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

양자 기계 학습 모델에 의해 생성되는 함수 집합

신성욱

Published Jan 1, 2024• 0 citations
OpenAlex

Abstract

The advent of quantum computing has dramatically changed the field of human information processing technology. Simultaneously, machine learning algorithms have achieved remarkable success in various applications. In this context, integrating quantum computing with machine learning has gained attention, spurring investigations into its potential advantages over classical methods. To deepen our understanding of quantum machine learning, we analyze function classes generated by quantum machine learning models that utilize classical data. These include variational quantum circuits and quantum kernel models that can be efficiently implemented using quantum devices. We initially examine the dimensionality of the function classes of these quantum models, noting that their dimensions can be exponentially large while requiring only polynomial scaling of quantum resources. Using a tensor network framework, we identify that all variational quantum machine learning models are essentially linear models within a potentially exponentially large-dimensional feature space, where the feature map is derived from a tensor product. The coefficients of quantum models, determined by the data-independent part of the circuits, exhibit high entanglement with a small number of parameters. We apply a similar approach to reveal the function space of quantum kernel models, offering a novel perspective for their analysis. On the other hand, we introduce and explore the dequantizability of quantum machine learning models, which serves as a necessary condition for their replacement with efficient classical models. We determine the conditions for (non)dequantizable models and highlight the importance of analyzing the coefficient part of these models. This approach provides us insight into the potential limitations and strengths of quantum computing in the realm of machine learning.

Related papers

Dequantizing quantum machine learning models using tensor networks

Seongwook Shin, Yong Siah Teo, Hyunseok Jeong

Ascertaining whether a classical model can efficiently replace a given quantum model——is crucial in assessing the true potential of quantum algorithms. In this work, we introduced the dequantizability of the function class of variational quantum-machine-learning (VQML) models by employing the tensor network formalism, effectively identifying every VQML model as a subclass of matrix product state (MPS) model characterized by constrained coefficient MPS and tensor product-based feature maps. From this formalism, we identify the conditions for which a VQML model's function class is dequantizable or not. Furthermore, we introduce an efficient quantum kernel-induced classical kernel which is as expressive as given any quantum kernel, hinting at a possible way to dequantize quantum kernel methods. This presents a thorough analysis of VQML models and demonstrates the versatility of our tensor-network formalism to properly distinguish VQML models according to their genuine quantum characteristics, thereby unifying classical and quantum machine-learning models within a single framework. Published by the American Physical Society 2024

arXiv:2307.06937•Physical Review Research•May 29, 2024•38 citations

Quantum Circuit-Based Learning Models: Bridging Quantum Computing and Machine Learning

Fan Fan, Yilei Shi, Mihai Datcu +5 more

Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.

quant-pharXiv:2602.00048•Artificial Intelligence Review•Jan 20, 2026•2 citations

Quantum machine learning beyond kernel methods

Sofiène Jerbi, Lukas J. Fiderer, Hendrik Poulsen Nautrup +3 more

Machine learning algorithms based on parametrized quantum circuits are prime candidates for near-term applications on noisy quantum computers. In this direction, various types of quantum machine learning models have been introduced and studied extensively. Yet, our understanding of how these models compare, both mutually and to classical models, remains limited. In this work, we identify a constructive framework that captures all standard models based on parametrized quantum circuits: that of linear quantum models. In particular, we show using tools from quantum information theory how data re-uploading circuits, an apparent outlier of this framework, can be efficiently mapped into the simpler picture of linear models in quantum Hilbert spaces. Furthermore, we analyze the experimentally-relevant resource requirements of these models in terms of qubit number and amount of data needed to learn. Based on recent results from classical machine learning, we prove that linear quantum models must utilize exponentially more qubits than data re-uploading models in order to solve certain learning tasks, while kernel methods additionally require exponentially more data points. Our results provide a more comprehensive view of quantum machine learning models as well as insights on the compatibility of different models with NISQ constraints.

