Importance of Kernel Bandwidth in Quantum Machine Learning

TL;DR

This paper highlights the critical role of kernel bandwidth in quantum machine learning, demonstrating how its optimization enhances model expressivity, mitigates qubit decay issues, and improves performance relative to classical methods.

Contribution

It introduces the quantum kernel bandwidth hyperparameter, analyzes its impact on model behavior, and shows how optimizing it can improve quantum kernel performance with increasing qubit count.

Findings

Optimal bandwidth balances underfitting and overfitting.

Bandwidth optimization improves quantum kernel scalability.

Performance with optimized bandwidth surpasses unoptimized quantum kernels.

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.