Importance of Kernel Bandwidth in Quantum Machine Learning

Abstract

Quantum kernel methods are considered a promising avenue for applying quantum computers to machine learning problems. Identifying hyperparameters controlling the inductive bias of quantum machine learning models is expected to be crucial given the central role hyperparameters play in determining the performance of classical machine learning methods. In this work we introduce the hyperparameter controlling the bandwidth of a quantum kernel and show that it controls the expressivity of the resulting model. We use extensive numerical experiments with multiple quantum kernels and classical datasets to show consistent change in the model behavior from underfitting (bandwidth too large) to overfitting (bandwidth too small), with optimal generalization in between. We draw a connection between the bandwidth of classical and quantum kernels and show analogous behavior in both cases. Furthermore, we show that optimizing the bandwidth can help mitigate the exponential decay of kernel values with qubit count, which is the cause behind recent observations that the performance of quantum kernel methods decreases with qubit count. We reproduce these negative results and show that if the kernel bandwidth is optimized, the performance instead improves with growing qubit count and becomes competitive with the best classical methods.

Camera-ready version

References in corpus (2)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Generalization in Quantum Machine Learning: a Quantum Information Perspective

Cited by in corpus (7)

• Unravelling physics beyond the standard model with classical and quantum anomaly detection
• Quantum Phase Recognition via Quantum Kernel Methods
• Quantum kernels to learn the phases of quantum matter
• Noisy Quantum Kernel Machines
• Numerical evidence against advantage with quantum fidelity kernels on classical data
• The role of entanglement for enhancing the efficiency of quantum kernels towards classification
• Reconstructing charged particle track segments with a quantum-enhanced support vector machine