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:2009.00298 · Physical Review Letters

Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces

Takahiro Goto, Quoc Hoan Tran, Kohei Nakajima

Published Aug 27, 2021• 123 citations
arXivHTMLPDF

Abstract

Encoding classical data into quantum states is considered a quantum feature map to map classical data into a quantum Hilbert space. This feature map provides opportunities to incorporate quantum advantages into machine learning algorithms to be performed on near-term intermediate-scale quantum computers. The crucial idea is using the quantum Hilbert space as a quantum-enhanced feature space in machine learning models. Although the quantum feature map has demonstrated its capability when combined with linear classification models in some specific applications, its expressive power from the theoretical perspective remains unknown. We prove that the machine learning models induced from the quantum-enhanced feature space are universal approximators of continuous functions under typical quantum feature maps. We also study the capability of quantum feature maps in the classification of disjoint regions. Our work enables an important theoretical analysis to ensure that machine learning algorithms based on quantum feature maps can handle a broad class of machine learning tasks. In light of this, one can design a quantum machine learning model with more powerful expressivity.

DOI
10.1103/physrevlett.127.090506

Related papers

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

Quantum Machine Learning: Leveraging Quantum Feature Maps for Enhanced Learning

Jincheng Zhang

This paper investigates the application of quantum feature maps in the context of quantum machine learning. The core claim is that effective quantum feature mapping can significantly improve the efficiency and accuracy of machine learning algorithms by transforming classical data into a quantum state representation. We propose a method for designing these feature maps, aiming to bridge the gap between classical and quantum data spaces. The central mechanism involves mapping classical data points to specific quantum states, subsequently leveraging quantum machine learning algorithms for training and prediction. This research contributes to the nascent field of quantum machine learning by exploring the potential of quantum feature maps as a foundational element for achieving enhanced learning capabilities. The study focuses on the theoretical foundations and design principles of these maps, without involving experimental validation.

•Aug 28, 2026•0 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 MACHINE LEARNING OVERVIEW

Sulekh Kumar, K. Krishna Kumari, Prabhat Purushottam +1 more

Quantum Machine Learning (QML) represents an emerging interdisciplinary field that harnesses quantum computing principles to enhance machine learning algorithms and develop quantum-native learning paradigms. This convergence exploits fundamental quantum mechanical phenomena superposition, entanglement, and quantum interference—to potentially achieve exponential computational advantages over classical approaches for specific algorithmic tasks. The theoretical foundation of QML rests on quantum systems' ability to encode information in exponentially scaling state spaces, enabling complex data representation in logarithmically fewer qubits compared to classical bits. Key quantum advantage mechanisms include quantum parallelism through superposition states, entanglement based correlations for efficient encoding of data relationships, and quantum interference effects that amplify optimal solutions while suppressing suboptimal ones. Contemporary QML approaches encompass several algorithmic frameworks. Variational Quantum Algorithms (VQAs) represent the most promising near-term strategy, utilizing hybrid quantum-classical optimization with parameterized quantum circuits optimized through classical feedback loops. Quantum Neural Networks extend classical architectures into quantum domains using trainable quantum gates, while quantum kernel methods leverage quantum feature maps to project data into high-dimensional Hilbert spaces for enhanced classification and regression tasks.

Iterative International Publishers eBooks•Jul 25, 2025•0 citations

Feature Map for Quantum Data in Classification

Hyeokjea Kwon, Hojun Lee, Joonwoo Bae

The kernel trick in supervised learning signifies transformations of an inner product by a feature map, which then restructures training data in a larger Hilbert space according to an endowed inner product. A quantum feature map corresponds to an instance with a Hilbert space of quantum states by fueling quantum resources to machine learning algorithms. In this work, we point out that the quantum state space is specific such that a measurement postulate characterizes an inner product and that manipulation of quantum states prepared from classical data cannot enhance the distinguishability of data points. We present a feature map for quantum data as a probabilistic manipulation of quantum states to improve supervised learning algorithms.

arXiv:2303.15665•International Conference on Quantum Communications, Networking, and Computing (QCNC)•Jul 1, 2024•8 citations

Benchmarking Quantum Machine Learning Kernel Training for Classification Tasks

Diego Álvarez-Estévez

Quantum-enhanced machine learning is a rapidly evolving field that aims to leverage the unique properties of quantum mechanics to enhance classical machine learning. However, the practical applicability of these methods remains an open question, particularly beyond the context of specifically crafted toy problems, and given the current limitations of quantum hardware. This study focuses on quantum kernel methods in the context of classification tasks. In particular, it examines the performance of quantum kernel estimation and quantum kernel training (QKT) in connection with two quantum feature mappings, namely, ZZFeatureMap and CovariantFeatureMap. Remarkably, these feature maps have been proposed in the literature under the conjecture of possible near-term quantum advantage and have shown promising performance in ad hoc datasets. This study aims to evaluate their versatility and generalization capabilities in a more general benchmark, encompassing both artificial and established reference datasets. Classical machine learning methods, specifically support vector machines and logistic regression, are also incorporated as baseline comparisons. Experimental results indicate that quantum methods exhibit varying performance across different datasets. Despite outperforming classical methods in ad hoc datasets, mixed results are obtained for the general case among standard classical benchmarks. The experimental data call into question a general added value of applying QKT optimization, for which the additional computational cost does not necessarily translate into improved classification performance. Instead, it is suggested that a careful choice of the quantum feature map in connection with proper hyperparameterization may prove more effective.