arXiv:2110.13162•Nature Communications•Jan 31, 2023•303 citations

Quantum Machine Learning in Feature Hilbert Spaces

Maria Schuld, Nathan Killoran

A basic idea of quantum computing is surprisingly similar to that of kernel methods in machine learning, namely, to efficiently perform computations in an intractably large Hilbert space. In this Letter we explore some theoretical foundations of this link and show how it opens up a new avenue for the design of quantum machine learning algorithms. We interpret the process of encoding inputs in a quantum state as a nonlinear feature map that maps data to quantum Hilbert space. A quantum computer can now analyze the input data in this feature space. Based on this link, we discuss two approaches for building a quantum model for classification. In the first approach, the quantum device estimates inner products of quantum states to compute a classically intractable kernel. The kernel can be fed into any classical kernel method such as a support vector machine. In the second approach, we use a variational quantum circuit as a linear model that classifies data explicitly in Hilbert space. We illustrate these ideas with a feature map based on squeezing in a continuous-variable system, and visualize the working principle with two-dimensional minibenchmark datasets.

arXiv:1803.07128•Physical Review Letters•Feb 1, 2019•2,212 citations

Applicability of quantum-enhanced machine learning (本文)

ユウダイ スズキ, Yudai Suzuki, 雄大 鈴木

Quantum computers are next-generation computing devices that have the potential to enhance the performance of machine learning.An approach to achieving quantum enhancement is to utilize the Hilbert space, whose dimension scales exponentially in the number of qubits, as a feature space for machine learning.The use of such quantum-enhanced feature space could enable us to find data patterns more easily than conventional methods.Thus far, it has been theoretically shown that quantum-enhanced machine learning models can solve specific classification tasks that classical methods cannot efficiently solve.This motivates many researchers to pursue practical advantages of the methods.Toward practical applications, it is critical to establish guidelines for designs of quantum-enhanced machine learning models.This thesis aims to analyze the performance of quantum-enhanced machine learning models and give insights into design principles of the models for practical applications.More specifically, we focus on two methods, quantum kernel methods and quantum reservoir computing, and then provide guidelines for building their models in practical situations.We focus on two challenges in quantum kernel methods for real-world applications.The first is that constructing quantum feature maps is nontrivial when applied to actual machine learning problems.This thesis proposes a method for analyzing quantum feature maps, which can help screen a suitable quantum feature map among many candidates.In addition, we examine the effectiveness of a synthesis method to construct a powerful quantum kernel.Another issue is that implementation feasibility and trainability deteriorate as the number of qubits increases.We thus propose a new quantum kernel called the quantum Fisher kernel and demonstrate from analytical and numerical perspectives that our proposal can avoid the aforementioned problem when shallow alternating layered ansatzes are used.In quantum reservoir computing, there is room for investigation in designing quantum reservoir systems that are amenable to implementation and can perform well.In this thesis, we propose a quantum reservoir computing framework that positively makes use of unavoidable quantum noise in actual quantum hardware.Our experimental demonstrations on superconducting quantum devices show that quantum noise can enhance temporal information processing.Also, numerical analysis using a tool called temporal information processing capacity elucidates that dissipation noise such as amplitude damping can induce sequential data processing capabilities.

•Jan 1, 2023•0 citations

Quantum Computing in Machine Learning: Performance Evaluation and Comparative Analysis

