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:2411.19281 · npj Quantum Information

The role of data-induced randomness in quantum machine learning classification tasks

Berta Casas, Xavier Bonet-Monroig, Adrián Pérez-Salinas

Published Jul 28, 2026• 1 citation
arXivHTMLPDF

Abstract

Abstract Quantum machine learning (QML) has surged as a prominent area of research with the objective to go beyond the capabilities of classical machine learning models. A critical aspect of any learning task is the process of data embedding, which directly impacts model performance. Poorly designed data-embedding strategies can significantly impact the success of a learning task. Despite its importance, rigorous analyses of data-embedding effects are limited, leaving many cases without effective assessment methods. In this work, we introduce a metric for binary classification tasks, the class margin , by merging the concepts of average randomness and classification margin. This metric analytically connects data-induced randomness with classification accuracy for a given data-embedding map. We benchmark a range of data-embedding strategies through class margin , demonstrating its ability to identify data-induced randomness that hinders classification performance. We expect this work to provide a new approach to evaluate QML models by their data-embedding processes, addressing gaps left by existing analytical tools

DOI
10.1038/s41534-026-01330-y

Related papers

Primer on Data in Quantum Machine Learning

Aviral Shrivastava, Vinayak Sharma

With the increased interest in Quantum Machine Learning (QML), the integration of classical data into quantum systems presents unique challenges and opportunities. The class "Primer on Data in Quantum Machine Learning" delves into the foundational concepts and advanced techniques of embedding classical data into quantum states, a critical process for enhancing the performance of quantum algorithms. By exploring various quantum embedding methods and understanding their strengths and limitations, participants will gain a comprehensive understanding of the impact quantum embeddings can have on machine learning applications. This lesson will cover the following concepts: Fundamental Concepts of Quantum Machine Learning, Limits of NISQ devices and Computing in the NISQ era, Embeddings for QML, and Practical effects of embeddings. The understanding of these topics should provide a better understanding of the importance and effect of embeddings on the overall performance of QML in the NISQ era.

International Conference on Compilers, Architecture, and Synthesis for Embedded Systems (CASES)•Sep 29, 2024•3 citations

Quantum data encoding: a comparative analysis of classical-to-quantum mapping techniques and their impact on machine learning accuracy

Minati Rath, Hema Date

This study explores the integration of quantum data embedding techniques into classical machine learning (ML) algorithms; to assess performance enhancements and computational implications across a spectrum of models. We explored various classical-to-quantum mapping methods; ranging from basis encoding and angle encoding to amplitude encoding; for encoding classical data. We conducted an extensive empirical study encompassing popular ML algorithms, including Logistic Regression, K-Nearest Neighbors, Support Vector Machines, and ensemble methods like Random Forest, LightGBM, AdaBoost, and CatBoost. Our findings reveal that quantum data embedding contributes to improved classification accuracy and F1 scores, particularly notable in models that inherently benefit from enhanced feature representation. We observed nuanced effects on running time, with low-complexity models exhibiting moderate increases and more computationally intensive models experiencing discernible changes. Notably, ensemble methods demonstrated a favorable balance between performance gains and computational overhead. This study underscores the potential of quantum data embedding to enhance classical ML models and emphasizes the importance of weighing performance improvements against computational costs. Future research may involve refining quantum encoding processes to optimize computational efficiency and explore scalability for real-world applications. Our work contributes to the growing body of knowledge on the intersection of quantum computing and classical machine learning, offering insights for researchers and practitioners seeking to harness the advantages of quantum-inspired techniques in practical scenarios.

arXiv:2311.10375•EPJ Quantum Technology•Oct 25, 2024•184 citations

Influence of Data Dimensionality Reduction Methods on the Effectiveness of Quantum Machine Learning Models

