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:2303.11028 · Quantum Information Processing

MAQA: a quantum framework for supervised learning

Antonio Macaluso, Matthias Klusch, Stefano Lodi, Claudio Sartori

Published Mar 22, 2023• 8 citations
arXivHTMLPDF

Abstract

Abstract Quantum machine learning has the potential to improve traditional machine learning methods and overcome some of the main limitations imposed by the classical computing paradigm. However, the practical advantages of using quantum resources to solve pattern recognition tasks are still to be demonstrated. This work proposes a universal, efficient framework that can reproduce the output of a plethora of classical supervised machine learning algorithms exploiting quantum computation’s advantages. The proposed framework is namedMultiple Aggregator Quantum Algorithm(MAQA) due to its capability to combine multiple and diverse functions to solve typical supervised learning problems. In its general formulation, MAQA can be potentially adopted as the quantum counterpart of all those models falling into the scheme of aggregation of multiple functions, such as ensemble algorithms and neural networks. From a computational point of view, the proposed framework allows generating an exponentially large number of different transformations of the input at the cost of increasing the depth of the corresponding quantum circuit linearly. Thus, MAQA produces a model with substantial descriptive power to broaden the horizon of possible applications of quantum machine learning with a computational advantage over classical methods. As a second meaningful addition, we discuss the adoption of the proposed framework as hybrid quantum–classical and fault-tolerant quantum algorithm.

DOI
10.1007/s11128-023-03901-w

Related papers

A Novel Framework for Quantum Machine Learning

Antonio Macaluso

Quantum computation is an emerging computing paradigm with the potential to revolutionise the world of information technology. It leverages the laws of quantum mechanics to endow quantum machines with tremendous computing power, thus enabling the solution of problems impossible to address with classical devices. For this reason, the field is attracting ever-increasing attention from both academic and private sectors, and its full potential is still to be understood. This dissertation investigates how classical machine learning can benefit from quantum computing and provides several contributions to the emerging field of Quantum Machine Learning. \nThe idea is to provide a universal and efficient framework that can reproduce the output of a plethora of classical machine learning algorithms exploiting quantum computation’s advantages. The proposed framework is named Multiple Aggregator Quantum Algorithm (MAQA) due to its capability to combine multiple functions to solve typical supervised learning tasks. Thanks to this property, in its general formulation MAQA can be potentially adopted as the quantum counterpart of all those models falling into the scheme of aggregation of multiple functions. The theoretical design of the quantum algorithm and the corresponding circuit’s implementation are presented. As a second meaningful addition, two practical applications are illustrated: the quantum version of ensemble methods and neural networks. \nThe final contribution addresses the restriction to linear operations imposed by quantum mechanics. The idea is to exploit a quantum transposition of classical Splines to approximate non-linear functions, thus overcoming this limitation and introducing significant advantages in terms of computational complexity theory.

•Jan 1, 2021•1 citation

Quantum machine learning for supervised pattern recognition.

Maria Schuld

Humans are experts at recognising patterns in past experience and applying them to new tasks. \nFor example, after seeing pictures of a face we can usually tell if another image contains the \nsame person or not. Machine learning is a research discipline at the intersection of computer \nscience, statistics and mathematics that investigates how pattern recognition can be performed \nby machines and for large amounts of data. Since a few years machine learning has come \ninto the focus of quantum computing in which information processing based on the laws of \nquantum theory is explored. Although large scale quantum computers are still in the first stages \nof development, their theoretical description is well-understood and can be used to formulate \n`quantum software' or `quantum algorithms' for pattern recognition. Researchers can therefore \nanalyse the impact quantum computers may have on intelligent data mining. This approach is \npart of the emerging research discipline of quantum machine learning that harvests synergies \nbetween quantum computing and machine learning. \nThe research objective of this thesis is to understand how we can solve a slightly more specific \nproblem called supervised pattern recognition based on the language that has been developed \nfor universal quantum computers. The contribution it makes is twofold: First, it presents a \nmethodology that understands quantum machine learning as the combination of data encoding into \nquantum systems and quantum optimisation. Second, it proposes several quantum algorithms for \nsupervised pattern recognition. These include algorithms for convex and non-convex optimisation, \nimplementations of distance-based methods through quantum interference, and the preparation of \nquantum states from which solutions can be derived via sampling. Amongst the machine learning \nmethods considered are least-squares linear regression, gradient descent and Newton's method, \nk-nearest neighbour, neural networks as well as ensemble methods. Together with the growing \nbody of literature, this thesis demonstrates that quantum computing offers a number of interesting \ntools for machine learning applications, and has the potential to create new models of how to learn \nfrom data.