Simões, Jaime Marques

This thesis explores the integration of quantum computing into Machine Learning (ML), aiming to evaluate the effectiveness and limitations of quantum-enhanced models compared to classical approaches. As quantum technologies continue to develop, they offer the potential for solving complex computational problems more efficiently, particularly in fields requiring high-dimensional data processing. A literature review is conducted to contextualize current advancements in Quantum Machine Learning, highlighting theoretical benefits and existing practical limitations. This work investigates whether quantum methods, specifically the Quantum Support Vector Classifier (QSVC), can provide measurable improvements over its classical counterpart. The QSVC, implemented using IBM’s Qiskit ML library, replaces traditional kernel functions with quantum kernels computed via quantum circuits and feature maps, embedding classical data into a Hilbert space. The experimental portion of this thesis compares classical and quantum models on two distinct datasets: one from the healthcare domain and another from particle physics. Various parameters are tested in a constrained grid search due to the high computational demands of quantum circuits. Results indicate that while quantum models are significantly more resource-intensive, they can achieve comparable or even improved performance on data that has more complex relations between their variables. However, scalability remains a major challenge. This work concludes that although QSVC does not yet consistently outperform classical models, it offers advantages in specific contexts and lays the groundwork for identifying future use cases where quantum computing may offer a practical advantage in ML.