Aakash Ravindra Shinde, Jukka K. Nurminen

Data dimensionality reduction techniques are often utilized in the implementation of Quantum Machine Learning models to address two significant issues: the constraints of NISQ quantum devices, which are characterized by noise and a limited number of qubits, and the challenge of simulating a large number of qubits on classical devices. It also raises concerns over the scalability of these approaches, as dimensionality reduction methods are slow to adapt to large datasets. In this article, we analyze how data reduction methods affect different QML models. We conduct this experiment over several generated datasets, quantum machine algorithms, quantum data encoding methods, and data reduction methods. All these models were evaluated on the performance metrics like accuracy, precision, recall, and F1 score. Our findings have led us to conclude that the usage of data dimensionality reduction methods results in skewed performance metric values, which results in wrongly estimating the actual performance of quantum machine learning models. There are several factors, along with data dimensionality reduction methods, that worsen this problem, such as characteristics of the datasets, classical to quantum information embedding methods, percentage of feature reduction, classical components associated with quantum models, and structure of quantum machine learning models. We consistently observed the difference in the accuracy range of 14% to 48% amongst these models, using data reduction and not using it. Apart from this, our observations have shown that some data reduction methods tend to perform better for some specific data embedding methodologies and ansatz constructions.

quant-pharXiv:2511.03320•IEEE International Conference on Quantum Computing and Engineering (QCE)•Nov 6, 2025•3 citations

A Systematic Review on Quantum Machine Learning Applications in Classification

Ehsan MohammadiSavadkoohi, Niusha Shafiabady, James Vakilian

Classification is a fundamental aspect of leveraging big data for decision-making across domains such as engineering, medicine, economics, and beyond. This systematic review explores the application of quantum machine learning (QML) to address the classification challenges. Despite the rising popularity of QML, challenges persist regarding its practical efficacy and applicability relative to classical methods. This study seeks to classify and analyse the application of QML across diverse domains. Employing a systematic methodology, a total of 23 research articles were chosen after applying rigorous selection criteria between the years 2013 to 2023. At first, 520 research articles were identified, and narrowed down to 296 papers, the abstracts of the papers have been read, 61 full-text papers have been studied, and ultimately 23 papers have been selected for review. A methodological approach was employed, involving the selection of relevant papers from reputable databases, evaluation of these papers, and the subsequent derivation of insights into the performance of QML in practical classification applications. Findings indicate that QML classifiers mostly achieved superior performance compared to conventional methods across accuracy, high-dimensional data management, and computational efficiency. However, challenges remain, including the limitations of noisy quantum hardware and the requirement for hybrid and innovative quantum algorithms. Analysis of current trends reveals significant progress in hybrid quantum-classical computational methods. To conclude, this analysis reveals QML’s revolutionary capabilities while noting its current shortcomings. This study provides a thorough overview for researchers investigating QML’s application to real-world classification problems, and it offers guidelines for future research endeavors.

IEEE Transactions on Artificial Intelligence•May 9, 2025•14 citations

Quantum embeddings for machine learning

Seth Lloyd, Maria Schuld, Aroosa Ijaz +2 more

Quantum classifiers are trainable quantum circuits used as machine learning models. The first part of the circuit implements a quantum feature map that encodes classical inputs into quantum states, embedding the data in a high-dimensional Hilbert space; the second part of the circuit executes a quantum measurement interpreted as the output of the model. Usually, the measurement is trained to distinguish quantum-embedded data. We propose to instead train the first part of the circuit -- the embedding -- with the objective of maximally separating data classes in Hilbert space, a strategy we call quantum metric learning. As a result, the measurement minimizing a linear classification loss is already known and depends on the metric used: for embeddings separating data using the l1 or trace distance, this is the Helstrom measurement, while for the l2 or Hilbert-Schmidt distance, it is a simple overlap measurement. This approach provides a powerful analytic framework for quantum machine learning and eliminates a major component in current models, freeing up more precious resources to best leverage the capabilities of near-term quantum information processors.

arXiv:2001.03622•Jan 10, 2020•515 citations

Implementation and Performance Evaluation of Quantum Machine Learning Algorithms for Binary Classification

