Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks
Abstract
For quantum machine learning, the exact boundary between classical and quantum advantage is still poorly understood. Direct comparison between quantum neural networks (QNNs) and existing classical models, which encompass fundamentally different function classes, often fails to provide broader insight into the difference between the two. Inspired by the techniques of Neural Quantum States and Random Fourier Features, this work introduces Neural Fourier Surrogates (NFS), a stochastic classical neural network architecture for efficiently learning coefficients over the same finite Fourier series support as quantum neural networks. Testing on a selection of tabular benchmark datasets, we find that NFS is an effective classifier architecture broadly competitive with established classical baselines, including a comparable Random Fourier Features model, and possessing comparable performance to data-reuploading QNNs; combined with additional analysis comparing the learned Fourier spectra of QNNs and NFS on synthetic data, these results establish NFS as a natural classical baseline for evaluating QNN performance.
Related
- Benchmarking Quantum Convolutional Neural Networks and their classical surrogates on long-range strongly correlated models
- Fourier-Geometric Circuit Design for Gate and Entanglement Placement in Quantum Neural Networks
- Polynomial neural surrogates for designing photonic quantum experiments
- 𝒪(n) alternative to Quantum Fourier Transform with efficient neural net classical post-processing
- Lazy training of quantum physics informed neural networks
BibTeX
@misc{knitter2026neural,
title = {{Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks}},
author = {Oliver Knitter and Jonathan Mei and Sang Hyub Kim and Chi Chen and Masako Yamada and Martin Roetteler},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.00841},
eprint = {2610.00841},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.00841},
}
RIS
TY - UNPB
TI - Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks
AU - Oliver Knitter
AU - Jonathan Mei
AU - Sang Hyub Kim
AU - Chi Chen
AU - Masako Yamada
AU - Martin Roetteler
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.00841
UR - https://arxiv.org/abs/2610.00841
AB - For quantum machine learning, the exact boundary between classical and quantum advantage is still poorly understood. Direct comparison between quantum neural networks (QNNs) and existing classical models, which encompass fundamentally different function classes, often fails to provide broader insight into the difference between the two. Inspired by the techniques of Neural Quantum States and Random Fourier Features, this work introduces Neural Fourier Surrogates (NFS), a stochastic classical neural network architecture for efficiently learning coefficients over the same finite Fourier series support as quantum neural networks. Testing on a selection of tabular benchmark datasets, we find that NFS is an effective classifier architecture broadly competitive with established classical baselines, including a comparable Random Fourier Features model, and possessing comparable performance to data-reuploading QNNs; combined with additional analysis comparing the learned Fourier spectra of QNNs and NFS on synthetic data, these results establish NFS as a natural classical baseline for evaluating QNN performance.
ER -