•Nov 6, 2025•0 citations
The advent of quantum computing has dramatically changed the field of human information processing technology. Simultaneously, machine learning algorithms have achieved remarkable success in various applications. In this context, integrating quantum computing with machine learning has gained attention, spurring investigations into its potential advantages over classical methods. To deepen our understanding of quantum machine learning, we analyze function classes generated by quantum machine learning models that utilize classical data. These include variational quantum circuits and quantum kernel models that can be efficiently implemented using quantum devices. We initially examine the dimensionality of the function classes of these quantum models, noting that their dimensions can be exponentially large while requiring only polynomial scaling of quantum resources. Using a tensor network framework, we identify that all variational quantum machine learning models are essentially linear models within a potentially exponentially large-dimensional feature space, where the feature map is derived from a tensor product. The coefficients of quantum models, determined by the data-independent part of the circuits, exhibit high entanglement with a small number of parameters. We apply a similar approach to reveal the function space of quantum kernel models, offering a novel perspective for their analysis. On the other hand, we introduce and explore the dequantizability of quantum machine learning models, which serves as a necessary condition for their replacement with efficient classical models. We determine the conditions for (non)dequantizable models and highlight the importance of analyzing the coefficient part of these models. This approach provides us insight into the potential limitations and strengths of quantum computing in the realm of machine learning.
Ascertaining whether a classical model can efficiently replace a given quantum model——is crucial in assessing the true potential of quantum algorithms. In this work, we introduced the dequantizability of the function class of variational quantum-machine-learning (VQML) models by employing the tensor network formalism, effectively identifying every VQML model as a subclass of matrix product state (MPS) model characterized by constrained coefficient MPS and tensor product-based feature maps. From this formalism, we identify the conditions for which a VQML model's function class is dequantizable or not. Furthermore, we introduce an efficient quantum kernel-induced classical kernel which is as expressive as given any quantum kernel, hinting at a possible way to dequantize quantum kernel methods. This presents a thorough analysis of VQML models and demonstrates the versatility of our tensor-network formalism to properly distinguish VQML models according to their genuine quantum characteristics, thereby unifying classical and quantum machine-learning models within a single framework. Published by the American Physical Society 2024
Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.
Machine learning algorithms based on parametrized quantum circuits are prime candidates for near-term applications on noisy quantum computers. In this direction, various types of quantum machine learning models have been introduced and studied extensively. Yet, our understanding of how these models compare, both mutually and to classical models, remains limited. In this work, we identify a constructive framework that captures all standard models based on parametrized quantum circuits: that of linear quantum models. In particular, we show using tools from quantum information theory how data re-uploading circuits, an apparent outlier of this framework, can be efficiently mapped into the simpler picture of linear models in quantum Hilbert spaces. Furthermore, we analyze the experimentally-relevant resource requirements of these models in terms of qubit number and amount of data needed to learn. Based on recent results from classical machine learning, we prove that linear quantum models must utilize exponentially more qubits than data re-uploading models in order to solve certain learning tasks, while kernel methods additionally require exponentially more data points. Our results provide a more comprehensive view of quantum machine learning models as well as insights on the compatibility of different models with NISQ constraints.
A basic idea of quantum computing is surprisingly similar to that of kernel methods in machine learning, namely, to efficiently perform computations in an intractably large Hilbert space. In this Letter we explore some theoretical foundations of this link and show how it opens up a new avenue for the design of quantum machine learning algorithms. We interpret the process of encoding inputs in a quantum state as a nonlinear feature map that maps data to quantum Hilbert space. A quantum computer can now analyze the input data in this feature space. Based on this link, we discuss two approaches for building a quantum model for classification. In the first approach, the quantum device estimates inner products of quantum states to compute a classically intractable kernel. The kernel can be fed into any classical kernel method such as a support vector machine. In the second approach, we use a variational quantum circuit as a linear model that classifies data explicitly in Hilbert space. We illustrate these ideas with a feature map based on squeezing in a continuous-variable system, and visualize the working principle with two-dimensional minibenchmark datasets.
Quantum computers are next-generation computing devices that have the potential to enhance the performance of machine learning.An approach to achieving quantum enhancement is to utilize the Hilbert space, whose dimension scales exponentially in the number of qubits, as a feature space for machine learning.The use of such quantum-enhanced feature space could enable us to find data patterns more easily than conventional methods.Thus far, it has been theoretically shown that quantum-enhanced machine learning models can solve specific classification tasks that classical methods cannot efficiently solve.This motivates many researchers to pursue practical advantages of the methods.Toward practical applications, it is critical to establish guidelines for designs of quantum-enhanced machine learning models.This thesis aims to analyze the performance of quantum-enhanced machine learning models and give insights into design principles of the models for practical applications.More specifically, we focus on two methods, quantum kernel methods and quantum reservoir computing, and then provide guidelines for building their models in practical situations.We focus on two challenges in quantum kernel methods for real-world applications.The first is that constructing quantum feature maps is nontrivial when applied to actual machine learning problems.This thesis proposes a method for analyzing quantum feature maps, which can help screen a suitable quantum feature map among many candidates.In addition, we examine the effectiveness of a synthesis method to construct a powerful quantum kernel.Another issue is that implementation feasibility and trainability deteriorate as the number of qubits increases.We thus propose a new quantum kernel called the quantum Fisher kernel and demonstrate from analytical and numerical perspectives that our proposal can avoid the aforementioned problem when shallow alternating layered ansatzes are used.In quantum reservoir computing, there is room for investigation in designing quantum reservoir systems that are amenable to implementation and can perform well.In this thesis, we propose a quantum reservoir computing framework that positively makes use of unavoidable quantum noise in actual quantum hardware.Our experimental demonstrations on superconducting quantum devices show that quantum noise can enhance temporal information processing.Also, numerical analysis using a tool called temporal information processing capacity elucidates that dissipation noise such as amplitude damping can induce sequential data processing capabilities.
This thesis explores the integration of quantum computing into Machine Learning (ML), aiming to evaluate the effectiveness and limitations of quantum-enhanced models compared to classical approaches. As quantum technologies continue to develop, they offer the potential for solving complex computational problems more efficiently, particularly in fields requiring high-dimensional data processing. A literature review is conducted to contextualize current advancements in Quantum Machine Learning, highlighting theoretical benefits and existing practical limitations. This work investigates whether quantum methods, specifically the Quantum Support Vector Classifier (QSVC), can provide measurable improvements over its classical counterpart. The QSVC, implemented using IBM’s Qiskit ML library, replaces traditional kernel functions with quantum kernels computed via quantum circuits and feature maps, embedding classical data into a Hilbert space. The experimental portion of this thesis compares classical and quantum models on two distinct datasets: one from the healthcare domain and another from particle physics. Various parameters are tested in a constrained grid search due to the high computational demands of quantum circuits. Results indicate that while quantum models are significantly more resource-intensive, they can achieve comparable or even improved performance on data that has more complex relations between their variables. However, scalability remains a major challenge. This work concludes that although QSVC does not yet consistently outperform classical models, it offers advantages in specific contexts and lays the groundwork for identifying future use cases where quantum computing may offer a practical advantage in ML.