Non-variational supervised quantum kernel methods: a review

2026-04-09

AI Summary

This work addresses non-variational supervised quantum kernel methods, aiming to circumvent gradient-based optimization challenges such as barren plateaus inherent in variational quantum algorithms and to investigate their provable quantum advantage. By decoupling a fixed quantum feature map from classical convex optimization, the approach encodes data into high-dimensional Hilbert spaces via quantum circuits and employs cross-validation for model selection. The study introduces a theoretical framework for assessing quantum advantage, clarifying scenarios where these methods may outperform classical models on structured problems. It integrates classical kernel theory, fidelity- and projector-based quantum kernel constructions, dequantization via tensor networks, and spectral analysis of kernel integral operators, supported by hardware experiments. The paper systematically summarizes the method’s theoretical foundations, generalization bounds, practical estimation techniques, necessary conditions for separation from classical models, and current technological limitations alongside future development pathways.

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.

Problem

• quantum kernel methods
• quantum advantage
• non-variational
• supervised quantum machine learning
• kernel methods

Innovation

• quantum kernel methods
• non-variational
• quantum feature maps
• classical convex optimisation
• quantum advantage