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:2604.07896

Non-variational supervised quantum kernel methods: a review

John Tanner, Chon-Fai Kam, Jingbo Wang

quant-phcs.LGSubmitted Apr 9, 2026• Announced Apr 10, 2026• 6 citations
arXivHTMLPDF

Abstract

Quantum kernel methods (QKMs) have emerged as a prominent framework for supervised quantum machine learning. Unlike variational quantum algorithms, which rely on gradient-based optimisation and may suffer from issues such as barren plateaus, non-variational QKMs employ fixed quantum feature maps, with model selection performed classically via convex optimisation and cross-validation. This separation of quantum feature embedding from classical training ensures stable optimisation while leveraging quantum circuits to encode data in high-dimensional Hilbert spaces. In this review, we provide a thorough analysis of non-variational supervised QKMs, covering their foundations in classical kernel theory, constructions of fidelity and projected quantum kernels, and methods for their estimation in practice. We examine frameworks for assessing quantum advantage, including generalisation bounds and necessary conditions for separation from classical models, and analyse key challenges such as exponential concentration, dequantisation via tensor-network methods, and the spectral properties of kernel integral operators. We further discuss structured problem classes that may enable advantage, and synthesise insights from comparative and hardware studies. Overall, this review aims to clarify the regimes in which QKMs may offer genuine advantages, and to delineate the conceptual, methodological, and technical obstacles that must be overcome for practical quantum-enhanced learning.

Comments
38 pages, 11 figures, 1 table

Related papers

Quantum Kernel Methods

Hamid D. Ismail

This chapter develops quantum kernel-based machine learning as one of the most mature and practically viable paradigms in quantum machine learning (QML). It explains how kernel methods separate quantum representation from classical learning, allowing quantum devices to define feature spaces through state preparation and kernel estimation while leaving optimization and inference to established classical algorithms. This hybrid structure makes quantum kernel methods especially well suited to near-term quantum hardware and provides a conceptually clean framework for studying the role of quantum-induced geometry in learning. This chapter examines the historical emergence of kernel methods in QML, their positioning relative to variational models, and the practical workflow of learning from precomputed quantum kernels. It then analyzes the issues of generalization, regularization, and kernel noise, showing how finite-shot estimation and hardware imperfections affect the learned geometry of the feature space. Two major models are developed in detail: quantum support vector machines (QSVMs), which perform margin maximization in quantum-induced Hilbert spaces, and quantum kernel ridge regression (QKRR), which provides a closed-form framework for studying stability and conditioning. Together, these models illustrate how quantum kernels can be integrated into standard classical learning pipelines while preserving both mathematical rigor and experimental feasibility.

CRC Press eBooks•Nov 4, 2026•0 citations

Quantum Machine Learning (QML): Variational Classifiers, Quantum Kernels and Hybrid Architectures

Vengathattil, Sunish

Quantum machine learning (QML) is an emerging interdisciplinary field which incorporates some features of quantum computing with machine learning. Quantum hardware development has sparked research interest for AI scientists because it gives capabilities in high-dimensional data processing and simultaneous operation execution. The investigation within this paper traces the main features of QML by reviewing variational quantum classifiers (VQCs) as well as quantum kernels and hybrid quantum-classical models. VQCs serve as quantum parameterized circuits whose optimization process with classical feedback achieves quantum superiority for classification applications. Quantum kernels expand Hilbert space features to improve traditional kernel methods, thus proving their functionality in quantum feature space. Hybrid approaches unite NISQ hardware with classical systems, which makes QML applicable to real-world applications right now. (Rietsche et al., 2022; Tychola et al., 2023) An analysis explores separate functions and combined effects of these components, which enhance model performance, extend generalization, and boost computational efficiency. The paper discusses necessary knowledge first, along with existing applications, before analyzing them against traditional methods. The paper reviews current QML tools while exploring their operational readiness as well as practical issues and deployment barriers for broader adoption. The paper conducts an in-depth investigation of significant limitations that include hardware noise alongside questions regarding scalability and interpretability. This paper shows how QML will transform machine learning applications through its review of obstacles that must be resolved to achieve its complete potential development. The study presents researchers and practitioners with an extensive comprehension of QML developments and emerging paths for this revolutionary field.