•Jan 1, 2017•5 citations

Quantum Machine Learning: Harnessing Quantum Algorithms for Supervised and Unsupervised Learning

Mohit Mittal

Quantum machine learning (QML) provides a transformative approach to data analysis by integrating the principles of quantum computing with classical machine learning methods. With the exponential growth of data and the increasing complexity of computational tasks, quantum algorithms offer tremendous advantages in terms of processing speed, memory efficiency, and the ability to resolve issues intractable for classical systems. In this work, the use of QML techniques for both supervised and unsupervised learning problems is explored. Quantum-enhanced models such Quantum Support Vector Machines (QSVMs) and Quantum Neural Networks (QNNs) show outstanding performance in classification and regression tasks by using quantum kernels and entanglement in supervised learning. Moreover, hybrid quantum-classical solutions offer useful implementations on noisy intermediate-scale quantum (NISQ) devices, hence bridging the gap between present quantum technology and practical uses. By means of comparative analysis, this paper emphasizes the possible benefits and drawbacks of QML, thereby providing understanding of its future importance in sectors including material science, finance, and healthcare. In the end, QML opens the path for a new era of intelligent data processing and solves until unthinkable difficult challenges.

International Journal of Innovative Research in Science Engineering and Technology•Sep 30, 2022•3 citations

A Hybrid Quantum Classical Framework for Enhanced Machine Learning Performance on High Dimensional Data

Nnaemeka Kingsley Ugwumba

Abstract This research presents a comprehensive hybrid quantum classical machine learning framework designed to overcome the computational limitations of classical algorithms when processing high dimensional data. The study integrates parameterized quantum circuits within classical neural network architectures and demonstrates their application across optimization tasks and supervised learning problems. The framework was evaluated on combinatorial optimization benchmarks including Max Cut and Job Shop Scheduling problems alongside classification tasks using quantum annealing based feature selection. Results demonstrate that hybrid quantum classical models achieve faster convergence rates and improved accuracy in high dimensional spaces compared to classical counterparts with the quantum algorithm for Max Cut optimization outperforming complete solution searches on larger problem instances. The findings provide machine learning practitioners and quantum computing researchers with validated hybrid architectures for near term quantum device deployment.

•Mar 13, 2026•0 citations

Quantum Machine Learning: Algorithms and Applications

Adewuyi Michael Oluwanifemi

Quantum machine learning (QML) represents a cutting-edge convergence of quantum computing and artificial intelligence, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance machine learning algorithms. By exploiting the computational advantages of quantum systems, QML offers the potential for exponential speedups in data processing, optimization, and pattern recognition tasks, particularly for high-dimensional and complex datasets. This article explores the foundational principles, algorithmic approaches, and practical applications of quantum machine learning across domains including finance, chemistry, drug discovery, optimization, and natural language processing. It discusses quantum-enhanced supervised and unsupervised learning, quantum neural networks, variational quantum algorithms, and hybrid quantum-classical architectures. Additionally, the article addresses challenges related to hardware limitations, noise, scalability, and interpretability, as well as the emerging trends in near-term quantum devices, quantum simulators, and integration with classical AI pipelines. Quantum machine learning holds the promise of revolutionizing computational intelligence, offering transformative capabilities for solving problems that are currently intractable for classical systems.