arXiv:2408.10274•IEEE Transactions on Quantum Engineering•Jan 1, 2025•52 citations
Encoding classical data into quantum states is considered a quantum feature map to map classical data into a quantum Hilbert space. This feature map provides opportunities to incorporate quantum advantages into machine learning algorithms to be performed on near-term intermediate-scale quantum computers. The crucial idea is using the quantum Hilbert space as a quantum-enhanced feature space in machine learning models. Although the quantum feature map has demonstrated its capability when combined with linear classification models in some specific applications, its expressive power from the theoretical perspective remains unknown. We prove that the machine learning models induced from the quantum-enhanced feature space are universal approximators of continuous functions under typical quantum feature maps. We also study the capability of quantum feature maps in the classification of disjoint regions. Our work enables an important theoretical analysis to ensure that machine learning algorithms based on quantum feature maps can handle a broad class of machine learning tasks. In light of this, one can design a quantum machine learning model with more powerful expressivity.
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.
This paper investigates the application of quantum feature maps in the context of quantum machine learning. The core claim is that effective quantum feature mapping can significantly improve the efficiency and accuracy of machine learning algorithms by transforming classical data into a quantum state representation. We propose a method for designing these feature maps, aiming to bridge the gap between classical and quantum data spaces. The central mechanism involves mapping classical data points to specific quantum states, subsequently leveraging quantum machine learning algorithms for training and prediction. This research contributes to the nascent field of quantum machine learning by exploring the potential of quantum feature maps as a foundational element for achieving enhanced learning capabilities. The study focuses on the theoretical foundations and design principles of these maps, without involving experimental validation.
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.
Quantum Machine Learning (QML) represents an emerging interdisciplinary field that harnesses quantum computing principles to enhance machine learning algorithms and develop quantum-native learning paradigms. This convergence exploits fundamental quantum mechanical phenomena superposition, entanglement, and quantum interference—to potentially achieve exponential computational advantages over classical approaches for specific algorithmic tasks. The theoretical foundation of QML rests on quantum systems' ability to encode information in exponentially scaling state spaces, enabling complex data representation in logarithmically fewer qubits compared to classical bits. Key quantum advantage mechanisms include quantum parallelism through superposition states, entanglement based correlations for efficient encoding of data relationships, and quantum interference effects that amplify optimal solutions while suppressing suboptimal ones. Contemporary QML approaches encompass several algorithmic frameworks. Variational Quantum Algorithms (VQAs) represent the most promising near-term strategy, utilizing hybrid quantum-classical optimization with parameterized quantum circuits optimized through classical feedback loops. Quantum Neural Networks extend classical architectures into quantum domains using trainable quantum gates, while quantum kernel methods leverage quantum feature maps to project data into high-dimensional Hilbert spaces for enhanced classification and regression tasks.
The kernel trick in supervised learning signifies transformations of an inner product by a feature map, which then restructures training data in a larger Hilbert space according to an endowed inner product. A quantum feature map corresponds to an instance with a Hilbert space of quantum states by fueling quantum resources to machine learning algorithms. In this work, we point out that the quantum state space is specific such that a measurement postulate characterizes an inner product and that manipulation of quantum states prepared from classical data cannot enhance the distinguishability of data points. We present a feature map for quantum data as a probabilistic manipulation of quantum states to improve supervised learning algorithms.
Quantum-enhanced machine learning is a rapidly evolving field that aims to leverage the unique properties of quantum mechanics to enhance classical machine learning. However, the practical applicability of these methods remains an open question, particularly beyond the context of specifically crafted toy problems, and given the current limitations of quantum hardware. This study focuses on quantum kernel methods in the context of classification tasks. In particular, it examines the performance of quantum kernel estimation and quantum kernel training (QKT) in connection with two quantum feature mappings, namely, ZZFeatureMap and CovariantFeatureMap. Remarkably, these feature maps have been proposed in the literature under the conjecture of possible near-term quantum advantage and have shown promising performance in ad hoc datasets. This study aims to evaluate their versatility and generalization capabilities in a more general benchmark, encompassing both artificial and established reference datasets. Classical machine learning methods, specifically support vector machines and logistic regression, are also incorporated as baseline comparisons. Experimental results indicate that quantum methods exhibit varying performance across different datasets. Despite outperforming classical methods in ad hoc datasets, mixed results are obtained for the general case among standard classical benchmarks. The experimental data call into question a general added value of applying QKT optimization, for which the additional computational cost does not necessarily translate into improved classification performance. Instead, it is suggested that a careful choice of the quantum feature map in connection with proper hyperparameterization may prove more effective.