World Journal of Advanced Research and Reviews•Oct 31, 2025•0 citations

Supervised quantum machine learning models are kernel methods

Maria Schuld

With near-term quantum devices available and the race for fault-tolerant quantum computers in full swing, researchers became interested in the question of what happens if we replace a supervised machine learning model with a quantum circuit. While such "quantum models" are sometimes called "quantum neural networks", it has been repeatedly noted that their mathematical structure is actually much more closely related to kernel methods: they analyse data in high-dimensional Hilbert spaces to which we only have access through inner products revealed by measurements. This technical manuscript summarises and extends the idea of systematically rephrasing supervised quantum models as a kernel method. With this, a lot of near-term and fault-tolerant quantum models can be replaced by a general support vector machine whose kernel computes distances between data-encoding quantum states. Kernel-based training is then guaranteed to find better or equally good quantum models than variational circuit training. Overall, the kernel perspective of quantum machine learning tells us that the way that data is encoded into quantum states is the main ingredient that can potentially set quantum models apart from classical machine learning models.

arXiv:2101.11020•Jan 26, 2021•566 citations

Neural quantum kernels: Training quantum kernels with quantum neural networks

Pablo Rodriguez-Grasa, Yue Ban, Mikel Sanz

Quantum and classical machine learning have been naturally connected through kernel methods, which have also served as proof-of-concept for quantum advantage. Quantum embeddings encode classical data into quantum feature states, enabling the construction of embedding quantum kernels (EQKs) by measuring vector similarities and projected quantum kernels (PQKs) through projections of these states. However, in both approaches, the model is influenced by the choice of the embedding. In this work, we propose using the training of a quantum neural network (QNN) to construct neural quantum kernels, specifically neural EQKs and neural PQKs—problem-inspired kernel functions. Unlike previous approaches, our method requires the kernel matrix to be constructed only once, significantly reducing computational overhead. To achieve this, we introduce a scalable training method for an n -qubit data reuploading QNN. Furthermore, we demonstrate neural quantum kernels can alleviate exponential concentration and enhance generalization capabilities compared to problem-agnostic kernels, positioning them as a scalable and robust solution for quantum machine learning applications.

arXiv:2401.04642•Physical Review Research•May 20, 2025•30 citations

Quantum kernel methods under scrutiny: a benchmarking study

Jan Schnabel, Marco Roth

Abstract Since the entry of kernel theory in the field of quantum machine learning, quantum kernel methods (QKMs) have gained increasing attention with regard to both probing promising applications and delivering intriguing research insights. Benchmarking these methods is crucial to gain robust insights and to understand their practical utility. In this work, we present a comprehensive large-scale study examining QKMs based on fidelity quantum kernels (FQKs) and projected quantum kernels (PQKs) across a manifold of design choices. Our investigation encompasses both classification and regression tasks for five dataset families and 64 datasets, systematically comparing the use of FQKs and PQKs quantum support vector machines and kernel ridge regression. This resulted in over 20,000 models that were trained and optimized using a state-of-the-art hyperparameter search to ensure robust and comprehensive insights. We delve into the importance of hyperparameters on model performance scores and support our findings through rigorous correlation analyses. Additionally, we provide an in-depth analysis addressing the design freedom of PQKs and explore the underlying principles responsible for learning. Our goal is not to identify the best-performing model for a specific task but to uncover the mechanisms that lead to effective QKMs and reveal universal patterns.