International Journal of Advance Industrial Engineering•Jun 30, 2024•0 citations

Advantage of quantum machine learning from general computational advantages

Hayata Yamasaki, Natsuto Isogai, Mio Murao

An overarching milestone of quantum machine learning (QML) is to demonstrate the advantage of QML over all possible classical learning methods in accelerating a common type of learning task, as represented by supervised learning from classical data. However, the provable advantages of QML in supervised learning have been known so far only for the learning tasks designed for using the advantage of specific quantum algorithms, i.e., Shor’s algorithms. Here, we explicitly construct an unprecedentedly broader family of supervised learning tasks with classical data to offer the provable advantage of QML based on general quantum computational advantages, progressing beyond Shor’s algorithms. Our learning task is feasibly achievable by executing a general class of functions that can be computed efficiently in polynomial time for a large fraction of inputs by arbitrary quantum algorithms, but not by any classical algorithm. We prove the hardness of achieving this learning task for any possible polynomial-time classical learning method. We also clarify protocols for preparing the classical data to demonstrate this learning task in experiments. These results provide a way to exploit a variety of quantum advantages in computing functions for the realization of provably advantageous QML.

arXiv:2312.03057•npj Quantum Information•Jul 28, 2026•19 citations
Abstract Quantum machine learning has the potential to improve traditional machine learning methods and overcome some of the main limitations imposed by the classical computing paradigm. However, the practical advantages of using quantum resources to solve pattern recognition tasks are still to be demonstrated. This work proposes a universal, efficient framework that can reproduce the output of a plethora of classical supervised machine learning algorithms exploiting quantum computation’s advantages. The proposed framework is namedMultiple Aggregator Quantum Algorithm(MAQA) due to its capability to combine multiple and diverse functions to solve typical supervised learning problems. In its general formulation, MAQA can be potentially adopted as the quantum counterpart of all those models falling into the scheme of aggregation of multiple functions, such as ensemble algorithms and neural networks. From a computational point of view, the proposed framework allows generating an exponentially large number of different transformations of the input at the cost of increasing the depth of the corresponding quantum circuit linearly. Thus, MAQA produces a model with substantial descriptive power to broaden the horizon of possible applications of quantum machine learning with a computational advantage over classical methods. As a second meaningful addition, we discuss the adoption of the proposed framework as hybrid quantum–classical and fault-tolerant quantum algorithm.
Quantum computation is an emerging computing paradigm with the potential to revolutionise the world of information technology. It leverages the laws of quantum mechanics to endow quantum machines with tremendous computing power, thus enabling the solution of problems impossible to address with classical devices. For this reason, the field is attracting ever-increasing attention from both academic and private sectors, and its full potential is still to be understood. This dissertation investigates how classical machine learning can benefit from quantum computing and provides several contributions to the emerging field of Quantum Machine Learning. \nThe idea is to provide a universal and efficient framework that can reproduce the output of a plethora of classical machine learning algorithms exploiting quantum computation’s advantages. The proposed framework is named Multiple Aggregator Quantum Algorithm (MAQA) due to its capability to combine multiple functions to solve typical supervised learning tasks. Thanks to this property, in its general formulation MAQA can be potentially adopted as the quantum counterpart of all those models falling into the scheme of aggregation of multiple functions. The theoretical design of the quantum algorithm and the corresponding circuit’s implementation are presented. As a second meaningful addition, two practical applications are illustrated: the quantum version of ensemble methods and neural networks. \nThe final contribution addresses the restriction to linear operations imposed by quantum mechanics. The idea is to exploit a quantum transposition of classical Splines to approximate non-linear functions, thus overcoming this limitation and introducing significant advantages in terms of computational complexity theory.
Humans are experts at recognising patterns in past experience and applying them to new tasks. \nFor example, after seeing pictures of a face we can usually tell if another image contains the \nsame person or not. Machine learning is a research discipline at the intersection of computer \nscience, statistics and mathematics that investigates how pattern recognition can be performed \nby machines and for large amounts of data. Since a few years machine learning has come \ninto the focus of quantum computing in which information processing based on the laws of \nquantum theory is explored. Although large scale quantum computers are still in the first stages \nof development, their theoretical description is well-understood and can be used to formulate \n`quantum software' or `quantum algorithms' for pattern recognition. Researchers can therefore \nanalyse the impact quantum computers may have on intelligent data mining. This approach is \npart of the emerging research discipline of quantum machine learning that harvests synergies \nbetween quantum computing and machine learning. \nThe research objective of this thesis is to understand how we can solve a slightly more specific \nproblem called