Surajudeen Shina Ajibosin, Deniz Çetinkaya

In this work, we studied the use of Quantum Machine Learning (QML) algorithms for binary classification and compared their performance with classical Machine Learning (ML) methods. QML merges principles of Quantum Computing (QC) and ML, offering improved efficiency and potential quantum advantage in data-driven tasks and when solving complex problems. In binary classification, where the goal is to assign data to one of two categories, QML uses quantum algorithms to process large datasets efficiently. Quantum algorithms like Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) exploit quantum parallelism and entanglement to enhance performance over classical methods. This study focuses on two common QML algorithms, Quantum Support Vector Classifier (QSVC) and QNN. We used the Qiskit software and conducted the experiments with three different datasets. Data preprocessing included dimensionality reduction using Principal Component Analysis (PCA) and standardization using scalers. The results showed that quantum algorithms demonstrated competitive performance against their classical counterparts in terms of accuracy, while QSVC performed better than QNN. These findings suggest that QML holds potential for improving computational efficiency in binary classification tasks. This opens the way for more efficient and scalable solutions in complex classification challenges and shows the complementary role of quantum computing.

Software•Nov 28, 2024•25 citations
Abstract Quantum machine learning (QML) has surged as a prominent area of research with the objective to go beyond the capabilities of classical machine learning models. A critical aspect of any learning task is the process of data embedding, which directly impacts model performance. Poorly designed data-embedding strategies can significantly impact the success of a learning task. Despite its importance, rigorous analyses of data-embedding effects are limited, leaving many cases without effective assessment methods. In this work, we introduce a metric for binary classification tasks, the class margin , by merging the concepts of average randomness and classification margin. This metric analytically connects data-induced randomness with classification accuracy for a given data-embedding map. We benchmark a range of data-embedding strategies through class margin , demonstrating its ability to identify data-induced randomness that hinders classification performance. We expect this work to provide a new approach to evaluate QML models by their data-embedding processes, addressing gaps left by existing analytical tools
With the increased interest in Quantum Machine Learning (QML), the integration of classical data into quantum systems presents unique challenges and opportunities. The class "Primer on Data in Quantum Machine Learning" delves into the foundational concepts and advanced techniques of embedding classical data into quantum states, a critical process for enhancing the performance of quantum algorithms. By exploring various quantum embedding methods and understanding their strengths and limitations, participants will gain a comprehensive understanding of the impact quantum embeddings can have on machine learning applications. This lesson will cover the following concepts: Fundamental Concepts of Quantum Machine Learning, Limits of NISQ devices and Computing in the NISQ era, Embeddings for QML, and Practical effects of embeddings. The understanding of these topics should provide a better understanding of the importance and effect of embeddings on the overall performance of QML in the NISQ era.
This study explores the integration of quantum data embedding techniques into classical machine learning (ML) algorithms; to assess performance enhancements and computational implications across a spectrum of models. We explored various classical-to-quantum mapping methods; ranging from basis encoding and angle encoding to amplitude encoding; for encoding classical data. We conducted an extensive empirical study encompassing popular ML algorithms, including Logistic Regression, K-Nearest Neighbors, Support Vector Machines, and ensemble methods like Random Forest, LightGBM, AdaBoost, and CatBoost. Our findings reveal that quantum data embedding contributes to improved classification accuracy and F1 scores, particularly notable in models that inherently benefit from enhanced feature representation. We observed nuanced effects on running time, with low-complexity models exhibiting moderate increases and more computationally intensive models experiencing discernible changes. Notably, ensemble methods demonstrated a favorable balance between performance gains and computational overhead. This study underscores the potential of quantum data embedding to enhance classical ML models and emphasizes the importance of weighing performance improvements against computational costs. Future research may involve refining quantum encoding processes to optimize computational efficiency and explore scalability for real-world applications. Our work contributes to the growing body of knowledge on the intersection of quantum computing and classical machine learning, offering insights for researchers and practitioners seeking to harness the advantages of quantum-inspired techniques in practical scenarios.
