Quantum Kernel Methods under Scrutiny: A Benchmarking Study

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.

20 pages main text including 9 figures and 1 table, appendix 18 pages with 22 figures and 2 tables; article in Quantum Machine Intelligence

References in corpus (20)

• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Quantum machine learning in feature Hilbert spaces
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum machine learning beyond kernel methods
• Quantum computing with Qiskit
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Modelling the influence of data structure on learning in neural networks: the hidden manifold model
• Automatic design of quantum feature maps
• Quantum machine learning of large datasets using randomized measurements
• Quantum Kernel Methods for Solving Differential Equations
• Alleviating Barren Plateaus in Parameterized Quantum Machine Learning Circuits: Investigating Advanced Parameter Initialization Strategies
• Reduction of finite sampling noise in quantum neural networks
• Numerical evidence against advantage with quantum fidelity kernels on classical data
• Quantum Advantage Seeker with Kernels (QuASK): a software framework to speed up the research in quantum machine learning
• A Hyperparameter Study for Quantum Kernel Methods
• Reinforcement learning-based architecture search for quantum machine learning

Cited by in corpus (4)

• On the similarity of bandwidth-tuned quantum kernels and classical kernels
• Quantum Kernel Methods: Convergence Theory, Separation Bounds and Applications to Marketing Analytics
• Predicting fermionic densities using a Projected Quantum Kernel method
• New perspectives on quantum kernels through the lens of entangled tensor kernels