arXiv:2409.04406•Quantum Machine Intelligence•Apr 24, 2025•84 citations

Applications of the Quantum Kernel Method on a Superconducting Quantum Processor

Evan Peters

The widespread benefits of classical machine learning along with promised speedups by quantum algorithms over their best performing classical counterparts have motivated development of quantum machine learning algorithms that combine these two approaches. Quantum Kernel Methods (QKMs) [22, 49] describe one such combination, which seeks to leverage the high dimensional Hilbert space over quantum states to perform classification on encoded classical data. In this work I present an analysis of QKM algorithms used to encode and classify real data using a quantum processor, aided by a suite of custom noise models and hardware optimizations. I introduce and validate techniques for error mitigation and readout error correction designed specifically for this algorithm/hardware combination. Though I do not achieve high accuracy with one type of QKM-based classifier, I provide evidence for possible fundamental limitations to the QKM as well as hardware limitations that are unaccounted for by a reasonable Markovian noise model.

•May 29, 2020•0 citations
Quantum kernel methods (QKMs) have emerged as a prominent framework for supervised quantum machine learning. Unlike variational quantum algorithms, which rely on gradient-based optimisation and may suffer from issues such as barren plateaus, non-variational QKMs employ fixed quantum feature maps, with model selection performed classically via convex optimisation and cross-validation. This separation of quantum feature embedding from classical training ensures stable optimisation while leveraging quantum circuits to encode data in high-dimensional Hilbert spaces. In this review, we provide a thorough analysis of non-variational supervised QKMs, covering their foundations in classical kernel theory, constructions of fidelity and projected quantum kernels, and methods for their estimation in practice. We examine frameworks for assessing quantum advantage, including generalisation bounds and necessary conditions for separation from classical models, and analyse key challenges such as exponential concentration, dequantisation via tensor-network methods, and the spectral properties of kernel integral operators. We further discuss structured problem classes that may enable advantage, and synthesise insights from comparative and hardware studies. Overall, this review aims to clarify the regimes in which QKMs may offer genuine advantages, and to delineate the conceptual, methodological, and technical obstacles that must be overcome for practical quantum-enhanced learning.
This chapter develops quantum kernel-based machine learning as one of the most mature and practically viable paradigms in quantum machine learning (QML). It explains how kernel methods separate quantum representation from classical learning, allowing quantum devices to define feature spaces through state preparation and kernel estimation while leaving optimization and inference to established classical algorithms. This hybrid structure makes quantum kernel methods especially well suited to near-term quantum hardware and provides a conceptually clean framework for studying the role of quantum-induced geometry in learning. This chapter examines the historical emergence of kernel methods in QML, their positioning relative to variational models, and the practical workflow of learning from precomputed quantum kernels. It then analyzes the issues of generalization, regularization, and kernel noise, showing how finite-shot estimation and hardware imperfections affect the learned geometry of the feature space. Two major models are developed in detail: quantum support vector machines (QSVMs), which perform margin maximization in quantum-induced Hilbert spaces, and quantum kernel ridge regression (QKRR), which provides a closed-form framework for studying stability and conditioning. Together, these models illustrate how quantum kernels can be integrated into standard classical learning pipelines while preserving both mathematical rigor and experimental feasibility.
Quantum machine learning (QML) is an emerging interdisciplinary field which incorporates some features of quantum computing with machine learning. Quantum hardware development has sparked research interest for AI scientists because it gives capabilities in high-dimensional data processing and simultaneous operation execution. The investigation within this paper traces the main features of QML by reviewing variational quantum classifiers (VQCs) as well as quantum kernels and hybrid quantum-classical models. VQCs serve as quantum parameterized circuits whose optimization process with classical feedback achieves quantum superiority for classification applications. Quantum kernels expand Hilbert space features to improve traditional kernel methods, thus proving their functionality in quantum feature space. Hybrid approaches unite NISQ hardware with classical systems, which makes QML applicable to real-world applications right now. (Rietsche et al., 2022; Tychola et al., 2023) An analysis explores separate functions and combined effects of these components, which enhance model performance, extend generalization, and boost computational efficiency. The paper discusses necessary knowledge first, along with existing applications, before analyzing them against traditional methods. The paper reviews current QML tools while exploring their operational readiness as well as practical issues and deployment barriers for broader adoption. The paper conducts an in-depth investigation of significant limitations that include hardware noise alongside questions regarding scalability and interpretability. This paper shows how QML will transform machine learning applications through its review of obstacles that must be resolved to achieve its complete potential development. The study presents researchers and practitioners with an extensive comprehension of QML developments and emerging paths for this revolutionary field.