Data dimensionality reduction techniques are often utilized in the implementation of Quantum Machine Learning models to address two significant issues: the constraints of NISQ quantum devices, which are characterized by noise and a limited number of qubits, and the challenge of simulating a large number of qubits on classical devices. It also raises concerns over the scalability of these approaches, as dimensionality reduction methods are slow to adapt to large datasets. In this article, we analyze how data reduction methods affect different QML models. We conduct this experiment over several generated datasets, quantum machine algorithms, quantum data encoding methods, and data reduction methods. All these models were evaluated on the performance metrics like accuracy, precision, recall, and F1 score. Our findings have led us to conclude that the usage of data dimensionality reduction methods results in skewed performance metric values, which results in wrongly estimating the actual performance of quantum machine learning models. There are several factors, along with data dimensionality reduction methods, that worsen this problem, such as characteristics of the datasets, classical to quantum information embedding methods, percentage of feature reduction, classical components associated with quantum models, and structure of quantum machine learning models. We consistently observed the difference in the accuracy range of 14% to 48% amongst these models, using data reduction and not using it. Apart from this, our observations have shown that some data reduction methods tend to perform better for some specific data embedding methodologies and ansatz constructions.
Classification is a fundamental aspect of leveraging big data for decision-making across domains such as engineering, medicine, economics, and beyond. This systematic review explores the application of quantum machine learning (QML) to address the classification challenges. Despite the rising popularity of QML, challenges persist regarding its practical efficacy and applicability relative to classical methods. This study seeks to classify and analyse the application of QML across diverse domains. Employing a systematic methodology, a total of 23 research articles were chosen after applying rigorous selection criteria between the years 2013 to 2023. At first, 520 research articles were identified, and narrowed down to 296 papers, the abstracts of the papers have been read, 61 full-text papers have been studied, and ultimately 23 papers have been selected for review. A methodological approach was employed, involving the selection of relevant papers from reputable databases, evaluation of these papers, and the subsequent derivation of insights into the performance of QML in practical classification applications. Findings indicate that QML classifiers mostly achieved superior performance compared to conventional methods across accuracy, high-dimensional data management, and computational efficiency. However, challenges remain, including the limitations of noisy quantum hardware and the requirement for hybrid and innovative quantum algorithms. Analysis of current trends reveals significant progress in hybrid quantum-classical computational methods. To conclude, this analysis reveals QML’s revolutionary capabilities while noting its current shortcomings. This study provides a thorough overview for researchers investigating QML’s application to real-world classification problems, and it offers guidelines for future research endeavors.
Quantum classifiers are trainable quantum circuits used as machine learning models. The first part of the circuit implements a quantum feature map that encodes classical inputs into quantum states, embedding the data in a high-dimensional Hilbert space; the second part of the circuit executes a quantum measurement interpreted as the output of the model. Usually, the measurement is trained to distinguish quantum-embedded data. We propose to instead train the first part of the circuit -- the embedding -- with the objective of maximally separating data classes in Hilbert space, a strategy we call quantum metric learning. As a result, the measurement minimizing a linear classification loss is already known and depends on the metric used: for embeddings separating data using the l1 or trace distance, this is the Helstrom measurement, while for the l2 or Hilbert-Schmidt distance, it is a simple overlap measurement. This approach provides a powerful analytic framework for quantum machine learning and eliminates a major component in current models, freeing up more precious resources to best leverage the capabilities of near-term quantum information processors.
In this work, we studied the use of Quantum Machine Learning (QML) algorithms for binary classification and compared their performance with classical Machine Learning (ML) methods. QML merges principles of Quantum Computing (QC) and ML, offering improved efficiency and potential quantum advantage in data-driven tasks and when solving complex problems. In binary classification, where the goal is to assign data to one of two categories, QML uses quantum algorithms to process large datasets efficiently. Quantum algorithms like Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) exploit quantum parallelism and entanglement to enhance performance over classical methods. This study focuses on two common QML algorithms, Quantum Support Vector Classifier (QSVC) and QNN. We used the Qiskit software and conducted the experiments with three different datasets. Data preprocessing included dimensionality reduction using Principal Component Analysis (PCA) and standardization using scalers. The results showed that quantum algorithms demonstrated competitive performance against their classical counterparts in terms of accuracy, while QSVC performed better than QNN. These findings suggest that QML holds potential for improving computational efficiency in binary classification tasks. This opens the way for more efficient and scalable solutions in complex classification challenges and shows the complementary role of quantum computing.