Fourier Fingerprints of Ansatzes in Quantum Machine Learning

TL;DR

This paper introduces Fourier fingerprints as a new tool to analyze and predict the performance of ansatzes in quantum machine learning, addressing the correlation structure of Fourier modes and improving ansatz selection.

Contribution

It demonstrates the existence of Fourier coefficient correlations in quantum ansatzes and introduces Fourier fingerprints to predict ansatz performance more effectively.

Findings

Fourier fingerprints reveal correlation structures in ansatzes.

FCC accurately predicts ansatz performance in learning Fourier series.

Framework applies to high-energy physics jet reconstruction.

Abstract

Typical schemes to encode classical data in variational quantum machine learning (QML) lead to quantum Fourier models with $\mathcal{O}(\exp(n))$ Fourier basis functions in the number of qubits. Despite this, in order for the model to be efficiently trainable, the number of parameters must scale as $\mathcal{O}(\mathrm{poly}(n))$. This imbalance implies the existence of correlations between the Fourier modes, which depend on the structure of the circuit. In this work, we demonstrate that this phenomenon exists and show cases where these correlations can be used to predict ansatz performance. For several popular ansatzes, we numerically compute the Fourier coefficient correlations (FCCs) and construct the Fourier fingerprint, a visual representation of the correlation structure. We subsequently show how, for the problem of learning random Fourier series, the FCC correctly predicts relative performance of ansatzes whilst the widely-used expressibility metric does not. Finally, we demonstrate how our framework applies to the more challenging problem of jet reconstruction in high-energy physics. Overall, our results demonstrate how the Fourier fingerprint is a powerful new tool in the problem of optimal ansatz choice for QML.