supervised pattern recognition based on the language that has been developed \nfor universal quantum computers. The contribution it makes is twofold: First, it presents a \nmethodology that understands quantum machine learning as the combination of data encoding into \nquantum systems and quantum optimisation. Second, it proposes several quantum algorithms for \nsupervised pattern recognition. These include algorithms for convex and non-convex optimisation, \nimplementations of distance-based methods through quantum interference, and the preparation of \nquantum states from which solutions can be derived via sampling. Amongst the machine learning \nmethods considered are least-squares linear regression, gradient descent and Newton's method, \nk-nearest neighbour, neural networks as well as ensemble methods. Together with the growing \nbody of literature, this thesis demonstrates that quantum computing offers a number of interesting \ntools for machine learning applications, and has the potential to create new models of how to learn \nfrom data.
Quantum machine learning (QML) provides a transformative approach to data analysis by integrating the principles of quantum computing with classical machine learning methods. With the exponential growth of data and the increasing complexity of computational tasks, quantum algorithms offer tremendous advantages in terms of processing speed, memory efficiency, and the ability to resolve issues intractable for classical systems. In this work, the use of QML techniques for both supervised and unsupervised learning problems is explored. Quantum-enhanced models such Quantum Support Vector Machines (QSVMs) and Quantum Neural Networks (QNNs) show outstanding performance in classification and regression tasks by using quantum kernels and entanglement in supervised learning. Moreover, hybrid quantum-classical solutions offer useful implementations on noisy intermediate-scale quantum (NISQ) devices, hence bridging the gap between present quantum technology and practical uses. By means of comparative analysis, this paper emphasizes the possible benefits and drawbacks of QML, thereby providing understanding of its future importance in sectors including material science, finance, and healthcare. In the end, QML opens the path for a new era of intelligent data processing and solves until unthinkable difficult challenges.
Abstract This research presents a comprehensive hybrid quantum classical machine learning framework designed to overcome the computational limitations of classical algorithms when processing high dimensional data. The study integrates parameterized quantum circuits within classical neural network architectures and demonstrates their application across optimization tasks and supervised learning problems. The framework was evaluated on combinatorial optimization benchmarks including Max Cut and Job Shop Scheduling problems alongside classification tasks using quantum annealing based feature selection. Results demonstrate that hybrid quantum classical models achieve faster convergence rates and improved accuracy in high dimensional spaces compared to classical counterparts with the quantum algorithm for Max Cut optimization outperforming complete solution searches on larger problem instances. The findings provide machine learning practitioners and quantum computing researchers with validated hybrid architectures for near term quantum device deployment.
Quantum machine learning (QML) represents a cutting-edge convergence of quantum computing and artificial intelligence, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance machine learning algorithms. By exploiting the computational advantages of quantum systems, QML offers the potential for exponential speedups in data processing, optimization, and pattern recognition tasks, particularly for high-dimensional and complex datasets. This article explores the foundational principles, algorithmic approaches, and practical applications of quantum machine learning across domains including finance, chemistry, drug discovery, optimization, and natural language processing. It discusses quantum-enhanced supervised and unsupervised learning, quantum neural networks, variational quantum algorithms, and hybrid quantum-classical architectures. Additionally, the article addresses challenges related to hardware limitations, noise, scalability, and interpretability, as well as the emerging trends in near-term quantum devices, quantum simulators, and integration with classical AI pipelines. Quantum machine learning holds the promise of revolutionizing computational intelligence, offering transformative capabilities for solving problems that are currently intractable for classical systems.
An overarching milestone of quantum machine learning (QML) is to demonstrate the advantage of QML over all possible classical learning methods in accelerating a common type of learning task, as represented by supervised learning from classical data. However, the provable advantages of QML in supervised learning have been known so far only for the learning tasks designed for using the advantage of specific quantum algorithms, i.e., Shor’s algorithms. Here, we explicitly construct an unprecedentedly broader family of supervised learning tasks with classical data to offer the provable advantage of QML based on general quantum computational advantages, progressing beyond Shor’s algorithms. Our learning task is feasibly achievable by executing a general class of functions that can be computed efficiently in polynomial time for a large fraction of inputs by arbitrary quantum algorithms, but not by any classical algorithm. We prove the hardness of achieving this learning task for any possible polynomial-time classical learning method. We also clarify protocols for preparing the classical data to demonstrate this learning task in experiments. These results provide a way to exploit a variety of quantum advantages in computing functions for the realization of provably advantageous QML.