Jing Li +2 more

ABSTRACT As an unsupervised feature representation paradigm, Self‐Supervised Learning (SSL) uses the intrinsic structure of data to extract meaningful features without relying on manual annotation. Despite the success of SSL, there are still problems, such as limited model capacity or insufficient representation ability. Quantum SSL has become a promising alternative because it can exploit quantum states to enhance expression ability and learning efficiency. This letter proposes a Quantum SSL with entanglement augmentation method (QSEA). Different from existing Quantum SSLs, QSEA introduces an entanglement‐based sample generation scheme and a fidelity‐driven quantum loss function. Specifically, QSEA constructs augmented samples by entangling an auxiliary qubit with the raw state and applying parameterized unitary transformations. The loss function is defined using quantum fidelity, quantifying similarity between quantum representations and effectively capturing sample relations. Experimental results show that QSEA outperforms existing quantum self‐supervised methods on multiple benchmarks and shows stronger stability in decorrelation noise environments. This framework lays the theoretical and practical foundation for quantum learning systems and advances the development of quantum machine learning in SSL.

arXiv:2506.10306•Advanced Quantum Technologies•Nov 28, 2025•0 citations
ABSTRACT Quantum machine learning (QML) aims to leverage the principles of quantum mechanics to speed up the process of solving machine learning problems or improve the quality of solutions. In supervised learning, training samples that are entangled with an auxiliary system were shown to reduce the approximation error of the trained model. However, also the training process is affected by various properties of the supervised learning task, including the model's circuit structure, the used cost function, and noise on the quantum computer. To evaluate the applicability of entanglement in supervised learning, the effect of highly entangled training data on the trainability is investigated in this work. This study shows that for highly expressive models, i.e., models capable of expressing a large number of candidate solutions, the possible improvement of loss function values in constrained neighborhoods during optimization is severely limited when maximally entangled states are used. Furthermore, this finding is experimentally supported by simulating training with Parameterized Quantum Circuits (PQCs). As the expressivity of the PQC increases, this training process becomes more susceptible to loss concentration induced by entangled training data. Lastly, for non‐maximally entangled states, the experiments highlight the fundamental role of entanglement entropy as a predictor for the trainability.
Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the principles of quantum mechanics and machine learning to develop algorithms that can potentially outperform classical algorithms in certain tasks. QML leverages the unique properties of quantum systems, such as superposition and entanglement, to process information in ways that are not possible with classical computers. This paper provides a comprehensive overview of QML, including its principles, algorithms, and applications. We focus particularly on supervised learning methods, which involve training a quantum model on labeled data to make predictions on new, unseen data. We discuss the potential of QML to revolutionize various domains, such as finance, chemistry, and materials science, and highlight the challenges associated with the development and implementation of QML algorithms, including the need for more advanced quantum hardware and software. This paper aims to provide a clear understanding of the current state of QML research and its potential impact on future computational capabilities.
Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the principles of quantum mechanics and machine learning to develop algorithms that can potentially outperform classical algorithms in certain tasks. QML leverages the unique properties of quantum systems, such as superposition and entanglement, to process information in ways that are not possible with classical computers. This paper provides a comprehensive overview of QML, including its principles, algorithms, and applications. We focus particularly on supervised learning methods, which involve training a quantum model on labeled data to make predictions on new, unseen data. We discuss the potential of QML to revolutionize various domains, such as finance, chemistry, and materials science, and highlight the challenges associated with the development and implementation of QML algorithms, including the need for more advanced quantum hardware and software. This paper aims to provide a clear understanding of the current state of QML research and its potential impact on future computational capabilities.
Quantum Machine Learning (QML) is an emerging field that explores the potential of quantum computing to revolutionize various computational tasks. This paper introduces a novel quantum machine learning framework leveraging adaptive loss functions to optimize quantum model parameters, ultimately aiming to improve model performance and reduce computational costs. The core mechanism involves dynamically adjusting the loss weight based on the model's error during training, providing a more sophisticated and adaptable approach compared to traditional, fixed loss functions. We analyze the benefits of this approach across different quantum model architectures and demonstrate its effectiveness through simulations and preliminary experiments. The paper concludes with a discussion of future research directions, focusing on expanding the applicability of this adaptive loss function to diverse quantum machine learning applications.
High-quality, large-scale datasets have played a crucial role in the development and success of classical machine learning. Quantum Machine Learning (QML) is a new field that aims to use quantum computers for data analysis, with the hope of obtaining a quantum advantage of some sort. While most proposed QML architectures are benchmarked using classical datasets, there is still doubt whether QML on classical datasets will achieve such an advantage. In this work, we argue that one should instead employ quantum datasets composed of quantum states. For this purpose, we introduce the NTangled dataset composed of quantum states with different amounts and types of multipartite entanglement. We first show how a quantum neural network can be trained to generate the states in the NTangled dataset. Then, we use the NTangled dataset to benchmark QML models for supervised learning classification tasks. We also consider an alternative entanglement-based dataset, which is scalable and is composed of states prepared by quantum circuits with different depths. As a byproduct of our results, we introduce a novel method for generating multipartite entangled states, providing a use-case of quantum neural networks for quantum entanglement theory.
Quantum entanglement is a key resource for achieving superiority of quantum computing.Currently, scientists are extensively focusing on how to integrate quantum entanglement into various components of quantum machine learning (QML) models, aiming to surpass the performance of traditional machine learning models.Notable successes include the use of entangled measurements [1][2][3] and entangled channels [4] , which have been shown to reduce query complexity or improve the prediction precision for specified QML tasks.Quantum entangled data, capable of encoding more information compared to classical data of the same size, is recognized for its potential to achieve quantum advantages.Nevertheless, the impact of the entanglement degree in quantum data on model performance remains a challenging and unresolved research question.Recently, Wang and collaborators [5] (Nat Commun 2024, 15, 3716) rigorously analyzed the impact of the entanglement degree of quantum data, the number and type of measurements, and the size of training dataset on the prediction error of QML models by establishing the quantum no-free-lunch (NFL) theorem.They consider tasks of quantum dynamics learning with entangled data, which is fundamental to many advanced quantum algorithms, as illustrated in Fig. 1.While conventional understanding suggests that entanglement mainly confers benefits to QML in terms of sample complexity [6,7] , this study demonstrates that the effect of the degree of entanglement on prediction error exhibits a dual effect, that is, whether quantum entanglement improves performance depends on the number of measurements allowed.With a sufficient number of measurements, increasing the entanglement degree in quan-
ABSTRACT As an unsupervised feature representation paradigm, Self‐Supervised Learning (SSL) uses the intrinsic structure of data to extract meaningful features without relying on manual annotation. Despite the success of SSL, there are still problems, such as limited model capacity or insufficient representation ability. Quantum SSL has become a promising alternative because it can exploit quantum states to enhance expression ability and learning efficiency. This letter proposes a Quantum SSL with entanglement augmentation method (QSEA). Different from existing Quantum SSLs, QSEA introduces an entanglement‐based sample generation scheme and a fidelity‐driven quantum loss function. Specifically, QSEA constructs augmented samples by entangling an auxiliary qubit with the raw state and applying parameterized unitary transformations. The loss function is defined using quantum fidelity, quantifying similarity between quantum representations and effectively capturing sample relations. Experimental results show that QSEA outperforms existing quantum self‐supervised methods on multiple benchmarks and shows stronger stability in decorrelation noise environments. This framework lays the theoretical and practical foundation for quantum learning systems and advances the development of quantum machine learning in SSL.