With near-term quantum devices available and the race for fault-tolerant quantum computers in full swing, researchers became interested in the question of what happens if we replace a supervised machine learning model with a quantum circuit. While such "quantum models" are sometimes called "quantum neural networks", it has been repeatedly noted that their mathematical structure is actually much more closely related to kernel methods: they analyse data in high-dimensional Hilbert spaces to which we only have access through inner products revealed by measurements. This technical manuscript summarises and extends the idea of systematically rephrasing supervised quantum models as a kernel method. With this, a lot of near-term and fault-tolerant quantum models can be replaced by a general support vector machine whose kernel computes distances between data-encoding quantum states. Kernel-based training is then guaranteed to find better or equally good quantum models than variational circuit training. Overall, the kernel perspective of quantum machine learning tells us that the way that data is encoded into quantum states is the main ingredient that can potentially set quantum models apart from classical machine learning models.
Quantum and classical machine learning have been naturally connected through kernel methods, which have also served as proof-of-concept for quantum advantage. Quantum embeddings encode classical data into quantum feature states, enabling the construction of embedding quantum kernels (EQKs) by measuring vector similarities and projected quantum kernels (PQKs) through projections of these states. However, in both approaches, the model is influenced by the choice of the embedding. In this work, we propose using the training of a quantum neural network (QNN) to construct neural quantum kernels, specifically neural EQKs and neural PQKs—problem-inspired kernel functions. Unlike previous approaches, our method requires the kernel matrix to be constructed only once, significantly reducing computational overhead. To achieve this, we introduce a scalable training method for an n -qubit data reuploading QNN. Furthermore, we demonstrate neural quantum kernels can alleviate exponential concentration and enhance generalization capabilities compared to problem-agnostic kernels, positioning them as a scalable and robust solution for quantum machine learning applications.
Abstract Since the entry of kernel theory in the field of quantum machine learning, quantum kernel methods (QKMs) have gained increasing attention with regard to both probing promising applications and delivering intriguing research insights. Benchmarking these methods is crucial to gain robust insights and to understand their practical utility. In this work, we present a comprehensive large-scale study examining QKMs based on fidelity quantum kernels (FQKs) and projected quantum kernels (PQKs) across a manifold of design choices. Our investigation encompasses both classification and regression tasks for five dataset families and 64 datasets, systematically comparing the use of FQKs and PQKs quantum support vector machines and kernel ridge regression. This resulted in over 20,000 models that were trained and optimized using a state-of-the-art hyperparameter search to ensure robust and comprehensive insights. We delve into the importance of hyperparameters on model performance scores and support our findings through rigorous correlation analyses. Additionally, we provide an in-depth analysis addressing the design freedom of PQKs and explore the underlying principles responsible for learning. Our goal is not to identify the best-performing model for a specific task but to uncover the mechanisms that lead to effective QKMs and reveal universal patterns.
The widespread benefits of classical machine learning along with promised speedups by quantum algorithms over their best performing classical counterparts have motivated development of quantum machine learning algorithms that combine these two approaches. Quantum Kernel Methods (QKMs) [22, 49] describe one such combination, which seeks to leverage the high dimensional Hilbert space over quantum states to perform classification on encoded classical data. In this work I present an analysis of QKM algorithms used to encode and classify real data using a quantum processor, aided by a suite of custom noise models and hardware optimizations. I introduce and validate techniques for error mitigation and readout error correction designed specifically for this algorithm/hardware combination. Though I do not achieve high accuracy with one type of QKM-based classifier, I provide evidence for possible fundamental limitations to the QKM as well as hardware limitations that are unaccounted for by a reasonable Markovian noise model.